Deep neural networks are vulnerable to adversarial examples, posing a threat to the models' applications and raising security concerns. An intriguing property of adversarial examples is their strong transferability. Several methods have been proposed to enhance transferability, including ensemble attacks which have demonstrated their efficacy. However, prior approaches simply average logits, probabilities, or losses for model ensembling, lacking a comprehensive analysis of how and why model ensembling significantly improves transferability. In this paper, we propose a similar targeted attack method named Similar Target~(ST). By promoting cosine similarity between the gradients of each model, our method regularizes the optimization direction to simultaneously attack all surrogate models. This strategy has been proven to enhance generalization ability. Experimental results on ImageNet validate the effectiveness of our approach in improving adversarial transferability. Our method outperforms state-of-the-art attackers on 18 discriminative classifiers and adversarially trained models.

翻译：深度神经网络易受对抗样本的影响，这对模型的应用构成威胁并引发安全担忧。对抗样本的一个有趣特性是其强可迁移性。已有多种方法被提出以增强可迁移性，其中集成攻击已被证明具有有效性。然而，现有方法仅简单地对模型集成的对数几率、概率或损失进行平均，尚未系统分析模型集成如何及为何能显著提升可迁移性。本文提出一种名为相似目标（Similar Target, ST）的针对性攻击方法。该方法通过提升各模型梯度间的余弦相似度，正则化优化方向以同时攻击所有替代模型。实验证明，该策略可增强泛化能力。在ImageNet数据集上的实验结果验证了我们的方法在提升对抗可迁移性方面的有效性。在18个判别型分类器及对抗训练模型上，本方法优于现有最先进的攻击方法。