用对抗攻击保护生成肖像的隐私，防止被人脸识别系统追踪。
Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks
- 通过双层加密机制，注入目标身份并增强隐私保护。
- 攻击成功率比现有方法高2.86%以上，有效干扰人脸识别。
- 适合关注数字肖像隐私与安全生成的开发者与研究者。
近期的定制化肖像生成（CPG）方法虽能生成高保真肖像，但难以防止其被恶意人脸识别系统追踪和滥用。为此，本文提出一种引入面部对抗攻击的定制化肖像生成框架（Adv-CPG）。为实现面部隐私保护，设计轻量级局部身份加密器与加密增强器，通过直接注入目标身份并添加额外身份引导，实现渐进式双层加密防护。同时，开发多模态图像定制器，以控制生成细粒度人脸特征。据我们所知，Adv-CPG是首个将面部对抗攻击引入CPG的研究。大量实验表明其优越性：相比最先进的基于噪声的攻击方法和无约束攻击方法，平均攻击成功率分别高出28.1%和2.86%。
原文摘要 · Abstract (English)
Recent Customized Portrait Generation (CPG) methods, taking a facial image and a textual prompt as inputs, have attracted substantial attention. Although these methods generate high-fidelity portraits, they fail to prevent the generated portraits from being tracked and misused by malicious face recognition systems. To address this, this paper proposes a Customized Portrait Generation framework with facial Adversarial attacks (Adv-CPG). Specifically, to achieve facial privacy protection, we devise a lightweight local ID encryptor and an encryption enhancer. They implement progressive double-layer encryption protection by directly injecting the target identity and adding additional identity guidance, respectively. Furthermore, to accomplish fine-grained and personalized portrait generation, we develop a multi-modal image customizer capable of generating controlled fine-grained facial features. To the best of our knowledge, Adv-CPG is the first study that introduces facial adversarial attacks into CPG. Extensive experiments demonstrate the superiority of Adv-CPG, e.g., the average attack success rate of the proposed Adv-CPG is 28.1% and 2.86% higher compared to the SOTA noise-based attack methods and unconstrained attack methods, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。