ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers

Ensemble-based attacks have been proven to be effective in enhancing adversarial transferability by aggregating the outputs of models with various architectures. However, existing research primarily focuses on refining ensemble weights or optimizing the ensemble path, overlooking the exploration of ensemble models to enhance the transferability of adversarial attacks. To address this gap, we propose applying adversarial augmentation to the surrogate models, aiming to boost overall generalization of ensemble models and reduce the risk of adversarial overfitting. Meanwhile, observing that ensemble Vision Transformers (ViTs) gain less attention, we propose ViT-EnsembleAttack based on the idea of model adversarial augmentation, the first ensemble-based attack method tailored for ViTs to the best of our knowledge. Our approach generates augmented models for each surrogate ViT using three strategies: Multi-head dropping, Attention score scaling, and MLP feature mixing, with the associated parameters optimized by Bayesian optimization. These adversarially augmented models are ensembled to generate adversarial examples. Furthermore, we introduce Automatic Reweighting and Step Size Enlargement modules to boost transferability. Extensive experiments demonstrate that ViT-EnsembleAttack significantly enhances the adversarial transferability of ensemble-based attacks on ViTs, outperforming existing methods by a substantial margin. Code is available at https://github.com/Trustworthy-AI-Group/TransferAttack.

AutoAugment Input Transformation for Highly Transferable Targeted Attacks

Deep Neural Networks (DNNs) are widely acknowledged to be susceptible to adversarial examples, wherein imperceptible perturbations are added to clean examples through diverse input transformation attacks. However, these methods originally designed for non-targeted attacks exhibit low success rates in targeted attacks. Recent targeted adversarial attacks mainly pay attention to gradient optimization, attempting to find the suitable perturbation direction. However, few of them are dedicated to input transformation.In this work, we observe a positive correlation between the logit/probability of the target class and diverse input transformation methods in targeted attacks. To this end, we propose a novel targeted adversarial attack called AutoAugment Input Transformation (AAIT). Instead of relying on hand-made strategies, AAIT searches for the optimal transformation policy from a transformation space comprising various operations. Then, AAIT crafts adversarial examples using the found optimal transformation policy to boost the adversarial transferability in targeted attacks. Extensive experiments conducted on CIFAR-10 and ImageNet-Compatible datasets demonstrate that the proposed AAIT surpasses other transfer-based targeted attacks significantly.