用于分析人脸识别任务中个体特定模式的可解释人工智能
Explainable AI for Analyzing Person-Specific Patterns in Facial Recognition Tasks
AI总结：
本文提出可解释性方法 LEAM，通过分析 1000 名个体在 9 个人脸识别模型中的激活模式，揭示个体特定识别区域，为个性化隐私保护提供基础。
摘要：
人脸识别系统的广泛部署带来了重大的隐私风险，从而推动了对有效对抗措施的需求。当前的对抗技术采用通用方法，而非适应个体面部特征，这限制了其有效性和隐蔽性。在本工作中，我们提出了层嵌入激活映射（Layer Embedding Activation Mapping，LEAM），这是一种新技术，能够在个体层面识别哪些面部区域对识别贡献最大。与旨在欺骗识别系统的对抗攻击方法不同，LEAM 是一种可解释性技术，旨在理解这些系统的工作方式，为未来的隐私保护研究提供洞见。我们将 LEAM 与人脸解析器相结合，分析了来自 1000 名个体的数据，并覆盖 9 个预训练人脸识别模型。我们的分析表明，尽管人脸识别模型中的不同层在其关注区域上存在显著差异，但从整体激活模式来看，这些模型在不同架构之间通常优先关注相似的面部区域；同一人的图像之间激活模式的相似性显著更高（Bhattacharyya 系数：0.32–0.57），而不同个体之间则较低（0.04–0.13），这验证了个体特定识别模式的存在。我们的结果表明，人脸识别模型优先关注人脸图像的中心区域（其中鼻子区域占关键识别区域的 18.9%–29.7%），同时仍将注意力分布在多个面部片段上。通过验证性遮挡实验确认了相关面部区域的正确选择，仅基于 LEAM 识别出的最相关的 1% 图像像素，且这些区域被证明可在不同模型之间迁移。我们的发现为未来以 LEAM 所选择的待扰动区域为核心的个体定制化隐私保护系统奠定了基础。
英文摘要：
The proliferation of facial recognition systems presents major privacy risks, driving the need for effective countermeasures. Current adversarial techniques apply generalized methods rather than adapting to individual facial characteristics, limiting their effectiveness and inconspicuousness. In this work, we introduce Layer Embedding Activation Mapping (LEAM), a novel technique that identifies which facial areas contribute most to recognition at an individual level. Unlike adversarial attack methods that aim to fool recognition systems, LEAM is an explainability technique designed to understand how these systems work, providing insights that could inform future privacy protection research. We integrate LEAM with a face parser to analyze data from 1000 individuals across 9 pre-trained facial recognition models. Our analysis reveals that while different layers within facial recognition models vary significantly in their focus areas, these models generally prioritize similar facial regions across architectures when considering their overall activation patterns, which show significantly higher similarity between images of the same individual (Bhattacharyya Coefficient: 0.32-0.57) vs. different individuals (0.04-0.13), validating the existence of person-specific recognition patterns. Our results show that facial recognition models prioritize the central region of face images (with nose areas accounting for 18.9-29.7% of critical recognition regions), while still distributing attention across multiple facial fragments. Proper selection of relevant facial areas was confirmed using validation occlusions, based on just 1% of the most relevant, LEAM-identified, image pixels, which proved to be transferable across different models. Our findings establish the foundation for future individually tailored privacy protection systems centered around LEAM's choice of areas to be perturbed.
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。
