Adversarial Examples on Object Recognition: A Comprehensive Survey
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect behavior. Such perturbations, called adversarial examples, are intentionally designed to test the network’s sensitivity to distribution drifts. Given their surprisingly small size, a wide body of literature conjectures on their existence and how this phenomenon can be mitigated. In this article, we discuss the impact of adversarial examples on security, safety, and robustness of neural networks. We start by introducing the hypotheses behind their existence, the methods used to construct or protect against them, and the capacity to transfer adversarial examples between different machine learning models. Altogether, the goal is to provide a comprehensive and self-contained survey of this growing field of research.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
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
Adversarial examples in the physical world
Kurakin, A., Goodfellow, I. J., & Bengio, S. (2018) · Artificial Intelligence Safety and Security · doi:10.1201/9781351251389-8 · Cited by 5,375
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Moosavi-Dezfooli, S.-M., Fawzi, A., & Frossard, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.282 · Cited by 5,317 · cited 2×
“L-BFGS [161] x x x *** *** *** *** Deep Fool [123] x x x * *** *** *** UAP [120] x x x *** ** *** ** Carlini [26] x x x x *** *** *** *** FGS [65] x x x * * ** *** JSMA [130] x x x x * *** ** *** STA [79] x x x ** *** * * SV-UAP [91] x x x * *** ** * RSSA [165] x x x * * *** *** BPDA [4] x x x *** *** *** *** Elastic-…”
BackgroundThe 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
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
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
One Pixel Attack for Fooling Deep Neural Networks
Su, J., Vargas, D. V., & Sakurai, K. (2019) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2019.2890858 · Cited by 2,406
Adversarial machine learning at scale
Kurakin, A., Goodfellow, I., & Bengio, S. (2016) · arXiv · doi:10.48550/arxiv.1611.01236 · Cited by 2,325
Ensemble Adversarial Training: Attacks and Defenses
Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., & McDaniel, P. (2017) · arXiv · doi:10.48550/arxiv.1705.07204 · Cited by 2,176 · cited 4×
“This phenomenon, called gradient masking [129, 131] was identified to give a false sense of security and leads to an improper evaluation of adversarial defenses [4, 24, 165].”
BackgroundInfluentialRobust physical-world attacks on deep learning visual classification
Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Rahmati, A., Xiao, C., Prakash, A., Kohno, T., & Song, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00175 · Cited by 2,173
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 5×
“[4] showed that 7 out of 9 defenses published at ICLR 2018 as noncertified defenses suffer from gradient masking (a phenomenon described in the next section) and are not efficient against the BPDA attack (Table 1).”
BackgroundInfluentialThreat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
Akhtar, N., & Mian, A. (2018) · IEEE Access · doi:10.1109/access.2018.2807385 · Cited by 2,021
Poisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
Papernot, N., McDaniel, P., & Goodfellow, I. (2016) · arXiv · doi:10.48550/arxiv.1605.07277 · Cited by 1,326
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
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 3×
“Thereafter, a large body of publications discussed adversarial attacks against ML models at both training time [15, 143] and test or inference time [61, 110] or defense mechanisms against such attacks [18, 93].”
BackgroundDetecting Adversarial Samples from Artifacts
Feinman, R., Curtin, R. R., Shintre, S., & Gardner, A. B. (2017) · arXiv · doi:10.48550/arxiv.1703.00410 · Cited by 606
PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
Song, Y., Kim, T., Nowozin, S., Ermon, S., & Kushman, N. (2017) · arXiv · doi:10.48550/arxiv.1710.10766 · Cited by 562 · cited 2×
“Many conjectures have been proposed and are discussed in this section.”
BackgroundMethodGenerating Natural Adversarial Examples
Zhao, Z., Dua, D., & Singh, S. (2017) · arXiv · doi:10.48550/arxiv.1710.11342 · Cited by 508
SoK: Security and Privacy in Machine Learning
Papernot, N., McDaniel, P., Sinha, A., & Wellman, M. P. (2018) · 2018 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2018.00035 · Cited by 502 · cited 4×
“This phenomenon, called gradient masking [129, 131] was identified to give a false sense of security and leads to an improper evaluation of adversarial defenses [4, 24, 165].”
BackgroundInfluentialA Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View
Liu, Q., Li, P., Zhao, W., Cai, W., Yu, S., & Leung, V. C. M. (2018) · IEEE Access · doi:10.1109/access.2018.2805680 · Cited by 421
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 · cited 1×
“Thereafter, a large body of publications discussed adversarial attacks against ML models at both training time [15, 143] and test or inference time [61, 110] or defense mechanisms against such attacks [18, 93].”
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
Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
Wong, E., Schmidt, F. R., & Kolter, J. Z. (2019) · arXiv · doi:10.48550/arxiv.1902.07906 · Cited by 145 · cited 2×
“This behavior is achieved using an un-directed DNN that back-propagates the errors in both directions – each direction of the network has its own biases and the weights are shared.”
BackgroundMethodDense Associative Memory Is Robust to Adversarial Inputs
Krotov, D., & Hopfield, J. (2018) · Neural Computation · doi:10.1162/neco_a_01143 · Cited by 106 · cited 2×
“However, RBF units can not generalize very well and do not achieve the same performance as ReLU based DNNs. Krotov and Hopfield [96] tried to replace ReLU activations with higher rectified polynomials and observed an increase in robustness.”
Background
Cited by
Membership Inference Attacks on Machine Learning: A Survey
Hu, H., Salcic, Z., Sun, L., Dobbie, G., Yu, P. S., & Zhang, X. (2022) · ACM Computing Surveys · doi:10.1145/3523273 · Cited by 564
Adversarial Machine Learning for Network Intrusion Detection Systems: A Comprehensive Survey
He, K., Kim, D. D., & Asghar, M. R. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3233793 · Cited by 450
Ahmad, K., Maabreh, M., Ghaly, M., Khan, K., Qadir, J., & Al-Fuqaha, A. (2022) · Computer Science Review · doi:10.1016/j.cosrev.2021.100452 · Cited by 291
Beyond generalization: a theory of robustness in machine learning
Freiesleben, T., & Grote, T. (2023) · Synthese · doi:10.1007/s11229-023-04334-9 · Cited by 106
“…papers on ML robustness rather focus only on specific robustness notions, such as adversarial robustness (Dong et al., 2020; Dreossi et al., 2019; Serban et al., 2020), robustness to natural distribution shifts (Drenkow et al., 2021; Hendrycks et al., 2021; Koh et al., 2021; Taori et al.,…”
BackgroundAdversarial Attacks Against Deep Generative Models on Data: A Survey
Sun, H., Zhu, T., Zhang, Z., Jin, D., Xiong, P., & Zhou, W. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3130903 · Cited by 90
“elaborated on adversarial examples, including their construction, defense strategies, and transfer capabilities [26].”
Background
Metadata
- Authors
- Serban, A., Poll, E., & Visser, J.
- Venue
- ACM Computing Surveys
- Published
- 2020-06-12
- Volume
- 53
- Issue
- 3
- Pages
- 1-38
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W3035584216
- Cited by
- 136
- References
- 29
- FWCI
- 7.86
- Type
- journal article
- Language
- en
- Open access
- green
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.