Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation
This work studies sparse adversarial perturbations, including both unstructured and structured ones. We propose a framework based on a white-box PGD-like attack method named Sparse-PGD to effectively and efficiently generate such perturbations. Furthermore, we combine Sparse-PGD with a black-box attack to comprehensively and more reliably evaluate the models' robustness against unstructured and structured sparse adversarial perturbations. Moreover, the efficiency of Sparse-PGD enables us to conduct adversarial training to build robust models against various sparse perturbations. Extensive experiments demonstrate that our proposed attack algorithm exhibits strong performance in different scenarios. More importantly, compared with other robust models, our adversarially trained model demonstrates state-of-the-art robustness against various sparse attacks.
Code (1)
Similar Papers 제목 키워드 기반
Sparse patches adversarial attacks via extrapolating point-wise information
Sparse and patch adversarial attacks were previously shown to be applicable in realistic settings and are considered a security risk to autonomous systems. Sparse adversarial perturbations constitute a setting in which t…
Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks
We propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-…
Malware DetectionSAIF: Sparse Adversarial and Imperceptible Attack Framework
Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal. The addition of calculated small distortion to images, for instance, can deceive a well-trained image classificati…
Decision Makingimage-classificationImage ClassificationTargeted Nonlinear Adversarial Perturbations in Images and Videos
We introduce a method for learning adversarial perturbations targeted to individual images or videos. The learned perturbations are found to be sparse while at the same time containing a high level of feature detail. Thu…
Action RecognitionData AugmentationGeneral ClassificationTemporal Action Localization+1Learning to Attack with Fewer Pixels: A Probabilistic Post-hoc Framework for Refining Arbitrary Dense Adversarial Attacks
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Many adversarial attacks belong to the category of …
Adversarial AttackAdversarial Attack Detection