LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions
Recent work shows that well-designed adversarial examples can fool deep neural networks (DNNs). Due to their transferability, adversarial examples can also attack target models without extra information, called black-box attacks. However, most existing ensemble attacks depend on numerous substitute models to cover the vulnerable subspace of a target model. In this work, we find three types of models with non-overlapping vulnerable frequency regions, which can cover a large enough vulnerable subspace. Based on this finding, we propose a lightweight ensemble adversarial attack named LEA2, integrated by standard, weakly robust, and robust models. Moreover, we analyze Gaussian noise from the perspective of frequency and find that Gaussian noise is located in the vulnerable frequency regions of standard models. Therefore, we substitute standard models with Gaussian noise to ensure the use of high-frequency vulnerable regions while reducing attack time consumption. Experiments on several image datasets indicate that LEA^2 achieves better transferability under different defended models compared with extensive baselines and state-of-the-art attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
A New Ensemble Adversarial Attack Powered by Long-term Gradient Memories
Deep neural networks are vulnerable to adversarial attacks.
Adversarial AttackCAAD 2018: Iterative Ensemble Adversarial Attack
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically mislead…
Adversarial AttackImproving Adversarial Robustness of Ensembles with Diversity Training
Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked. Such attacks usually rely on the principle of transferability, whereby an a…
Adversarial RobustnessDiversityImproved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes
Neural network ensembles have been studied extensively in the context of adversarial robustness and most ensemble-based approaches remain vulnerable to adaptive attacks. In this paper, we investigate the robustness of Er…
Adversarial RobustnessDiversityDynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness
The deep neural network has attained significant efficiency in image recognition. However, it has vulnerable recognition robustness under extensive data uncertainty in practical applications. The uncertainty is attribute…
Adversarial AttackAdversarial RobustnessDiversity