Trust Region Based Adversarial Attack on Neural Networks
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tuning, or require many iterations to solve an optimization based adversarial attack. To address this problem, we present a new family of trust region based adversarial attacks, with the goal of computing adversarial perturbations efficiently. We propose several attacks based on variants of the trust region optimization method. We test the proposed methods on Cifar-10 and ImageNet datasets using several different models including AlexNet, ResNet-50, VGG-16, and DenseNet-121 models. Our methods achieve comparable results with the Carlini-Wagner (CW) attack, but with significant speed up of up to 37×, for the VGG-16 model on a Titan Xp GPU. For the case of ResNet-50 on ImageNet, we can bring down its classification accuracy to less than 0.1% with at most 1.5% relative L∞(or L2) perturbation requiring only 1.02 seconds as compared to 27.04 seconds for the CW attack. We have open sourced our method which can be accessed at [1].
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
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
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
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 4×
“In particular, we compare to DeepFool [16], iterative FGSM [8, 13], and the Carlini-Wagner (CW) attack [5].”
MethodResultInfluentialUniversal 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
Searching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335 · cited 1×
“, CNNs with Swish activation function [19].”
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 1×
“This adversarial training was further extended to ensemble adversarial training [26], with the goal of making the model more robust to black box attacks.”
BackgroundObfuscated 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×
“shown that, with a stronger attack method, defense schemes such as distillation or obfuscated gradients can be broken [2, 4, 5].”
Cited by
Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey
Akhtar, N., Mian, A., Kardan, N., & Shah, M. (2021) · IEEE Access · doi:10.1109/access.2021.3127960 · Cited by 302
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
Dong, Z., Yao, Z., Cai, Y., Arfeen, D., Gholami, A., Mahoney, M. W., & Keutzer, K. (2019) · arXiv · doi:10.48550/arxiv.1911.03852 · Cited by 110
“Similar recent work has also shown promising results when using second-order information for adversarial attacks [27] and the analysis of large batch size training [25, 26].”
ResultSelf-citationArtificial intelligence in medicine and the disclosure of risks
Kiener, M. (2021) · AI & SOCIETY · doi:10.1007/s00146-020-01085-w · Cited by 97
Kazmi, S. M. K. A., Aafaq, N., Khan, M. A., Khalil, M., & Saleem, A. (2023) · IEEE Access · doi:10.1109/access.2023.3299878 · Cited by 13
Metadata
- Authors
- Yao, Z., Gholami, A., Xu, P., Keutzer, K., & Mahoney, M. W.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 11342-11351
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2979878901
- Cited by
- 64
- References
- 11
- FWCI
- 4.41
- Type
- conference paper
- 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.