paper-with-me

Papers

Boosting Adversarial Transferability via Commonality-Oriented Gradient Optimization

2025-06-08 · Yanting Gao, Yepeng Liu, Junming Liu, Qi Zhang, Hongyun Zhang, Duoqian Miao, Cairong Zhao

Exploring effective and transferable adversarial examples is vital for understanding the characteristics and mechanisms of Vision Transformers (ViTs). However, adversarial examples generated from surrogate models often exhibit weak transferability in black-box settings due to overfitting. Existing methods improve transferability by diversifying perturbation inputs or applying uniform gradient regularization within surrogate models, yet they have not fully leveraged the shared and unique features of surrogate models trained on the same task, leading to suboptimal transfer performance. Therefore, enhancing perturbations of common information shared by surrogate models and suppressing those tied to individual characteristics offers an effective way to improve transferability. Accordingly, we propose a commonality-oriented gradient optimization strategy (COGO) consisting of two components: Commonality Enhancement (CE) and Individuality Suppression (IS). CE perturbs the mid-to-low frequency regions, leveraging the fact that ViTs trained on the same dataset tend to rely more on mid-to-low frequency information for classification. IS employs adaptive thresholds to evaluate the correlation between backpropagated gradients and model individuality, assigning weights to gradients accordingly. Extensive experiments demonstrate that COGO significantly improves the transfer success rates of adversarial attacks, outperforming current state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2506.06992

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Boosting the Local Invariance for Better Adversarial Transferability

2025-03-08 · Bohan Liu, Xiaosen Wang

Transfer-based attacks pose a significant threat to real-world applications by directly targeting victim models with adversarial examples generated on surrogate models. While numerous approaches have been proposed to enh…

Boosting Adversarial Transferability through Enhanced Momentum

2021-03-19 · Xiaosen Wang, Jiadong Lin, Han Hu, Jingdong Wang 외

Deep learning models are known to be vulnerable to adversarial examples crafted by adding human-imperceptible perturbations on benign images. Many existing adversarial attack methods have achieved great white-box attack …

Adversarial Attack

Improving the Transferability of Adversarial Examples by Feature Augmentation

2024-07-09 · Donghua Wang, Wen Yao, Tingsong Jiang, Xiaohu Zheng 외

Despite the success of input transformation-based attacks on boosting adversarial transferability, the performance is unsatisfying due to the ignorance of the discrepancy across models. In this paper, we propose a simple…

Diversity

Boosting Adversarial Transferability via Residual Perturbation Attack

2025-08-06 · Jinjia Peng, Zeze Tao, Huibing Wang, Meng Wang 외 arxiv

Deep neural networks are susceptible to adversarial examples while suffering from incorrect predictions via imperceptible perturbations. Transfer-based attacks create adversarial examples for surrogate models and transfe…

Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability

2022-07-24 · Quanshi Zhang, Xin Wang, Jie Ren, Xu Cheng 외

Although many methods have been proposed to enhance the transferability of adversarial perturbations, these methods are designed in a heuristic manner, and the essential mechanism for improving adversarial transferabilit…