paper-with-me

Papers

An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability

2023-08-05 · ICCV 2023 1 · Bin Chen, Jia-Li Yin, Shukai Chen, Bo-Hao Chen, Ximeng Liu

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 gained great attention. Previous works mostly study gradient variation or image transformations to amplify the distortion on critical parts of inputs. These methods can work on transferring across models with limited differences, i.e., from CNNs to CNNs, but always fail in transferring across models with wide differences, such as from CNNs to ViTs. Alternatively, model ensemble adversarial attacks are proposed to fuse outputs from surrogate models with diverse architectures to get an ensemble loss, making the generated adversarial example more likely to transfer to other models as it can fool multiple models concurrently. However, existing ensemble attacks simply fuse the outputs of the surrogate models evenly, thus are not efficacious to capture and amplify the intrinsic transfer information of adversarial examples. In this paper, we propose an adaptive ensemble attack, dubbed AdaEA, to adaptively control the fusion of the outputs from each model, via monitoring the discrepancy ratio of their contributions towards the adversarial objective. Furthermore, an extra disparity-reduced filter is introduced to further synchronize the update direction. As a result, we achieve considerable improvement over the existing ensemble attacks on various datasets, and the proposed AdaEA can also boost existing transfer-based attacks, which further demonstrates its efficacy and versatility.

📄 PDF Abstract BibTeX arXiv:2308.02897

Code (1)

CHENBIN99/AdaEA 공식 구현 pytorch

Tasks

Adversarial Attack

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Towards Robust Vision Transformer via Masked Adaptive Ensemble

2024-07-22 · Fudong Lin, Jiadong Lou, Xu Yuan, Nian-Feng Tzeng

Adversarial training (AT) can help improve the robustness of Vision Transformers (ViT) against adversarial attacks by intentionally injecting adversarial examples into the training data. However, this way of adversarial …

Adversarial Robustness

Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability

2021-11-21 · CVPR 2022 1 · Yifeng Xiong, Jiadong Lin, Min Zhang, John E. Hopcroft 외

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 Attack

Building Robust Ensembles via Margin Boosting

2022-06-07 · Dinghuai Zhang, Hongyang Zhang, Aaron Courville, Yoshua Bengio 외

In the context of adversarial robustness, a single model does not usually have enough power to defend against all possible adversarial attacks, and as a result, has sub-optimal robustness. Consequently, an emerging line …

Adversarial Robustness

CARE: Ensemble Adversarial Robustness Evaluation Against Adaptive Attackers for Security Applications

2024-01-20 · Hangsheng Zhang, Jiqiang Liu, Jinsong Dong

Ensemble defenses, are widely employed in various security-related applications to enhance model performance and robustness. The widespread adoption of these techniques also raises many questions: Are general ensembles d…

Adversarial Robustness

Understanding and Improving Ensemble Adversarial Defense

2023-09-21 · NeurIPS 2023 11

The strategy of ensemble has become popular in adversarial defense, which trains multiple base classifiers to defend against adversarial attacks in a cooperative manner. Despite the empirical success, theoretical explana…