Stochastic Variance Reduced Ensemble Adversarial Attack
Black-box adversarial attack has attracted much attention for its practical use in deep learning applications, and it is very challenging as there is no access to the architecture and weights of the target model. Based on the hypothesis that if an example remains adversarial for multiple models, then it is more likely to transfer to other models, the ensemble-based attack methods are efficient and widely used in the black-box setting. Nevertheless, existing ensemble-based approaches simply aggregate the outputs of all models but ignore the variance of different models, leading to a rather poor local optimum. To address this issue, we propose a stochastic variance reduced ensemble attack method to boost the performance of black-box adversarial attacks. By integrating the stochastic variance reduced gradient technique into the model ensemble attack, our method can balance the gradient of different models and leads to a better local maximum, resulting in highly transferable adversarial examples. Empirical results on the standard ImageNet dataset demonstrate that our method can boost the ensemble attack performance and significantly improve the transferability of the generated adversarial examples.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability
The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security. Meanwhile, it is very challenging as there is no access to the network architecture or int…
Adversarial AttackDynamic Stochastic Ensemble with Adversarial Robust Lottery Ticket Subnetworks
Adversarial attacks are considered the intrinsic vulnerability of CNNs. Defense strategies designed for attacks have been stuck in the adversarial attack-defense arms race, reflecting the imbalance between attack and def…
Adversarial AttackDiversityAdversarial Training with Stochastic Weight Average
Adversarial training deep neural networks often experience serious overfitting problem. Recently, it is explained that the overfitting happens because the sample complexity of training data is insufficient to generalize …
An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability
While the transferability property of adversarial examples allows the adversary to perform black-box attacks (i.e., the attacker has no knowledge about the target model), the transfer-based adversarial attacks have gaine…
Adversarial AttackGNN-Ensemble: Towards Random Decision Graph Neural Networks
Graph Neural Networks (GNNs) have enjoyed wide spread applications in graph-structured data. However, existing graph based applications commonly lack annotated data. GNNs are required to learn latent patterns from a limi…
Adversarial RobustnessDecision MakingEnsemble Learning