深入探讨图像分类中的对抗迁移性：综述、基准测试与评估
Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation
AI总结：
本文通过综述和基准测试，探讨图像分类中对抗迁移性的问题，提出评估框架并分析提升迁移性的策略及潜在问题。
摘要：
对抗迁移性指的是在替代模型上生成的对抗示例欺骗其他未接触的受害者模型的能力。这一特性消除了对受害者模型直接访问的需求，从而在实际应用中引发了相当大的安全担忧，并吸引了最近大量的研究关注。在本工作中，我们发现缺乏标准化的框架和评估对抗基于攻击的准则，导致现有方法的评估可能存在偏差。为弥补这一差距，我们对数百项相关研究进行了详尽回顾，将各种基于迁移的攻击分为六个不同的类别。随后，我们提出了一种全面的框架，旨在作为评估这些攻击的基准。此外，我们阐述了增强对抗迁移性的常见策略，并突出了可能导致不公平比较的普遍问题。最后，我们简要回顾了超越图像分类的基于迁移的攻击。
英文摘要：
Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an attack, thereby raising considerable security concerns in practical applications and attracting substantial research attention recently. In this work, we discern a lack of a standardized framework and criteria for evaluating transfer-based attacks, leading to potentially biased assessments of existing approaches. To rectify this gap, we have conducted an exhaustive review of hundreds of related works, organizing various transfer-based attacks into six distinct categories. Subsequently, we propose a comprehensive framework designed to serve as a benchmark for evaluating these attacks. In addition, we delineate common strategies that enhance adversarial transferability and highlight prevalent issues that could lead to unfair comparisons. Finally, we provide a brief review of transfer-based attacks beyond image classification.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
