Boosting Adversarial Transferability with Spatial Adversarial Alignment

Zhaoyu Chen, HaiJing Guo, Kaixun Jiang, Jiyuan Fu, Xinyu Zhou, Dingkang Yang, Hao Tang, Bo Li, Wenqiang Zhang

Keywords: adversarial transferability, model alignment

TL;DR: We propose Spatial Adversarial Alignment (SAA), which leverages a witness model to fine-tune the surrogate model via spatial-aware and adversarial-aware alignment to generate highly transferable adversarial examples.

Abstract: Deep neural networks are vulnerable to adversarial examples that exhibit transferability across various models. Numerous approaches are proposed to enhance the transferability of adversarial examples, including advanced optimization, data augmentation, and model modifications. However, these methods still show limited transferability, partiovovocularly in cross-architecture scenarios, such as from CNN to ViT. To achieve high transferability, we propose a technique termed Spatial Adversarial Alignment (SAA), which employs an alignment loss and leverages a witness model to fine-tune the surrogate model. Specifically, SAA consists of two key parts: spatial-aware alignment and adversarial-aware alignment. First, we minimize the divergences of features between the two models in both global and local regions, facilitating spatial alignment. Second, we introduce a self-adversarial strategy that leverages adversarial examples to impose further constraints, aligning features from an adversarial perspective. Through this alignment, the surrogate model is trained to concentrate on the common features extracted by the witness model. This facilitates adversarial attacks on these shared features, thereby yielding perturbations that exhibit enhanced transferability. Extensive experiments on various architectures on ImageNet show that aligned surrogate models based on SAA can provide higher transferable adversarial examples, especially in cross-architecture attacks.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 27785