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攻击，这威胁到模型的应用并引发安全隐患。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，其中集成攻击已证明其有效性。然而，先前的方法仅简单地对数几率、概率或损失进行平均以实现模型集成，缺乏对模型集成如何及为何显著提升可迁移性的全面分析。本文提出了一种名为相似目标（Similar Target，ST）的相似目标攻击方法。通过提升每个模型梯度之间的余弦相似性，我们的方法正则化优化方向，以同时攻击所有代理模型。该策略已被证明能增强泛化能力。在ImageNet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个判别式分类器和对抗训练模型上，我们的方法优于最先进的攻击方法。