提出线性子空间移除法，在保留图像检索能力的同时有效降低视觉编码器的身份泄露风险。
From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal
- 设计线性投影方法，从编码器中移除估计的身份子空间，实现隐私净化。
- 在CelebA-20和VGGFace2上验证，移除后线性攻击接近随机水平，但检索性能仅轻微下降。
- 首次对非人脸识别模型进行攻防校准的隐私审计，适合关注图像隐私保护的研究者。
冻结的视觉嵌入（如CLIP、DINOv2/v3、SSCD）广泛用于图像检索与完整性系统，但在含人脸数据上的应用受限于未量化的人脸身份泄露及缺乏可部署的缓解手段。本文从攻击者视角出发，构建了基准评估体系：包含低误接受率下的开放集验证、基于扩散的模板反演校验，以及等面积扰动下的人脸上下文归因。同时提出一种一次性线性投影方法——身份净化投影（ISP），通过移除估计的身份子空间，保留互补空间以维持功能实用性。在CelebA-20和VGGFace2数据集上，结果显示这些编码器对开放集线性探测具有鲁棒性，其中CLIP比DINOv2/v3和SSCD更易泄露身份；对模板反演也具备鲁棒性，且以上下文为主导。进一步表明，使用ISP后线性访问几乎达到随机水平，同时保持高非生物特征实用性，并能在不同数据集间良好迁移，仅有小幅性能下降。本研究建立了首个针对非人脸识别编码器的攻防校准面部隐私审计，证明线性子空间移除可在保障视觉搜索与检索性能的前提下实现强隐私保障。
原文摘要 · Abstract (English)
Frozen visual embeddings (e.g., CLIP, DINOv2/v3, SSCD) power retrieval and integrity systems, yet their use on face-containing data is constrained by unmeasured identity leakage and a lack of deployable mitigations. We take an attacker-aware view and contribute: (i) a benchmark of visual embeddings that reports open-set verification at low false-accept rates, a calibrated diffusion-based template inversion check, and face-context attribution with equal-area perturbations; and (ii) propose a one-shot linear projector that removes an estimated identity subspace while preserving the complementary space needed for utility, which for brevity we denote as the identity sanitization projection ISP. Across CelebA-20 and VGGFace2, we show that these encoders are robust under open-set linear probes, with CLIP exhibiting relatively higher leakage than DINOv2/v3 and SSCD, robust to template inversion, and are context-dominant. In addition, we show that ISP drives linear access to near-chance while retaining high non-biometric utility, and transfers across datasets with minor degradation. Our results establish the first attacker-calibrated facial privacy audit of non-FR encoders and demonstrate that linear subspace removal achieves strong privacy guarantees while preserving utility for visual search and retrieval.
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。