arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2505.03435cs.CV
收藏

AI生成检测中的鲁棒性:增强对对抗攻击的抵抗力

Robustness in AI-Generated Detection: Enhancing Resistance to Adversarial Attacks

Shanghai Jiao Tong University(上海交通大学);Alibaba Group(阿里巴巴集团)

Sun Haoxuan, Hong Yan, Zhan Jiahui, Chen Haoxing, Lan Jun, Zhu Huijia, Wang Weiqiang, Zhang Liqing, Zhang Jianfu

AI总结:

本文针对AI生成人脸检测系统易受对抗攻击的问题,提出结合对抗训练与扩散反演重建的方法,显著提升了检测鲁棒性,并公开代码以促进后续研究。

摘要:

生成式图像技术的快速发展带来了重大的安全问题,尤其是在人脸生成检测领域。本文研究了当前AI生成人脸检测系统的脆弱性。我们的研究表明,尽管现有检测方法在标准条件下通常能达到较高准确率,但它们在面对对抗攻击时表现出有限的鲁棒性。为应对这些挑战,我们提出了一种整合对抗训练的方法,以减轻对抗样本的影响。此外,我们利用扩散反演与重建来进一步增强检测鲁棒性。实验结果表明,微小的对抗扰动可以轻易绕过现有检测系统,但我们的方法显著提升了这些系统的鲁棒性。另外,我们对对抗样本和良性样本进行了深入分析,为AI生成内容的内在特征提供了见解。所有相关代码将在一个专门的代码库中公开,以促进进一步的研究与验证。

英文摘要:

The rapid advancement of generative image technology has introduced significant security concerns, particularly in the domain of face generation detection. This paper investigates the vulnerabilities of current AI-generated face detection systems. Our study reveals that while existing detection methods often achieve high accuracy under standard conditions, they exhibit limited robustness against adversarial attacks. To address these challenges, we propose an approach that integrates adversarial training to mitigate the impact of adversarial examples. Furthermore, we utilize diffusion inversion and reconstruction to further enhance detection robustness. Experimental results demonstrate that minor adversarial perturbations can easily bypass existing detection systems, but our method significantly improves the robustness of these systems. Additionally, we provide an in-depth analysis of adversarial and benign examples, offering insights into the intrinsic characteristics of AI-generated content. All associated code will be made publicly available in a dedicated repository to facilitate further research and verification.

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。

↑