使用 GE-AdvGAN+ 增强对抗攻击的迁移性：一个全面的梯度编辑框架
Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing
AI总结：
本文提出基于梯度编辑的可迁移对抗攻击通用框架 GE-AdvGAN+，集成主流攻击方法，在显著降低计算成本的同时提升攻击迁移性与效率，其最佳变体 ASR 大幅提升且达 2217.7 FPS。
摘要：
可迁移对抗攻击对深度神经网络构成了重大威胁，特别是在无法获取内部模型信息的黑盒场景中。研究对抗攻击方法有助于推进防御机制的性能并探索模型漏洞。这些方法能够揭示和利用模型的弱点，促进更鲁棒架构的发展。然而，当前的可迁移攻击方法通常伴随着巨大的计算成本，限制了它们的部署和应用，特别是在边缘计算场景中。对抗生成模型，如生成对抗网络（GANs），其特点在于初始训练阶段后无需重新训练即可生成样本。GE-AdvGAN 是一种近期提出的可迁移对抗攻击方法，正是基于这一原理。在本文中，我们提出了一个基于梯度编辑的可迁移攻击的全新通用框架，名为 GE-AdvGAN+，该框架集成了几乎所有主流攻击方法，以增强迁移性，同时显著降低计算资源消耗。我们的实验证明了我们框架的兼容性和有效性。与基线 AdvGAN 相比，我们表现最佳的方法 GE-AdvGAN++ 实现了平均 47.8 的 ASR 提升。此外，它还超越了最新的竞争算法 GE-AdvGAN，平均 ASR 提高了 5.9。该框架还展现出更高的计算效率，达到 2217.7 FPS，优于 BIM 和 MI-FGSM 等传统方法。我们 GE-AdvGAN+ 框架的实现代码可在 https://github.com/GEAdvGANP 获取。
英文摘要：
Transferable adversarial attacks pose significant threats to deep neural networks, particularly in black-box scenarios where internal model information is inaccessible. Studying adversarial attack methods helps advance the performance of defense mechanisms and explore model vulnerabilities. These methods can uncover and exploit weaknesses in models, promoting the development of more robust architectures. However, current methods for transferable attacks often come with substantial computational costs, limiting their deployment and application, especially in edge computing scenarios. Adversarial generative models, such as Generative Adversarial Networks (GANs), are characterized by their ability to generate samples without the need for retraining after an initial training phase. GE-AdvGAN, a recent method for transferable adversarial attacks, is based on this principle. In this paper, we propose a novel general framework for gradient editing-based transferable attacks, named GE-AdvGAN+, which integrates nearly all mainstream attack methods to enhance transferability while significantly reducing computational resource consumption. Our experiments demonstrate the compatibility and effectiveness of our framework. Compared to the baseline AdvGAN, our best-performing method, GE-AdvGAN++, achieves an average ASR improvement of 47.8. Additionally, it surpasses the latest competing algorithm, GE-AdvGAN, with an average ASR increase of 5.9. The framework also exhibits enhanced computational efficiency, achieving 2217.7 FPS, outperforming traditional methods such as BIM and MI-FGSM. The implementation code for our GE-AdvGAN+ framework is available at https://github.com/GEAdvGANP
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。
