Phantom: 一种结合潜在与空间约束的统一换脸深度伪造防护框架
Phantom: A Unified Face-Swap Deepfake Protection Framework with Latent and Spatial Constraints
AI总结：
提出Phantom框架，通过自适应合成身份偏移目标引导潜在优化，并对语义相关面部区域施加掩蔽扰动，在换脸防护中提升成功率27.8%-16.6%，同时增强视觉质量。
摘要：
换脸深度伪造通过未经授权的身份操纵对个人隐私构成日益严重的威胁。虽然对抗方法在黑盒人脸识别模型上取得了成功，但其在换脸场景中的适用性仍未被充分探索。特别是，依赖固定或随机目标会产生模糊的潜在引导，且缺乏显式空间约束导致扰动扩散到身份无关区域。身份风格解耦进一步加剧了这些问题，在深度伪造生成过程中抑制了对抗信号。本文提出Phantom，一个统一的换脸深度伪造防护框架，在潜在和空间域联合约束扰动。Phantom自适应合成身份偏移但属性保留的目标，以引导身份感知的潜在优化，并对语义相关的面部区域施加掩蔽扰动。在最新换脸深度伪造上的大量实验表明，Phantom在躲避场景下将UniFace、INSwap和SimSwap上的防护成功率分别提升27.8%、25.6%和16.6%，同时增强了视觉质量。此外，Phantom可泛化到冒充场景，在提升感知保真度的同时实现高达10.2%的防护提升。这些结果强调了联合利用潜在和空间约束实现鲁棒且连贯的面部隐私保护的有效性。
英文摘要：
Face-swapping deepfakes pose an escalating threat to personal privacy by enabling unauthorized identity manipulation. While adversarial approaches have demonstrated success against black-box face recognition (FR) models, their applicability to face-swapping scenarios remains underexplored. In particular, reliance on fixed or random targets yields ambiguous latent guidance, and the lack of explicit spatial constraints causes perturbations to spill into identity-irrelevant regions. These issues are further exacerbated by identity-style disentanglement, which suppresses adversarial signals during deepfake generation. In this paper, we present Phantom, a unified face-swap deepfake protection framework that jointly constrains perturbations in latent and spatial domains. Phantom adaptively synthesizes identity-shifted yet attribute-preserving targets to guide identity-aware latent optimization, and applies masked perturbations confined to semantically relevant facial regions. Extensive experiments on state-of-the-art face-swapping deepfakes demonstrate that Phantom improves protection success rates in dodging scenarios by 27.8%, 25.6%, and 16.6% on UniFace, INSwapper, and SimSwap, respectively, while also enhancing visual quality. Furthermore, Phantom generalizes to impersonation scenario, yielding up to 10.2% higher protection while improving perceptual fidelity. These results underscore the effectiveness of jointly leveraging latent and spatial constraints for robust and coherent facial privacy protection.
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。
