Superclass Adversarial Attack
Not on the map. Why?
Abstract (arXiv)
Adversarial attacks have only focused on changing the predictions of the classifier, but their danger greatly depends on how the class is mistaken. For example, when an automatic driving system mistakes a Persian cat for a Siamese cat, it is hardly a problem. However, if it mistakes a cat for a 120km/h minimum speed sign, serious problems can arise. As a stepping stone to more threatening adversarial attacks, we consider the superclass adversarial attack, which causes misclassification of not only fine classes, but also superclasses. We conducted the first comprehensive analysis of superclass adversarial attacks (an existing and 19 new methods) in terms of accuracy, speed, and stability, and identified several strategies to achieve better performance. Although this study is aimed at superclass misclassification, the findings can be applied to other problem settings involving multiple classes, such as top-k and multi-label classification attacks.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 29 May 2022.
Builds on
30 of 44 references.
References · 30
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Wide Residual Networkscited by 3,057
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2016Adversarial examples in the physical worldcited by 1,762
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2016Adversarial Machine Learning at Scalecited by 934
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
18 more
- 2016Universal adversarial perturbationscited by 774
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
- 2017One pixel attack for fooling deep neural networkscited by 579
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
- 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
- 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
- 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
- 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
- 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
- 2017A General Framework for Adversarial Examples with Objectivescited by 82
- 2015Adversarial Manipulation of Deep Representationscited by 56
- 2021TkML-AP: Adversarial Attacks to Top-k Multi-Label Learningcited by 26
- 2019Multi-Label Adversarial Perturbationscited by 18
- 2020Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifierscited by 10
- 2020Geometry-Inspired Top-k Adversarial Perturbationscited by 7
- 2020Characterizing the Evasion Attackability of Multi-label Classifierscited by 5
- 2021Improving Hierarchical Adversarial Robustness of Deep Neural Networkscited by 4
- 2021Attack Transferability Characterization for Adversarially Robust Multi-label Classificationcited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.