arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.01635cs.CR
收藏

基于扩散模型的对抗扰动注入:用于对抗面部操纵的通用防御

Diffusion-Guided Adversarial Perturbation Injection for Generalizable Defense Against Facial Manipulations

College of Computer Science and Technology, National Huaqiao University(华侨大学计算机科学与技术学院);Xiamen Key Laboratory of Data Security and Blockchain Technology(厦门市数据安全与区块链重点实验室);Shenzhen Key Laboratory of Media Security, Shenzhen University(深圳大学媒体安全深圳市重点实验室);School of Cyber Science and Engineering, Sichuan University(四川大学网络空间科学学院);Zhejiang Key Laboratory of Artificial Intelligence of Things (AIoT) Network and Data Security(浙江省物联网(AIoT)网络与数据安全重点实验室)

Yue Li, Linying Xue, Kaiqing Lin, Hanyu Quan, Dongdong Lin, Hui Tian, Hongxia Wang, Bin Wang

AI总结:

本文提出AEGIS,通过在扩散模型中注入对抗扰动来增强面部深度伪造的防御能力,通过解耦扰动幅度与像素约束提升防御效果,并在白盒和黑盒场景中均表现出色。

摘要:

最近的生成对抗网络(GAN)和扩散模型进展显著提升了面部深度伪造的逼真度和可控性,引发了严重的隐私、安全和身份滥用问题。主动防御试图在操纵发生前通过注入对抗扰动来对抗这一威胁。然而,现有方法由于扰动注入策略不优且通常基于白盒假设,仅针对简单的GAN属性编辑,限制了其在实际应用中的有效性。本文提出AEGIS,这是首个基于扩散模型的对抗扰动注入框架,用于生成对抗性面部图像以实现身份保护。我们发现现有方法的防御能力有限源于峰值截断约束,即由于固定的$L_\infty$-有界,扰动被强制截断。为克服这一限制,AEGIS不直接修改像素,而是在DDIM去噪轨迹的潜在空间中注入对抗扰动,从而解耦扰动幅度与像素级约束,使扰动能够适应性放大以达到最有效的位置。AEGIS的可扩展设计允许防御从纯白盒使用扩展到通过梯度估计策略支持黑盒场景。在GAN和扩散模型深度伪造生成器上的广泛实验表明,AEGIS在保持高质量感知效果的同时,始终提供强大的防御效果。在白盒设置中,它实现了稳健的操纵破坏,而在黑盒设置中,它展示了强的跨模型迁移能力。

英文摘要:

Recent advances in GAN and diffusion models have significantly improved the realism and controllability of facial deepfake manipulation, raising serious concerns regarding privacy, security, and identity misuse. Proactive defenses attempt to counter this threat by injecting adversarial perturbations into images before manipulation takes place. However, existing approaches remain limited in effectiveness due to suboptimal perturbation injection strategies and are typically designed under white-box assumptions, targeting only simple GAN-based attribute editing. These constraints hinder their applicability in practical real-world scenarios. In this paper, we propose AEGIS, the first diffusion-guided paradigm in which the AdvErsarial facial images are Generated for Identity Shielding. We observe that the limited defense capability of existing approaches stems from the peak-clipping constraint, where perturbations are forcibly truncated due to a fixed $L_\infty$-bounded. To overcome this limitation, instead of directly modifying pixels, AEGIS injects adversarial perturbations into the latent space along the DDIM denoising trajectory, thereby decoupling the perturbation magnitude from pixel-level constraints and allowing perturbations to adaptively amplify where most effective. The extensible design of AEGIS allows the defense to be expanded from purely white-box use to also support black-box scenarios through a gradient-estimation strategy. Extensive experiments across GAN and diffusion-based deepfake generators show that AEGIS consistently delivers strong defense effectiveness while maintaining high perceptual quality. In white-box settings, it achieves robust manipulation disruption, whereas in black-box settings, it demonstrates strong cross-model transferability.

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。

↑