Adversarial examples (AEs) for DNNs have been shown to be transferable: AEs that successfully fool white-box surrogate models can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable AEs, many of these findings lack explanations and even lead to inconsistent advice. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing little robustness phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates, we attribute it to a trade-off between two predominant factors: model smoothness and gradient similarity. Our investigations focus on their joint effects, rather than their separate correlations with transferability. Through a series of theoretical and empirical analyses, we conjecture that the data distribution shift in adversarial training explains the degradation of gradient similarity. Building on these insights, we explore the impacts of data augmentation and gradient regularization on transferability and identify that the trade-off generally exists in the various training mechanisms, thus building a comprehensive blueprint for the regulation mechanism behind transferability. Finally, we provide a general route for constructing better surrogates to boost transferability which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other, and emphasize the crucial role of manipulating surrogate models.

翻译：深度神经网络（DNN）的对抗样本（AE）已被证具有迁移性：能成功欺骗白盒替代模型的对抗样本，也能欺骗其他架构不同的黑盒模型。尽管大量实证研究为生成高迁移性对抗样本提供了指导，但许多发现缺乏解释，甚至给出相互矛盾的建议。本文进一步探究对抗迁移性，并特别关注替代模型方面。从有趣的"轻微鲁棒性"现象（即经轻微扰动对抗样本对抗训练的模型，可作为更优替代模型）出发，我们将其归因于两个主导因素间的权衡：模型平滑性与梯度相似性。我们聚焦于两者的联合效应，而非其与迁移性的各自关联。通过系列理论与实证分析，我们推测对抗训练中的数据分布偏移解释了梯度相似性的退化。基于这些见解，我们探究数据增强与梯度正则化对迁移性的影响，发现该权衡广泛存在于各类训练机制中，从而为迁移性背后的调控机制构建全面蓝图。最终，我们提出构建更优替代模型以增强迁移性的通用路径——同时优化模型平滑性与梯度相似性，例如输入梯度正则化与锐度感知最小化（SAM）的结合，并通过大量实验验证。总之，我们呼吁关注这两个因素对发起有效迁移攻击的联合影响，而非优化其一忽略其二，并强调操控替代模型的关键作用。