On the Suitability of Lp-Norms for Creating and Preventing Adversarial Examples
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Much research has been devoted to better understanding adversarial examples, which are specially crafted inputs to machine-learning models that are perceptually similar to benign inputs, but are classified differently (i.e., misclassified). Both algorithms that create adversarial examples and strategies for defending against adversarial examples typically use Lp-norms to measure the perceptual similarity between an adversarial input and its benign original. Prior work has already shown, however, that two images need not be close to each other as measured by an Lp-norm to be perceptually similar. In this work, we show that nearness according to an Lp-norm is not just unnecessary for perceptual similarity, but is also insufficient. Specifically, focusing on datasets (CIFAR10 and MNIST), Lp-norms, and thresholds used in prior work, we show through online user studies that "adversarial examples" that are closer to their benign counterparts than required by commonly used Lp-norm thresholds can nevertheless be perceptually distinct to humans from the corresponding benign examples. Namely, the perceptual distance between two images that are "near" each other according to an Lp-norm can be high enough that participants frequently classify the two images as representing different objects or digits. Combined with prior work, we thus demonstrate that nearness of inputs as measured by Lp-norms is neither necessary nor sufficient for perceptual similarity, which has implications for both creating and defending against adversarial examples. We propose and discuss alternative similarity metrics to stimulate future research in the area.
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
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
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
Tversky, A. (1977) · Psychological Review · doi:10.1037/0033-295x.84.4.327 · Cited by 7,414
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
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
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
Adversarial machine learning at scale
Kurakin, A., Goodfellow, I., & Bengio, S. (2016) · arXiv · doi:10.48550/arxiv.1611.01236 · Cited by 2,325
Cited by
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
PRADA: Protecting Against DNN Model Stealing Attacks
Juuti, M., Szyller, S., Marchal, S., & Asokan, N. (2019) · 2019 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2019.00044 · Cited by 440
“Alternatively, any L norm or the structural similarity metric [45] could be used for image input.”
BackgroundMethodABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation
Liu, Y., Lee, W.-C., Tao, G., Ma, S., Aafer, Y., & Zhang, X. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3363216 · Cited by 404
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
Disentangling Adversarial Robustness and Generalization
Stutz, D., Hein, M., & Schiele, B. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00714 · Cited by 223
Hard to Forget: Poisoning Attacks on Certified Machine Unlearning
Marchant, N. G., Rubinstein, B. I. P., & Alfeld, S. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i7.20736 · Cited by 64
“While ℓ 𝑝 -norm constraints are easy to work with, they have been criticized for failing to capture perceptual distortion (Sharif, Bauer, and Reiter, 2018), which has lead to work on more effective perturbation constraints (Zhao, Z. Liu, and Larson, 2020; Ballet et al., 2019).”
Metadata
- Authors
- Sharif, M., Bauer, L., & Reiter, M. K.
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 1686-16868
- OpenAlex
- W2788552737
- Cited by
- 119
- References
- 13
- FWCI
- 6.45
- 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.