The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Practical Evasion of a Learning-Based Classifier: A Case Study
Open accessAbstract
Learning-based classifiers are increasingly used for detection of various forms of malicious data. However, if they are deployed online, an attacker may attempt to evade them by manipulating the data. Examples of such attacks have been previously studied under the assumption that an attacker has full knowledge about the deployed classifier. In practice, such assumptions rarely hold, especially for systems deployed online. A significant amount of information about a deployed classifier system can be obtained from various sources. In this paper, we experimentally investigate the effectiveness of classifier evasion using a real, deployed system, PDFrate, as a test case. We develop a taxonomy for practical evasion strategies and adapt known evasion algorithms to implement specific scenarios in our taxonomy. Our experimental results reveal a substantial drop of PDFrate's classification scores and detection accuracy after it is exposed even to simple attacks. We further study potential defense mechanisms against classifier evasion. Our experiments reveal that the original technique proposed for PDFrate is only effective if the executed attack exactly matches the anticipated one. In the discussion of the findings of our study, we analyze some potential techniques for increasing robustness of learning-based systems against adversarial manipulation of data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
On Estimation of a Probability Density Function and Mode
Parzen, E. (1962) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177704472 · Cited by 10,585
Scikit-learn: Machine Learning in Python
(2011) · Journal of Machine Learning Research · doi:10.5555/1953048.2078195 · Cited by 8,539
Differential Privacy: A Survey of Results
Dwork, C. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-79228-4_1 · Cited by 3,542
International Conference on Machine Learning (ICML)-2005
津田, 宏. (2006) · 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence · Cited by 2,558
Evasion attacks against machine learning at test time
Biggio, B., Corona, I., Maiorca, D., Nelson, B. A., Srndic, N., Laskov, P., Giacinto, G., & Roli, F. (2017) · Cited by 1,857
Self-citationPoisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331
Self-citationPrivacy Preserving Data Mining
Lindell, Y., & Pinkas, B. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-44598-6_3 · Cited by 1,077
Evasion Attacks against Machine Learning at Test Time
Biggio, B., Corona, I., Maiorca, D., Nelson, B., Šrndić, N., Laskov, P., Giacinto, G., & Roli, F. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-40994-3_25 · Cited by 890
Self-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
Scalable, behavior-based malware clustering
Bayer, U. (2009) · Cited by 603
Detection and analysis of drive-by-download attacks and malicious JavaScript code
Cova, M., Kruegel, C., & Vigna, G. (2010) · Proceedings of the 19th international conference on World wide web · doi:10.1145/1772690.1772720 · Cited by 580
Learning to Detect and Classify Malicious Executables in the Wild
Kolter, J. Z., & Maloof, M. A. (2006) · doi:10.5555/1248547.1248646 · Cited by 562
Security Evaluation of Pattern Classifiers under Attack
Biggio, B., Fumera, G., & Roli, F. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.57 · Cited by 411
Learning in the Presence of Malicious Errors
Kearns, M., & Li, M. (1993) · SIAM Journal on Computing · doi:10.1137/0222052 · Cited by 340
Prophiler: a fast filter for the large-scale detection of malicious web pages
Canali, D., Cova, M., Vigna, G., & Kruegel, C. (2011) · Proceedings of the 20th international conference on World wide web · doi:10.1145/1963405.1963436 · Cited by 335
Exploiting 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) · Cited by 322
Anagram: A Content Anomaly Detector Resistant to Mimicry Attack
Wang, K., Parekh, J. J., & Stolfo, S. J. (2006) · Lecture Notes in Computer Science · doi:10.1007/11856214_12 · Cited by 310
Nightmare 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
Malicious PDF detection using metadata and structural features
Smutz, C., & Stavrou, A. (2012) · Proceedings of the 28th Annual Computer Security Applications Conference · doi:10.1145/2420950.2420987 · Cited by 271
McPAD: A multiple classifier system for accurate payload-based anomaly detection
Perdisci, R., Ariu, D., Fogla, P., Giacinto, G., & Lee, W. (2009) · Computer Networks · doi:10.1016/j.comnet.2008.11.011 · Cited by 269
Good Word Attacks on Statistical Spam Filters.
Lowd, D., & Meek, C. (2005) · Cited by 251
COMPA: Detecting Compromised Accounts on Social Networks.
Egele, M., Stringhini, G., Krügel, C., & Vigna, G. (2013) · Cited by 250
Die Free or Live Hard? Empirical Evaluation and New Design for Fighting Evolving Twitter Spammers
Yang, C., Harkreader, R. C., & Gu, G. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-23644-0_17 · Cited by 235
Fogla, P., Sharif, M., Perdisci, R., et al. (2006) · Cited by 213
Adversarial stylometry: Circumventing authorship recognition to preserve privacy and anonymity
Brennan, M., Afroz, S., & Greenstadt, R. (2012) · ACM Transactions on Information and System Security · doi:10.1145/2382448.2382450 · Cited by 193
Misleading worm signature generators using deliberate noise injection
Perdisci, R., Dagon, D., Lee, W., Fogla, P., & Sharif, M. (2006) · 2006 IEEE Symposium on Security and Privacy (S&P'06) · doi:10.1109/sp.2006.26 · Cited by 189
Methods for Designing Multiple Classifier Systems
Roli, F., Giacinto, G., & Vernazza, G. L. (2001) · Lecture notes in computer science · doi:10.1007/3-540-48219-9_8 · Cited by 183
Cujo: efficient detection and prevention of drive-by-download attacks
Rieck, K., Krueger, T., & Dewald, A. (2010) · Proceedings of the 26th Annual Computer Security Applications Conference · doi:10.1145/1920261.1920267 · Cited by 168
Static prediction games for adversarial learning problems
Brückner, M., Kanzow, C., & Scheffer, T. (2012) · publish.UP (University of Potsdam) · doi:10.5555/2503308.2503326 · Cited by 162
Static detection of malicious JavaScript-bearing PDF documents
Laskov, P., & Šrndić, N. (2011) · Proceedings of the 27th Annual Computer Security Applications Conference · doi:10.1145/2076732.2076785 · Cited by 161
Self-citationEvading network anomaly detection systems: formal reasoning and practical techniques
Fogla, P., & Lee, W. (2006) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/1180405.1180414 · Cited by 161
Learning to classify with missing and corrupted features
Dekel, O., Shamir, O., & Xiao, L. (2009) · Machine Learning · doi:10.1007/s10994-009-5124-8 · Cited by 126
Embedded Malware Detection Using Markov n-Grams
Shafiq, M. Z., Khayam, S. A., & Farooq, M. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-70542-0_5 · Cited by 111
Maiorca, D., Corona, I., & Giacinto, G. (2013) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/2484313.2484327 · Cited by 111
Shady paths: leveraging surfing crowds to detect malicious web pages
Stringhini, G., Kruegel, C., & Vigna, G. (2013) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/2508859.2516682 · Cited by 108
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
Self-citationDetecting adversarial advertisements in the wild
Sculley, D., Otey, M. E., Pohl, M., Spitznagel, B., Hainsworth, J., & Zhou, Y. (2011) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2020408.2020455 · Cited by 95
Security Analysis of Online Centroid Anomaly DetectionPreprint
Kloft, M., & Laskov, P. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1003.0078 · Cited by 87
Self-citationAbusing File Processing in Malware Detectors for Fun and Profit
Jana, S., & Shmatikov, V. (2012) · Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · doi:10.1109/sp.2012.15 · Cited by 81
Using naive bayes to detect spammy names in social networks
Freeman, D. M. (2013) · ACM Workshop on Artificial Intelligence and Security (AISec) · doi:10.1145/2517312.2517314 · Cited by 48
Multiple Classifier Systems for Adversarial Classification Tasks
Biggio, B., Fumera, G., & Roli, F. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02326-2_14 · Cited by 33
Bayesian mixed-effects inference on classification performance in hierarchical datasets
Brodersen, K. H., Mathys, C. D., Chumbley, J. R., Jean Daunizeau, A., Ong, C. S., Buchmann, J. M., & Stephan, K. E. (2012) · Journal of Machine Learning Research · doi:10.5167/uzh-71594 · Cited by 23
Outlier-Based Approaches for Intrinsic and External Plagiarism Detection
Oberreuter, G., L’Huillier, G., Ríos, S. A., & Velásquez, J. D. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23863-5_2 · Cited by 18
Cited by
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
Federated Learning in Mobile Edge Networks: A Comprehensive Survey
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986024 · Cited by 2,565
Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
Sharif, M., Bhagavatula, S., Bauer, L., & Reiter, M. K. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978392 · Cited by 1,530
Wild patterns: Ten years after the rise of adversarial machine learning
Biggio, B., & Roli, F. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.07.023 · Cited by 1,409
A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security
Al-Garadi, M. A., Mohamed, A., Al-Ali, A. K., Du, X., Ali, I., & Guizani, M. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2988293 · Cited by 1,392
Metadata
- Authors
- Srndic, N., & Laskov, P.
- Venue
- 2014 IEEE Symposium on Security and Privacy
- Publisher
- IEEE
- Published
- 2014-05
- Pages
- 197-211
- ISSN
- 1081-6011 (ISSN-L)
- OpenAlex
- W2038296020
- Cited by
- 346
- References
- 46
- FWCI
- 12.85
- Type
- conference paper
- Language
- en
- Open access
- bronze
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.