The DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index.
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
Open accessAbstract
Lack of transparency in deep neural networks (DNNs) make them susceptible to backdoor attacks, where hidden associations or triggers override normal classification to produce unexpected results. For example, a model with a backdoor always identifies a face as Bill Gates if a specific symbol is present in the input. Backdoors can stay hidden indefinitely until activated by an input, and present a serious security risk to many security or safety related applications, e.g. biometric authentication systems or self-driving cars. We present the first robust and generalizable detection and mitigation system for DNN backdoor attacks. Our techniques identify backdoors and reconstruct possible triggers. We identify multiple mitigation techniques via input filters, neuron pruning and unlearning. We demonstrate their efficacy via extensive experiments on a variety of DNNs, against two types of backdoor injection methods identified by prior work. Our techniques also prove robust against a number of variants of the backdoor attack.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Gauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.41 · Cited by 5,479
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
On Assessing ML Model Robustness: A Methodological Framework (Academic Track)
Awadid, A., & Robert, B. (2025) · OASIcs : OpenAccess Series in Informatics · doi:10.4230/oasics.saia.2024.1 · Cited by 4,702
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524
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
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
The Influence Curve and its Role in Robust Estimation
Hampel, F. R. (1974) · Journal of the American Statistical Association · doi:10.1080/01621459.1974.10482962 · Cited by 2,706
Universal Adversarial Perturbations
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., & Frossard, P. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.17 · Cited by 2,680
Drebin: Effective and Explainable Detection of Android Malware in Your Pocket
Arp, D., Spreitzenbarth, M., Hübner, M., Gascon, H., & Rieck, K. (2014) · Proceedings 2014 Network and Distributed System Security Symposium · doi:10.14722/ndss.2014.23247 · Cited by 2,331
Adversarial machine learning at scale
Kurakin, A., Goodfellow, I., & Bengio, S. (2016) · arXiv · doi:10.48550/arxiv.1611.01236 · Cited by 2,325
Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples
Athalye, A., Carlini, N., & Wagner, D. (2018) · arXiv · doi:10.48550/arxiv.1802.00420 · Cited by 2,172 · cited 1×
“A number of defenses have been proposed [43], [44], [45], [46], [47], yet many have shown to be less effective against an adaptive adversary [48], [49], [50], [51].”
BackgroundDeep Learning Face Representation from Predicting 10,000 Classes
Sun, Y., Wang, X., & Tang, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.244 · Cited by 1,997
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
Xu, W., Evans, D., & Qi, Y. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23198 · Cited by 1,768
Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition
Stallkamp, J., Schlipsing, M., Salmen, J., & Igel, C. (2012) · Neural Networks · doi:10.1016/j.neunet.2012.02.016 · Cited by 1,537
Alternatives to the Median Absolute Deviation
Rousseeuw, P. J., & Croux, C. (1993) · Journal of the American Statistical Association · doi:10.2307/2291267 · Cited by 1,466
Understanding Neural Networks Through Deep Visualization
Yosinski, J., Clune, J., Nguyen, A. M., Fuchs, T. J., & Lipson, H. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.06579 · Cited by 1,358
Delving into Transferable Adversarial Examples and Black-box Attacks
Liu, Y., Chen, X., Liu, C., & Song, D. (2016) · arXiv · doi:10.48550/arxiv.1611.02770 · Cited by 1,310
Trojaning Attack on Neural Networks
Liu, Y., Ma, S., Aafer, Y., Lee, W.-C., Zhai, J., Wang, W., & Zhang, X. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23291 · Cited by 1,270
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
Gu, T., Dolan-Gavitt, B., & Garg, S. (2017) · arXiv · doi:10.48550/arxiv.1708.06733 · Cited by 1,061
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
Liu, K., Dolan-Gavitt, B., & Garg, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00470-5_13 · Cited by 1,055
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Chen, X., Liu, C., Li, B., Lu, K., & Song, D. (2017) · arXiv · doi:10.48550/arxiv.1712.05526 · Cited by 1,039
MagNet: A Two-Pronged Defense against Adversarial Examples
Meng, D., & Chen, H. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134057 · Cited by 1,006
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
Jagielski, M., Oprea, A., Biggio, B., Liu, C., Nita-Rotaru, C., & Li, B. (2018) · 2018 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2018.00057 · Cited by 861
Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
Hu, H., Peng, R., Tai, Y., & Tang, C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.03250 · Cited by 668
Brown, T. B., Mané, D., Roy, A., Abadi, M., & Gilmer, J. (2017) · arXiv · doi:10.48550/arxiv.1712.09665 · Cited by 509
Certified Defenses for Data Poisoning Attacks
Steinhardt, J., Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1706.03691 · Cited by 479
A neural network component for an intrusion detection system
Debar, H., Becker, M., & Siboni, D. (2003) · Proceedings 1992 IEEE Computer Society Symposium on Research in Security and Privacy · doi:10.1109/risp.1992.213257 · Cited by 461
(1995) · Cited by 440
Boyle, E., LaVigne, R., & Vaikuntanathan, V. (2018) · arXiv (Cornell University) · doi:10.4230/lipics.itcs.2019.16 · Cited by 408
Systematic Poisoning Attacks on and Defenses for Machine Learning in Healthcare
Mozaffari-Kermani, M., Sur-Kolay, S., Raghunathan, A., & Jha, N. K. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2014.2344095 · Cited by 383
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
Recognizing functions in binaries with neural networks
Shin, E. C. R., Song, D. X., & Moazzezi, R. (2015) · USENIX Security Symposium · Cited by 322
LEMNA: Explaining Deep Learning based Security Applications
Guo, W., Mu, D., Xu, J., Su, P., Wang, G., & Xing, X. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243792 · Cited by 287
Liu, Y., Xie, Y., & Srivastava, A. (2017) · 2017 IEEE International Conference on Computer Design (ICCD) · doi:10.1109/iccd.2017.16 · Cited by 241
Casting out Demons: Sanitizing Training Data for Anomaly Sensors
Cretu, G. F., Stavrou, A., Locasto, M. E., Stolfo, S. J., & Keromytis, A. D. (2008) · 2008 IEEE Symposium on Security and Privacy (sp 2008) · doi:10.1109/sp.2008.11 · Cited by 226
Adversarial Example Defense: Ensembles of Weak Defenses are not Strong
He, W., Wei, J., Chen, X., Carlini, N., & Song, D. X. (2017) · Cited by 221
MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial ExamplesPreprint
Carlini, N., & Wagner, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.08478 · Cited by 217
Defensive Distillation is Not Robust to Adversarial Examples
Carlini, N., & Wagner, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.04311 · Cited by 216
Adversary Resistant Deep Neural Networks with an Application to Malware Detection
Wang, Q., Guo, W., Zhang, K., Ororbia, A. G., Xing, X., Liu, X., & Giles, C. L. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098158 · Cited by 176
Neural Nets Can Learn Function Type Signatures From Binaries
Chua, Z. L., Shen, S., Saxena, P., & Liang, Z. (2017) · USENIX Security Symposium · Cited by 118
Adversarial Example Defenses: Ensembles of Weak Defenses are not StrongPreprint
He, W., Wei, J., Chen, X., Carlini, N., & Song, D. X. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.04701 · Cited by 111
With Great Training Comes Great Vulnerability: Practical Attacks against Transfer Learning
Wang, B., Yao, Y., Viswanath, B., Zheng, H.-T., & Zhao, B. Y. (2018) · USENIX Security Symposium · Cited by 105
Self-citationHardware Trojan Attacks on Neural NetworksPreprint
Clements, J., & Lao, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.05768 · Cited by 93
Liu, Y., Xie, Y., & Srivastava, A. (2017) · IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD) · Cited by 81
Hu-Fu: Hardware and Software Collaborative Attack Framework Against Neural Networks
Li, W., Yu, J., Ning, X., Wang, P., Wei, Q., Wang, Y., & Yang, H. (2018) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi.2018.00093 · Cited by 73
Efficient Repair of Polluted Machine Learning Systems via Causal Unlearning
Cao, Y., Yu, A. F., Aday, A., Stahl, E., Merwine, J., & Yang, J. (2018) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3196494.3196517 · Cited by 50
Cited by
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
How to backdoor federated learning
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2018) · arXiv · doi:10.48550/arxiv.1807.00459 · Cited by 1,495
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks
Gu, T., Liu, K., Dolan-Gavitt, B., & Garg, S. (2019) · IEEE Access · doi:10.1109/access.2019.2909068 · Cited by 1,238
“There have also been very recent attempts at defending against backdoor attacks [36], [37]; however, defenses have only”
BackgroundSTRIP: a defence against trojan attacks on deep neural networks
Gao, Y., Xu, C., Wang, D., Chen, S., Ranasinghe, D. C., & Nepal, S. (2019) · Proceedings of the 35th Annual Computer Security Applications Conference · doi:10.1145/3359789.3359790 · Cited by 707
Li, Y., Jiang, Y., Li, Z., & Xia, S.-T. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3182979 · Cited by 682
Metadata
- Authors
- Wang, B., Yao, Y., Shan, S., Li, H., Viswanath, B., Zheng, H., & Zhao, B. Y.
- Venue
- 2019 IEEE Symposium on Security and Privacy (SP)
- Publisher
- IEEE
- Published
- 2019-05
- Pages
- 707-723
- ISSN
- 1081-6011 (ISSN-L)
- OpenAlex
- W2934843808
- Cited by
- 1,368
- References
- 52
- FWCI
- 49.38
- 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.