探索CLIP在AI生成图像检测中的对抗鲁棒性
Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection
AI总结：
本文研究基于CLIP和ViT的AI生成图像检测器对抗鲁棒性，发现其与CNN检测器同样易受白盒攻击，但攻击在两类方法间难以迁移，频域噪声模式差异证实了这一点。
摘要：
近年来，许多取证检测器被提出用于检测AI生成图像并防止其被用于恶意目的。卷积神经网络（CNNs）长期以来一直是该领域的主导架构，并受到了广泛研究。然而，最近提出的基于Transformer的检测器已被证明能够匹敌甚至超越基于CNN的检测器，尤其是在泛化能力方面。本文研究了AI生成图像检测器的对抗鲁棒性，重点关注依赖视觉Transformer（ViT）骨干网络的对比语言-图像预训练（CLIP）方法，并将其性能与基于CNN的方法进行比较。我们在多种条件下研究了针对不同对抗攻击的鲁棒性，并分析了数值结果和频域模式。研究发现，基于CLIP的检测器与基于CNN的检测器一样容易受到白盒攻击。然而，攻击在基于CNN和基于CLIP的方法之间不易迁移。这一点也通过频域中对抗噪声模式的不同分布得到了证实。总体而言，该分析为取证检测器的特性提供了新的见解，有助于制定更有效的策略。
英文摘要：
In recent years, many forensic detectors have been proposed to detect AI-generated images and prevent their use for malicious purposes. Convolutional neural networks (CNNs) have long been the dominant architecture in this field and have been the subject of intense study. However, recently proposed Transformer-based detectors have been shown to match or even outperform CNN-based detectors, especially in terms of generalization. In this paper, we study the adversarial robustness of AI-generated image detectors, focusing on Contrastive Language-Image Pretraining (CLIP)-based methods that rely on Visual Transformer (ViT) backbones and comparing their performance with CNN-based methods. We study the robustness to different adversarial attacks under a variety of conditions and analyze both numerical results and frequency-domain patterns. CLIP-based detectors are found to be vulnerable to white-box attacks just like CNN-based detectors. However, attacks do not easily transfer between CNN-based and CLIP-based methods. This is also confirmed by the different distribution of the adversarial noise patterns in the frequency domain. Overall, this analysis provides new insights into the properties of forensic detectors that can help to develop more effective strategies.
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。
