Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence · 2022 · 32 citations · 17 references
ComputingComputer EngineeringComputer ScienceComputer SecurityComputer VisionMachine LearningDeep LearningFeature TransformationImage Feature EngineeringTransfer LearningAdversarial ExamplesAttack SuccessFeature TransferTransferable RepresentationsVision Transformers
Adversarial examples can fool deep learning models, and their transferability is critical for attacking black-box models in real-world scenarios. Existing state-of-the-art transferable adversarial attacks tend to exploit intrinsic features of objects to generate adversarial examples. This paper proposes the Random Patch Attack (RPA) to significantly improve the transferability of adversarial examples by the patch-wise random transformation that effectively highlights important intrinsic features of objects. Specifically, we introduce random patch transformations to original images to variate model-specific features. Important object-related features are preserved after aggregating the transformed images since they stay consistent in multiple transformations while model-specific elements are neutralized. The obtained essential features steer noises to perturb the object-related regions, generating the adversarial examples of superior transferability across different models. Extensive experimental results demonstrate the effectiveness of the proposed RPA. Compared to the state-of-the-art transferable attacks, our attacks improve the black-box attack success rate by 2.9\% against normally trained models, 4.7\% against defense models, and 4.6\% against vision transformers on average, reaching a maximum of 99.1\%, 93.2\%, and 87.8\%, respectively.
17
Rethinking the Inception Architecture for Computer Vision
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe et al. · 2016 · 30.9K citations
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke et al. · 2017 · 12.6K citations · Full text
Explaining and Harnessing Adversarial Examples
Ian Goodfellow, Jonathon Shlens, Christian Szegedy · arXiv (Cornell University) · 2014 · 8.2K citations · Full text