Adversarial machine learning
The DOI matches its Crossref record; 192 of the 197 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
In this paper (expanded from an invited talk at AISEC 2010), we discuss an emerging field of study: adversarial machine learning---the study of effective machine learning techniques against an adversarial opponent. In this paper, we: give a taxonomy for classifying attacks against online machine learning algorithms; discuss application-specific factors that limit an adversary's capabilities; introduce two models for modeling an adversary's capabilities; explore the limits of an adversary's knowledge about the algorithm, feature space, training, and input data; explore vulnerabilities in machine learning algorithms; discuss countermeasures against attacks; introduce the evasion challenge; and discuss privacy-preserving learning techniques.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Indeed, models might not fail in obvious ways, or might even be subject to attacks designed to change them in targeted ways [41].”
From Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making (2018) · cites this paper as [41]
In the citing paper
“Second, many of the promising approaches to building safe AI rely on a lack of cooperation, such as adversarial training (Huang et al., 2011; Perez et al., 2022a; Ziegler et al., 2022) or scalable oversight (Christiano et al., 2018, 2021; Greenblatt et al., 2023; Irving et al., 2018; Leike et al., 2018).”
From Multi-Agent Risks from Advanced AI (2025) · cites this paper as Huang et al., 2011
In the citing paper
“Similarly, many of the more promising approaches to ensure the safety of advanced AI are implicitly multi-agent, such as adversarial training (Huang et al., 2011; Perez et al., 2022a; Ziegler et al., 2022), oversight schemes (Christiano et al., 2018, 2021; Greenblatt et al., 2023; Irving et al., 2018; Leike et al., 2018), the modularisation of agents (Dalrymple et al., 2024; Drexler, 2019), or”
From Multi-Agent Risks from Advanced AI (2025) · cites this paper as Huang et al., 2011
In the citing paper
“Many of the more promising approaches to ensuring the safety of advanced AI are implicitly multi-agent, such as adversarial training (Huang et al., 2011; Perez et al., 2022a; Ziegler et al., 2022), oversight schemes (Christiano et al., 2018, 2021; Greenblatt et al., 2023; Irving et al., 2018; Leike et al., 2018), the modularisation of agents (Dalrymple et al., 2024; Drexler, 2019), or automated”
From Multi-Agent Risks from Advanced AI (2025) · cites this paper as Huang et al., 2011
In the citing paper
“From the equation above, we can notice that solving for matrix Ω is not dependent on the data and therefore can be computed centrally; one major contribution of [15] is an efficient distributed optimization method for the W step.”
From Data Poisoning Attacks on Federated Machine Learning (2022) · cites this paper as [15]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
The Nature of Statistical Learning Theory
Vapnik, V. N. (1995) · doi:10.1007/978-1-4757-2440-0 · Cited by 39,138
A Simplex Method for Function Minimization
Nelder, J. A., & Mead, R. (1965) · The Computer Journal · doi:10.1093/comjnl/7.4.308 · Cited by 28,905
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 1×
“bounded PCA [36], anomaly detection algorithms that use hyper-sphere boundaries [5], one-class classifiers that predict anomalies by thresholding the log-likelihood of a log-concave (or uni-modal) density function, and some quadratic classifiers.”
MethodAdhi Harmoko, S., M.Komp, Jacquard, J. M., Zuse, K., & Eniac (2005) · Cited by 18,035
A Tutorial on Support Vector Machines for Pattern Recognition
Burges, C. J. C. (1998) · Data Mining and Knowledge Discovery · doi:10.1023/a:1009715923555 · Cited by 16,429
New directions in cryptography
Diffie, W., & Hellman, M. (1976) · IEEE Transactions on Information Theory · doi:10.1109/tit.1976.1055638 · Cited by 14,713
An Introduction to Support Vector Machines and Other Kernel-based Learning Methods
Cristianini, N., & Shawe-Taylor, J. (2000) · doi:10.1017/cbo9780511801389 · Cited by 13,855 · cited 13×
“5.1.1 Example: Private SVM Learning As a more practical example we have previously studied di.erentiallyprivate mechanismsforsupportvector machine (SVM) learning [56].”
BackgroundMethodInfluentialA method for obtaining digital signatures and public-key cryptosystems
Rivest, R. L., Shamir, A., & Adleman, L. (1983) · Communications of the ACM · doi:10.1145/357980.358017 · Cited by 13,012
LIII. On lines and planes of closest fit to systems of points in space
Pearson, K. (1901) · The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science · doi:10.1080/14786440109462720 · Cited by 11,934
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Schölkopf, B., & Smola, A. J. (2001) · The MIT Press eBooks · doi:10.7551/mitpress/4175.001.0001 · Cited by 11,703
Pattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
Communication Theory of Secrecy Systems
Shannon, C. E. (1949) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1949.tb00928.x · Cited by 9,440
k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
SWEENEY, L. (2002) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488502001648 · Cited by 8,571
(2006) · Springer eBooks · Cited by 8,123
Calibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272
Huber, P. J. (1981) · Wiley Series in Probability and Statistics · doi:10.1002/0471725250 · Cited by 7,066
Faires, J. D. (1978) · Cited by 6,711
Kernel Methods for Pattern Analysis
Shawe-Taylor, J., & Cristianini, N. (2004) · Cambridge University Press eBooks · doi:10.1017/cbo9780511809682 · Cited by 6,587
PE, & Billingsley, P. (1996) · Journal of the American Statistical Association · doi:10.2307/2291440 · Cited by 6,481
Face recognition: A literature survey
Zhao, W., Chellappa, R., Phillips, P. J., & Rosenfeld, A. (2003) · ACM Computing Surveys · doi:10.1145/954339.954342 · Cited by 6,163
Dwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291 · cited 13×
“[25] C. Dwork and S. Yekhanin.”
BackgroundMethodInfluentialJurafsky, D. S., & Martin, J. (2000) · Cited by 4,132
An Introduction to Support Vector Machines
Cristianini, N., & Shawe-Taylor, J. S. (2000) · ePrints Soton (University of Southampton) · Cited by 4,115
Robust Statistics: The Approach Based on Influence Functions
Ruppert, D. (1987) · Technometrics · doi:10.2307/1269782 · Cited by 3,880
L -diversity: Privacy beyond k -anonymity
Machanavajjhala, A., Kifer, D., Gehrke, J., & Venkitasubramaniam, M. (2007) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/1217299.1217302 · Cited by 3,617 · cited 1×
“Numerous definitions have been proposed and put aside due to the propositions being of a syntactic rather than semantic nature, most notably k-anonymity and its variants [61, 41].”
Backgroundt-Closeness: Privacy Beyond k-Anonymity and l-Diversity
Li, N., Li, T., & Venkatasubramanian, S. (2007) · 2007 IEEE 23rd International Conference on Data Engineering · doi:10.1109/icde.2007.367856 · Cited by 3,451
A Probabilistic Theory of Pattern Recognition
Devroye, L., Györfi, L., & Lugosi, G. (1996) · Stochastic Modelling and Applied Probability · doi:10.1007/978-1-4612-0711-5 · Cited by 3,274
Prediction, Learning, and Games
Cesa-Bianchi, N., & Lugosi, G. (2006) · Cambridge University Press eBooks · doi:10.1017/cbo9780511546921 · Cited by 3,162 · cited 1×
“Finally, iterative learning has an extensive theory for combining classifiers even under strong adversarial settings [9].”
BackgroundAlgorithms for Minimization Without Derivatives
G., D., & Brent, R. P. (1974) · Mathematics of Computation · doi:10.2307/2005713 · Cited by 2,847
Random Features for Large-Scale Kernel Machines
Rahimi, A., & Recht, B. (2007) · Cited by 2,783
Bro: a system for detecting network intruders in real-time
Paxson, V. (1999) · Computer Networks · doi:10.1016/s1389-1286(99)00112-7 · Cited by 2,636
Online and off-line handwriting recognition: a comprehensive survey
Plamondon, R., & Srihari, S. N. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.824821 · Cited by 2,498
Robust De-anonymization of Large Sparse Datasets
Narayanan, A., & Shmatikov, V. (2008) · 2008 IEEE Symposium on Security and Privacy (sp 2008) · doi:10.1109/sp.2008.33 · Cited by 2,372
A Taxonomy of Global Optimization Methods Based on Response Surfaces
Jones, D. R. (2001) · Journal of Global Optimization · doi:10.1023/a:1012771025575 · Cited by 2,159
Outside the Closed World: On Using Machine Learning for Network Intrusion Detection
Sommer, R., & Paxson, V. (2010) · 2010 IEEE Symposium on Security and Privacy · doi:10.1109/sp.2010.25 · Cited by 2,085
Lipschitzian optimization without the Lipschitz constant
Jones, D. R., Perttunen, C. D., & Stuckman, B. E. (1993) · Journal of Optimization Theory and Applications · doi:10.1007/bf00941892 · Cited by 1,976
The Weighted Majority Algorithm
Littlestone, N., & Warmuth, M. K. (1994) · Information and Computation · doi:10.1006/inco.1994.1009 · Cited by 1,975
Angluin, D. (1988) · Machine Learning · doi:10.1007/bf00116828 · Cited by 1,905
Parameterized Complexity Theory
(2006) · Texts in Theoretical Computer Science. An EATCS Series · doi:10.1007/3-540-29953-x · Cited by 1,869
(2006) · Spectral Interpretation of Decision Diagrams · doi:10.1007/0-387-21734-7_4 · Cited by 1,771
Robust Statistics: Theory and Methods
Maronna, R. A., Martin, R. D., & Yohai, V. J. (2006) · Cited by 1,715
Optimization by Direct Search: New Perspectives on Some Classical and Modern Methods
Kolda, T. G., Lewis, R. M., & Torczon, V. (2003) · SIAM Review · doi:10.1137/s003614450242889 · Cited by 1,653
Differentially Private Empirical Risk Minimization
Chaudhuri, K., Monteleoni, C., & Sarwate, A. (2009) · Journal of machine learning research · doi:10.5555/1953048.2021036 · Cited by 1,634 · cited 15×
“[10, 11] measure the utility of a differential private mechanism not by its approximation of a target non-private algorithm, but rather by the absolute error it achieves.”
BackgroundMethodInfluentialStatistical Fraud Detection: A Review
Bolton, R. J., & Hand, D. J. (2002) · Statistical Science · doi:10.1214/ss/1042727940 · Cited by 1,450
Incremental and Decremental Support Vector Machine Learning
Cauwenberghs, G., & Poggio, T. (2000) · neural information processing systems · Cited by 1,389
Mechanism Design via Differential Privacy
McSherry, F., & Talwar, K. (2007) · 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07) · doi:10.1109/focs.2007.66 · Cited by 1,371
Poisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331
Self-citationIntrusion detection using sequences of system calls
Hofmeyr, S. A., Forrest, S., & Somayaji, A. (1998) · Journal of Computer Security · doi:10.3233/jcs-980109 · Cited by 1,313
De-anonymizing Social Networks
Narayanan, A., & Shmatikov, V. (2009) · 2009 30th IEEE Symposium on Security and Privacy · doi:10.1109/sp.2009.22 · Cited by 1,301
Towards Sharp Inapproximability For Any 2-CSP
Austrin, P. (2007) · 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07) · doi:10.1109/focs.2007.41 · Cited by 1,294
Some results on Tchebycheffian spline functions
Kimeldorf, G., & Wahba, G. (1971) · Journal of Mathematical Analysis and Applications · doi:10.1016/0022-247x(71)90184-3 · Cited by 1,254
Control Procedures for Residuals Associated With Principal Component Analysis
Jackson, J. E., & Mudholkar, G. S. (1979) · Technometrics · doi:10.1080/00401706.1979.10489779 · Cited by 1,237
Homer, N., Szelinger, S., Redman, M., Duggan, D., Tembe, W., Muehling, J., Pearson, J. V., Stephan, D. A., Nelson, S. F., & Craig, D. W. (2008) · PLoS Genetics · doi:10.1371/journal.pgen.1000167 · Cited by 1,221
Bennett, J. R., & Lanning, S. (2007) · Cited by 1,216
Detecting intrusions using system calls: alternative data models
Warrender, C., Forrest, S., & Pearlmutter, B. (2003) · Proceedings of the 1999 IEEE Symposium on Security and Privacy (Cat. No.99CB36344) · doi:10.1109/secpri.1999.766910 · Cited by 1,106
Mining anomalies using traffic feature distributions
Lakhina, A., Crovella, M., & Diot, C. (2005) · Proceedings of the 2005 conference on Applications, technologies, architectures, and protocols for computer communications · doi:10.1145/1080091.1080118 · Cited by 1,054
Diagnosing network-wide traffic anomalies
Lakhina, A., Crovella, M., & Diot, C. (2004) · Proceedings of the 2004 conference on Applications, technologies, architectures, and protocols for computer communications · doi:10.1145/1015467.1015492 · Cited by 1,039 · cited 5×
“This assumption is empirically validated [36], but can be violated by a clever adversary as discussed below.”
BackgroundMethodInfluential(2011) · PubMed · Cited by 990 · cited 15×
“[10, 11] measure the utility of a differential private mechanism not by its approximation of a target non-private algorithm, but rather by the absolute error it achieves.”
BackgroundMethodInfluentialRevealing information while preserving privacy
Dinur, I., & Nissim, K. (2003) · Proceedings of the twenty-second ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems · doi:10.1145/773153.773173 · Cited by 980 · cited 9×
“[22] C. Dwork, F. McSherry, K. Nissim, and A. Smith.”
BackgroundInfluentialLess is More: Active Learning with Support Vector Machines
Schohn, G., & Cohn, D. A. (2000) · International Conference on Machine Learning · Cited by 901
Dalvi, N., Domingos, P., Mausam, Sanghai, S., & Verma, D. (2004) · Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1014052.1014066 · Cited by 887 · cited 2×
“exploit these costs to develop a cost-sensitive game-theoretic classification defense that is able to successfully detect optimal evasion of the original classifier [16].”
BackgroundA sense of self for Unix processes
Forrest, S., Hofmeyr, S. A., Somayaji, A., & Longstaff, T. A. (2002) · Proceedings 1996 IEEE Symposium on Security and Privacy · doi:10.1109/secpri.1996.502675 · Cited by 874
A firm foundation for private data analysis
Dwork, C. (2011) · Communications of the ACM · doi:10.1145/1866739.1866758 · Cited by 841 · cited 1×
“The most common approach to achieving differential privacy is to add noise to the target non-private mechanism’s response S(D), typically Laplace noise [22, 19, 6, 20, 56] but more generally an exponential mechanism is used to ran-”
MethodCan machine learning be secure?
Barreno, M., Nelson, B., Sears, R., Joseph, A. D., & Tygar, J. D. (2006) · Proceedings of the 2006 ACM Symposium on Information, computer and communications security · doi:10.1145/1128817.1128824 · Cited by 836 · cited 2×
“In prior work [2], we introduced a qualitative taxonomy of attacks against a machine learning system, which has since been extended to propose a framework for quantitatively evaluating security threats [37].”
BackgroundMethodSelf-citationThe security of machine learning
Barreno, M., Nelson, B., Joseph, A. D., & Tygar, J. D. (2010) · Machine Learning · doi:10.1007/s10994-010-5188-5 · Cited by 817
Self-citationIntrusion detection using neural networks and support vector machines
Mukkamala, S., Janoski, G., & Sung, A. (2003) · Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) · doi:10.1109/ijcnn.2002.1007774 · Cited by 814
Probability of Error for Optimal Codes in a Gaussian Channel
Shannon, C. E. (1959) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1959.tb03905.x · Cited by 807
Practical privacy: the SuLQ framework
Blum, A., Dwork, C., McSherry, F., & Nissim, K. (2005) · Proceedings of the twenty-fourth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems · doi:10.1145/1065167.1065184 · Cited by 797
Inferring Internet denial-of-service activity
Moore, D., Shannon, C., Brown, D. J., Voelker, G. M., & Savage, S. (2006) · ACM Transactions on Computer Systems · doi:10.1145/1132026.1132027 · Cited by 781
Lowd, D., & Meek, C. (2005) · Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining · doi:10.1145/1081870.1081950 · Cited by 755 · cited 11×
“[39] D. Lowd and C. Meek.”
BackgroundMethodInfluentialAutomatic analysis of malware behavior using machine learning
Rieck, K., Trinius, P., Willems, C., & Holz, T. (2011) · Journal of Computer Security · doi:10.3233/jcs-2010-0410 · Cited by 729
Mimicry attacks on host-based intrusion detection systems
Wagner, D., & Soto, P. (2002) · Proceedings of the 9th ACM conference on Computer and communications security · doi:10.1145/586110.586145 · Cited by 714 · cited 8×
“Independently, Wagner and Soto also developed mimicry attacks against pH, a sequence-based IDS [64].”
BackgroundInfluentialPolygraph: Automatically Generating Signatures for Polymorphic Worms
Newsome, J., Karp, B., & Song, D. (2005) · 2005 IEEE Symposium on Security and Privacy (S&P'05) · doi:10.1109/sp.2005.15 · Cited by 670
Differentially private recommender systems: Building privacy into the Netflix Prize contenders
McSherry, F., & Mironov, I. (2009) · Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1557019.1557090 · Cited by 664 · cited 2×
“Numerous other practical learning algorithms have been made differentially private including regularized logistic regression [10], several collaborative filtering algorithms [43],”
BackgroundMethodDifferential privacy and robust statistics
Dwork, C., & Lei, J. (2009) · Proceedings of the forty-first annual ACM symposium on Theory of computing · doi:10.1145/1536414.1536466 · Cited by 611 · cited 2×
“This definition has enjoyed a significant amount of interest in the Theory community [17, 6, 22, 19, 1, 7, 24, 23, 44, 33, 25, 21, 3, 31, 59] where the general consensus is that the formal definition is meaningful and appropriately strong, while allowing for statistical learning methods that preserve”
BackgroundKlimt, B., & Yang, Y. (2004) · Conference on Email and Anti-Spam · Cited by 575
An Analysis of the 1999 DARPA/Lincoln Laboratory Evaluation Data for Network Anomaly Detection
Mahoney, M. V., & Chan, P. K. (2003) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-45248-5_13 · Cited by 535 · cited 1×
“Feature deletion attacks instead specifically exclude high-value identifying features used by the detector [28]; this form of attack stresses the importance of proper feature selection as was also demonstrated empirically by [42] in their study of the behavior of intrusion detection systems on the DARPA/Lincoln Lab da…”
BackgroundPrivacy-preserving logistic regression
Chaudhuri, K., & Monteleoni, C. (2008) · Cited by 525
A learning theory approach to non-interactive database privacy
Blum, A., Ligett, K., & Roth, A. (2008) · Proceedings of the fortieth annual ACM symposium on Theory of computing · doi:10.1145/1374376.1374464 · Cited by 505 · cited 3×
“[7] whose mechanism releases anonymized data on which a class of analyses yield similar results as on the”
BackgroundResultExploiting machine learning to subvert your spam filter
Nelson, B. A., Barreno, M., Chi, F. J., Joseph, A. D., Rubinstein, B. I. P., Saini, U., Sutton, C. A., Tygar, J. D., & Xia, K. (2008) · Edinburgh Research Explorer (University of Edinburgh) · Cited by 481
Self-citationPrivacy, accuracy, and consistency too: a holistic solution to contingency table release
Barak, B., Chaudhuri, K., Dwork, C., Kale, S., McSherry, F., & Talwar, K. (2007) · Proceedings of the twenty-sixth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems · doi:10.1145/1265530.1265569 · Cited by 468
Robust statistics the approach based on influence functions
Hampel, F. R., Ronchetti, E. M., Rousseeuw, P. J., & Stahel, W. A. (1980) · Cited by 430
Characterization of network-wide anomalies in traffic flows
Lakhina, A., Crovella, M., & Diot, C. (2004) · Proceedings of the 4th ACM SIGCOMM conference on Internet measurement · doi:10.1145/1028788.1028813 · Cited by 421
Differentially Private Spatial Decompositions
Cormode, G., Procopiuc, C., Srivastava, D., Shen, E., & Yu, T. (2012) · 2012 IEEE 28th International Conference on Data Engineering · doi:10.1109/icde.2012.16 · Cited by 411
Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out Cross-Validation
Kearns, M., & Ron, D. (1999) · Neural Computation · doi:10.1162/089976699300016304 · Cited by 407
Robust Estimation of Dispersion Matrices and Principal Components
Devlin, S. J., Gnanadesikan, R., & Kettenring, J. R. (1981) · Journal of the American Statistical Association · doi:10.1080/01621459.1981.10477654 · Cited by 391
On‐Line Portfolio Selection Using Multiplicative Updates
Helmbold, D. P., Schapire, R. E., Singer, Y., & Warmuth, M. K. (1998) · Mathematical Finance · doi:10.1111/1467-9965.00058 · Cited by 387
Measurements and mitigation of peer-to-peer-based botnets: a case study on storm worm
Holz, T., Steiner, M., Dahl, F., Biersack, E. W., & Freiling, F. (2008) · Cited by 383
Resilient aggregation in sensor networks
Wagner, D. (2004) · Proceedings of the 2nd ACM workshop on Security of ad hoc and sensor networks · doi:10.1145/1029102.1029116 · Cited by 378
The Mathematics of Nonlinear Programming
Peressini, A. L., Uhl, J. J., & Sullivan, F. E. (1988) · Undergraduate Texts in Mathematics · doi:10.1007/978-1-4612-1025-2 · Cited by 374
Towards highly reliable enterprise network services via inference of multi-level dependencies
Bahl, P., Chandra, R., Greenberg, A., Kandula, S., Maltz, D. A., & Zhang, M. (2007) · Proceedings of the 2007 conference on Applications, technologies, architectures, and protocols for computer communications · doi:10.1145/1282380.1282383 · Cited by 369
On the complexity of differentially private data release: efficient algorithms and hardness results
Dwork, C., Naor, M., Reingold, O., Rothblum, G. N., & Vadhan, S. (2009) · Proceedings of the forty-first annual ACM symposium on Theory of computing · doi:10.1145/1536414.1536467 · Cited by 358
Sensitivity of PCA for traffic anomaly detection
Ringberg, H., Soule, A., Rexford, J., & Diot, C. (2007) · Proceedings of the 2007 ACM SIGMETRICS international conference on Measurement and modeling of computer systems · doi:10.1145/1254882.1254895 · Cited by 353
Functional mechanism: regression analysis under differential privacy
Zhang, J., Zhang, Z., Xiao, X., Yang, Y., & Winslett, M. (2012) · Proceedings of the VLDB Endowment · doi:10.14778/2350229.2350253 · Cited by 345
Learning in the Presence of Malicious Errors
Kearns, M., & Li, M. (1993) · SIAM Journal on Computing · doi:10.1137/0222052 · Cited by 340
Kasiviswanathan, S. P., Lee, H. K., Nissim, K., Raskhodnikova, S., & Smith, A. (2008) · 2008 49th Annual IEEE Symposium on Foundations of Computer Science · doi:10.1109/focs.2008.27 · Cited by 334
ANTIDOTE: understanding and defending against poisoning of anomaly detectors
Rubinstein, B. I. P., Nelson, B., Huang, L., Joseph, A. D., Lau, S.-H., Rao, S., Taft, N., & Tygar, J. D. (2009) · Proceedings of the 9th ACM SIGCOMM conference on Internet measurement · doi:10.1145/1644893.1644895 · Cited by 331
Self-citationHigh breakdown estimators for principal components: the projection-pursuit approach revisited
Croux, C., & Ruiz-Gazen, A. (2005) · Journal of Multivariate Analysis · doi:10.1016/j.jmva.2004.08.002 · Cited by 328
Learning nonstationary models of normal network traffic for detecting novel attacks
Mahoney, M. V., & Chan, P. K. (2002) · Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/775047.775102 · Cited by 321
Good Word Attacks on Statistical Spam Filters.
Lowd, D., & Meek, C. (2005) · Conference on Email and Anti-Spam · Cited by 316
Li, G., & Chen, Z. (1985) · Journal of the American Statistical Association · doi:10.1080/01621459.1985.10478181 · Cited by 314
On the geometry of differential privacy
Hardt, M., & Talwar, K. (2010) · Proceedings of the forty-second ACM symposium on Theory of computing · doi:10.1145/1806689.1806786 · Cited by 314 · cited 2×
“the notion of privacy to be of practical use [56, 43, 1, 33, 17, 25, 3, 31, 11].”
BackgroundNightmare at test time: robust learning by feature deletion
Globerson, A., & Roweis, S. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143889 · Cited by 309 · cited 1×
“Feature deletion attacks instead specifically exclude high-value identifying features used by the detector [28]; this form of attack stresses the importance of proper feature selection as was also demonstrated empirically by [42] in their study of the behavior of intrusion detection systems on the DARPA/Lincoln Lab da…”
BackgroundAlgorithms for Projection–Pursuit robust principal component analysis
Croux, C., Filzmoser, P., & Oliveira, M. R. (2007) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2007.01.004 · Cited by 285
A simple and practical algorithm for differentially private data release
Hardt, M., Ligett, K., & McSherry, F. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1012.4763 · Cited by 283
Filtering spam with behavioral blacklisting
Ramachandran, A., Feamster, N., & Vempala, S. (2007) · Proceedings of the 14th ACM conference on Computer and communications security · doi:10.1145/1315245.1315288 · Cited by 264
Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM Learning
Rubinstein, B. I. P., Bartlett, P. L., Huang, L., & Taft, N. (2012) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.v4i1.612 · Cited by 262
Self-citationCombining Filtering and Statistical Methods for Anomaly Detection
Soule, A., Salamatian, K., & Taft, N. (2005) · HAL · Cited by 261
Goldman, S. A., & Kearns, M. J. (1995) · Journal of Computer and System Sciences · doi:10.1006/jcss.1995.1003 · Cited by 257
Anomalous system call detection
Mutz, D., Valeur, F., Vigna, G., & Kruegel, C. (2006) · ACM Transactions on Information and System Security · doi:10.1145/1127345.1127348 · Cited by 251
Privacy-preserving statistical estimation with optimal convergence rates
Smith, A. (2011) · Proceedings of the forty-third annual ACM symposium on Theory of computing · doi:10.1145/1993636.1993743 · Cited by 251 · cited 2×
“Numerous other practical learning algorithms have been made differentially private including regularized logistic regression [10], several collaborative filtering algorithms [43], point estimation [59], nearest neighbor, histograms, perceptron [6], and more.”
BackgroundMethodAutomated response using system-call delays
Somayaji, A. B., & Forrest, S. (2000) · Cited by 247
Solving convex programs by random walks
Bertsimas, D., & Vempala, S. (2004) · Journal of the ACM · doi:10.1145/1008731.1008733 · Cited by 242
Simulated annealing in convex bodies and an O*(n4) volume algorithm
Lovász, L., & Vempala, S. (2006) · Journal of Computer and System Sciences · doi:10.1016/j.jcss.2005.08.004 · Cited by 239
Detection and identification of network anomalies using sketch subspaces
Li, X., Bian, F., Crovella, M., Diot, C., Govindan, R., Iannaccone, G., & Lakhina, A. (2006) · Proceedings of the 6th ACM SIGCOMM conference on Internet measurement · doi:10.1145/1177080.1177099 · Cited by 232
Distribution-free performance bounds for potential function rules
Devroye, L., & Wagner, T. (1979) · IEEE Transactions on Information Theory · doi:10.1109/tit.1979.1056087 · Cited by 226
Analysis of Perceptron-Based Active Learning
Dasgupta, S., Kalai, A. T., & Monteleoni, C. (2005) · Lecture Notes in Computer Science · doi:10.1007/11503415_17 · Cited by 214
Undermining an Anomaly-Based Intrusion Detection System Using Common Exploits
Tan, K. M. C., Killourhy, K. S., & Maxion, R. A. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-36084-0_4 · Cited by 212 · cited 8×
“Several authors have further explored evasion techniques used by spammers and demonstrated attacks against spam .lters using similar principles as those against IDSs as discussed above.”
BackgroundInfluentialZhang⋆, Y., Ge, Z., Greenberg, A. G., & Roughan, M. (2005) · doi:10.5555/1251086.1251116 · Cited by 209
Characterizing, modeling, and generating workload spikes for stateful services
Bodik, P., Fox, A., Franklin, M. J., Jordan, M. I., & Patterson, D. A. (2010) · Proceedings of the 1st ACM symposium on Cloud computing · doi:10.1145/1807128.1807166 · Cited by 207
The price of privacy and the limits of LP decoding
Dwork, C., McSherry, F., & Talwar, K. (2007) · Proceedings of the thirty-ninth annual ACM symposium on Theory of computing · doi:10.1145/1250790.1250804 · Cited by 205 · cited 1×
“This definition has enjoyed a significant amount of interest in the Theory community [17, 6, 22, 19, 1, 7, 24, 23, 44, 33, 25, 21, 3, 31, 59] where the general consensus is that the formal definition is meaningful and appropriately strong, while allowing for statistical learning methods that preserve”
BackgroundLearning Fast Classifiers for Image Spam.
Dredze, M. H., Gevaryahu, R., & Elias-Bachrach, A. (2007) · Conference on Email and Anti-Spam · Cited by 201
Statistical machine learning makes automatic control practical for internet datacenters
Bodík, P., Griffith, R., Sutton, C. A., Fox, A., Jordan, M. I., & Patterson, D. A. (2009) · Cited by 198
In-Network PCA and Anomaly Detection
Huang, L., Nguyen, X., Garofalakis, M., Jordan, M. I., Joseph, A., & Taft, N. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0082 · Cited by 196
Self-citationParagraph: Thwarting Signature Learning by Training Maliciously
Newsome, J., Karp, B., & Song, D. (2006) · Lecture Notes in Computer Science · doi:10.1007/11856214_5 · Cited by 193
Principal Components and Orthogonal Regression Based on Robust Scales
Maronna, R. (2005) · Technometrics · doi:10.1198/004017005000000166 · Cited by 192
Denning, D. E., & Denning, P. J. (1979) · ACM Computing Surveys · doi:10.1145/356778.356782 · Cited by 189
On Attacking Statistical Spam Filters.
Wittel, G. L., & Wu, S. F. (2004) · Cited by 180
Applying PCA for Traffic Anomaly Detection: Problems and Solutions
Brauckhoff, D., Salamatian, K., & May, M. (2009) · IEEE INFOCOM 2009 · doi:10.1109/infcom.2009.5062248 · Cited by 179
Online Anomaly Detection under Adversarial Impact
Kloft, M., & Laskov, P. (2010) · International Conference on Artificial Intelligence and Statistics · Cited by 177
Link prediction by de-anonymization: How We Won the Kaggle Social Network Challenge
Narayanan, A., Shi, E., & Rubinstein, B. I. P. (2011) · The 2011 International Joint Conference on Neural Networks · doi:10.1109/ijcnn.2011.6033446 · Cited by 176
Self-citationEvading network anomaly detection systems: formal reasoning and practical techniques
Fogla, P., & Lee, W. (2006) · Proceedings of the 13th ACM conference on Computer and communications security · doi:10.1145/1180405.1180414 · Cited by 157
Secure multiple linear regression based on homomorphic encryption
Hall, R., Fienberg, S. E., & Nardi, Y. (2011) · Journal of Official Statistics · Cited by 143
Efficient algorithms for universal portfolios
Kalai, A. T., & Vempala, S. (2002) · Annual Symposium on Foundations of Computer Science · doi:10.1109/sfcs.2000.892136 · Cited by 143
Misleading Learners: Co-opting Your Spam Filter
Nelson, B. A., Barreno, M., Chi, F. J., Joseph, A. D., Rubinstein, B. I. P., Saini, U., Sutton, C. A., Tygar, J. D., & Xia, K. (2009) · Springer eBooks · doi:10.1007/978-0-387-88735-7_2 · Cited by 137 · cited 2×
“We now describe two attacks that we studied in prior work [47, 48, 57], and subsequently we discuss general perspectives and guidelines we developed for analyzing”
BackgroundMethodSelf-citationSpamBayes: Effective open-source, Bayesian based, email classification system.
Meyer, T., & Whateley, B. (2004) · Conference on Email and Anti-Spam · Cited by 128
A statistical approach to the spam problem
Robinson, G. S. (2003) · Linux journal · doi:10.5555/636750.636753 · Cited by 128
Machine learning in adversarial environments
Laskov, P., & Lippmann, R. (2010) · Machine Learning · doi:10.1007/s10994-010-5207-6 · Cited by 126
Differential Privacy for Functions and Functional DataPreprint
HallRob, RinaldoAlessandro, & WassermanLarry (2010) · arXiv (Cornell University) · doi:10.1184/r1/6586565 · Cited by 125
Capabilities of Bounded Discrepancy Decoding
Wyner, A. D. (1965) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1965.tb04170.x · Cited by 124
Behavior-based modeling and its application to Email analysis
Stolfo, S. J., Hershkop, S., Hu, C.-W., Li, W., Nimeskern, O., & Wang, K. (2006) · ACM Transactions on Internet Technology · doi:10.1145/1149121.1149125 · Cited by 120
Bounds on the Sample Complexity for Private Learning and Private Data Release
Beimel, A., Kasiviswanathan, S. P., & Nissim, K. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-11799-2_26 · Cited by 119
Automating cross-layer diagnosis of enterprise wireless networks
Cheng, Y.-C., Afanasyev, M., Verkaik, P., Benkö, P., Chiang, J., Snoeren, A. C., Savage, S., & Voelker, G. M. (2007) · Proceedings of the 2007 conference on Applications, technologies, architectures, and protocols for computer communications · doi:10.1145/1282380.1282384 · Cited by 115
Hössjer, O., & Croux, C. (1995) · Journal of nonparametric statistics · doi:10.1080/10485259508832620 · Cited by 110
On Robustness Properties of Convex Risk Minimization Methods for Pattern Recognition
Christmann, A., & Steinwart, I. (2003) · RePEc: Research Papers in Economics · doi:10.17877/de290r-15035 · Cited by 110
Language models for detection of unknown attacks in network traffic
Rieck, K., & Laskov, P. (2006) · Journal of Computer Virology and Hacking Techniques · doi:10.1007/s11416-006-0030-0 · Cited by 105
Filtering Image Spam with Near-Duplicate Detection.
Wang, Z., Josephson, W. K., Lv, Q., Charikar, M., & Li, K. (2007) · Cited by 101
New Efficient Attacks on Statistical Disclosure Control Mechanisms
Dwork, C., & Yekhanin, S. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85174-5_26 · Cited by 100 · cited 2×
“the notion of privacy to be of practical use [56, 43, 1, 33, 17, 25, 3, 31, 11].”
BackgroundLower Bounds in Differential Privacy
De, A. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-28914-9_18 · Cited by 98
Query Strategies for Evading Convex-Inducing Classifiers
Nelson, B. A., Rubinstein, B. I. P., Huang, L., Joseph, A. D., Lee, S. J., Rao, S. B., & Tygar, J. D. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1007.0484 · Cited by 94
Self-citationDetecting adversarial advertisements in the wild
Sculley, D., Otey, M. E., Pohl, M., Spitznagel, B., Hainsworth, J., & Zhou, Y. (2011) · Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2020408.2020455 · Cited by 93
Classifier evaluation and attribute selection against active adversaries
Kantarcıoğlu, M., Xi, B., & Clifton, C. (2010) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-010-0197-3 · Cited by 93 · cited 1×
“Subsequent game theoretic approaches to learning have extended this setting and solved for equilibria of the game [8, 32].”
BackgroundNash Equilibria of Static Prediction Games
Brückner, M., & Scheffer, T. (2009) · neural information processing systems · Cited by 85
Spam Corpus Creation for TREC.
Cormack, G. V., & Lynam, T. R. (2005) · Cited by 84
What's going on? learning communication rules in edge networks
Kandula, S., Chandra, R., & Katabi, D. (2008) · ACM SIGCOMM Computer Communication Review · doi:10.1145/1402946.1402970 · Cited by 84
Hiding Intrusions: From the Abnormal to the Normal and Beyond
Tan, K. M. C., McHugh, J., & Killourhy, K. S. (2002) · Lecture notes in computer science · doi:10.1007/3-540-36415-3_1 · Cited by 83
Security Analysis of Online Centroid Anomaly Detection
Kloft, M., & Laskov, P. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1003.0078 · Cited by 79
Smith, R. L. (1996) · Winter Simulation Conference · doi:10.1145/256562.256619 · Cited by 68
P4P: practical large-scale privacy-preserving distributed computation robust against malicious users
Duan, Y., Canny, J., & Zhan, J. (2010) · USENIX Security Symposium · Cited by 65
Stealthy poisoning attacks on PCA-based anomaly detectors
Rubinstein, B. I. P., Nelson, B., Huang, L., Joseph, A. D., Lau, S.-H., Rao, S., Taft, N., & Tygar, J. D. (2009) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/1639562.1639592 · Cited by 62
Self-citationRobust detection of comment spam using entropy rate
Kantchelian, A., Ma, J. H., Huang, L., Afroz, S., Joseph, A. D., & Tygar, J. D. (2012) · ACM Workshop on Artificial Intelligence and Security (AISec) · doi:10.1145/2381896.2381907 · Cited by 62
Self-citationA framework for quantitative security analysis of machine learning
Laskov, P., & Kloft, M. (2009) · Proceedings of the 2nd ACM workshop on Security and artificial intelligence · doi:10.1145/1654988.1654990 · Cited by 62 · cited 1×
“In prior work [2], we introduced a qualitative taxonomy of attacks against a machine learning system, which has since been extended to propose a framework for quantitatively evaluating security threats [37].”
MethodSpamGuru: An Enterprise Anti-Spam Filtering System.
Segal, R. B., Crawford, J., Kephart, J. O., & Leiba, B. (2004) · Conference on Email and Anti-Spam · Cited by 59
Allergy Attack Against Automatic Signature Generation
Chung, S. P. H., & Mok, A. K. (2006) · Lecture notes in computer science · doi:10.1007/11856214_4 · Cited by 59 · cited 1×
“Chung and Mok also developed allergy attacks against the Autograph worm signature generation system [12, 13].”
BackgroundLovász, L., & Vempala, S. (2004) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/1007352.1007403 · Cited by 57
Multiple Classifier Systems under Attack
Biggio, B., Fumera, G., & Roli, F. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-12127-2_8 · Cited by 55 · cited 1×
“promote randomized classifiers as a defense against exploratory evasion [4].”
BackgroundPrivacy Violations Using Microtargeted Ads: A Case Study
Korolova, A. (2011) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.v3i1.594 · Cited by 55
Fighting unicode-obfuscated spam
Liu, C., & Stamm, S. (2007) · doi:10.1145/1299015.1299020 · Cited by 53 · cited 1×
“longer recognized by the filter) is another popular technique for evading spam filters [38, 58].”
MethodClassifier Evasion: Models and Open Problems
Nelson, B. A., Rubinstein, B. I. P., Huang, L., Joseph, A. D., & Tygar, J. D. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19896-0_8 · Cited by 51 · cited 1×
“While we have suspected randomization could prove beneficial to fighting attacks that violate integrity or availability [51], few positive results are known.”
BackgroundSelf-citationOn The Power of Membership Queries in Agnostic Learning
Feldman, V. (2008) · Cited by 51
Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM LearningPreprint
Rubinstein, B. I. P., Bartlett, P. L., Huang, L., et al. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0911.5708 · Cited by 51
Self-citationLimits of Learning-Based Signature Generation with Adversaries
Venkataraman, S., Blum, A. L., & Song, D. X. (2018) · Figshare · doi:10.1184/r1/6468965 · Cited by 50
A Learning-Based Approach to Reactive Security
Barth, A., Rubinstein, B. I. P., Sundararajan, M., Mitchell, J. C., Song, D. X., & Bartlett, P. L. (2011) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2011.42 · Cited by 47
Self-citationNear-Optimal Evasion of Convex-Inducing ClassifiersPreprint
Nelson, B. A., Rubinstein, B. I. P., Huang, L., Joseph, A. D., Lau, S.-H., Lee, S. J., Rao, S. B., Tran, A., & Tygar, J. D. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1003.2751 · Cited by 45 · cited 2×
“In the next section we discuss our extension to this framework [50].”
BackgroundSelf-citationStatistical Methods in Computer Security
(2004) · CRC Press eBooks · doi:10.1201/9781420030884 · Cited by 43
Machine Learning Methods for Computer Security (Dagstuhl Perspectives Workshop 12371)
Joseph, A. D., Laskov, P., Roli, F., Tygar, J. D., & Nelson, B. A. (2013) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/dagrep.2.9.109 · Cited by 42
Self-citationSculley, D., Wachman, G., & Brodley, C. E. (2006) · Cited by 41
Advanced Allergy Attacks: Does a Corpus Really Help?
Chung, S. P. H., & Mok, A. K. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74320-0_13 · Cited by 41
Hall, J. F. (2005) · American Journal of Physics · doi:10.1119/1.2074007 · Cited by 40
Regret Minimizing Audits: A Learning-Theoretic Basis for Privacy Protection
Blocki, J., Christin, N., Datta, A., & Sinha, A. (2011) · IEEE Computer Security Foundations Workshop (CSFW) · doi:10.1109/csf.2011.28 · Cited by 36
Johnson, P. B. (1955) · American Journal of Physics · doi:10.1119/1.1933957 · Cited by 32
Machine Learning in the Presence of an Adversary: Attacking and Defending the SpamBayes Spam Filter
Saini, U. (2008) · UC Berkeley · Cited by 31
Compromising PCA-based Anomaly Detectors for Network-Wide Traffic
Rubinstein, B. I. P., Nelson, B. A., Huang, L., Joseph, A. D., Lau, S.-H., Taft, N., & Tygar, D. (2008) · UC Berkeley · Cited by 27
Self-citationVC bounds on the cardinality of nearly orthogonal function classes
Gottlieb, L.-A. J., Kontorovich, A., & Mossel, E. (2012) · Discrete Mathematics · doi:10.1016/j.disc.2012.01.030 · Cited by 27
Detecting Viral Propagations Using Email Behavior Profiles
Stolfo, S. J., Li, W., Hershkop, S., Wang, K., Hu, C.-W., & Nimeskern, O. (2003) · Cited by 22
A Flexible Architecture for Statistical Learning and Data Mining from System Log Streams
Xu, W. Z., Bodík, P., & Patterson, D. A. (2004) · Cited by 21
Secure Learning and Learning for Security: Research in the Intersection
Rubinstein, B. I. P. (2010) · UC Berkeley · Cited by 21
Self-citationLearning convex bodies is hardPreprint
Goyal, N., & Rademacher, L. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0904.1227 · Cited by 21
An Evolutionary Algorithm for the Block Stacking Problem
Hohm, T., Egli, M., Gaehwiler, S., Bleuler, S., Feller, J., Frick, D., Huber, R., Karlsson, M., Lingenhag, R., Ruetimann, T., et al. (2008) · Springer eBooks · doi:10.1007/978-3-540-79305-2_10 · Cited by 5
VC bounds on the cardinality of nearly orthogonal function classesPreprint
Gottlieb, L.-A. J., Leonid, Kontorovich, et al. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1007.4915 · Cited by 4
Valiant, L. G. (2026) · Foundations of Computation and Machine Learning · doi:10.1145/3749740.3749746
Research works printed but not linked: 6
- 10.5555/1137817 · doi:10.5555/1137817
- 10.5555/345662 · doi:10.5555/345662
- R. A. Fisher . Question 14: Combining independent tests of significance. American Statistician, 2(5):30--31 , 1948 . R. A. Fisher. Question 14: Combining independent tests of significance. American Statistician, 2(5):30--31, 1948.
- A. Kerckhoffs . La cryptographie militaire . Journal des Sciences Militaires , 9 : 5 -- 83 , January 1883 . A. Kerckhoffs. La cryptographie militaire. Journal des Sciences Militaires, 9:5--83, January 1883.
- T. Mitchell . Machine Learning . McGraw Hill , 1997 . T. Mitchell. Machine Learning. McGraw Hill, 1997.
- B. Nelson and A. D. Joseph . Bounding an attack's complexity for a simple learning model . In Proc. Workshop on Tackling Computer Systems Problems with Machine Learning Techniques , 2006 . B. Nelson and A. D. Joseph. Bounding an attack's complexity for a simple learning model. In Proc. Workshop on Tackling Computer Systems Problems with Machine Learning Techniques, 2006.
Cited by
The Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993
Practical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks
Papernot, N., McDaniel, P., Wu, X., Jha, S., & Swami, A. (2016) · 2016 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2016.41 · Cited by 2,982
“Such attacks commonly occur today in non-DL classification systems [12], [13], [14], [15], [16].”
BackgroundBoosting Adversarial Attacks with Momentum
Dong, Y., Liao, F., Pang, T., Su, H., Zhu, J., Hu, X., & Li, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00957 · Cited by 2,956
“ntroduction It has long been shown that machine learning models are vulnerable to adversarial examples, which are the inputs crafted to make a model output attacker-desired but inaccurate predictions [3,18,11]. In particular, state-of-theart deep neural networks (DNNs) are challenged by their vulnerability to adversar…”
BackgroundReview of Deep Learning Algorithms and Architectures
Shrestha, A., & Mahmood, A. (2019) · IEEE Access · doi:10.1109/access.2019.2912200 · Cited by 1,883
“Reference [86] demonstrates these and other vulnerabilities and discusses how application domain, features and data distribution can be used to reduce the risk and impact of such adversarial attacks.”
Background
Metadata
- Authors
- Huang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I. P., & Tygar, J. D.
- Affiliations
- Intel (United States) (US)
- University of California, Berkeley (US)
- University of Tübingen (DE)
- Microsoft (United States) (US)
- Venue
- Proceedings of the 4th ACM workshop on Security and artificial intelligence
- Publisher
- ACM
- Published
- 2011-10-21
- Pages
- 43-58
- OpenAlex
- W2095577883
- Cited by
- 1,194
- References
- 197
- Citations by year
- 2026: 33 · 2025: 73 · 2024: 85 · 2023: 95 · 2022: 100 · 2021: 185 · 2020: 165 · 2019: 131 · 2018: 128 · 2017: 80 · 2016: 40 · 2015: 31 · 2014: 32 · 2013: 10 · 2012: 5
- FWCI
- 12.02
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Workshop on Artificial Intelligence and Security (AISec) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Hardware and Architecture › Security and Verification in Computing
- Keywords
- adversarial learning, online machine learning, opponent modeling, evasion attacks, countermeasures, privacy-preserving machine learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.