仅用相似度分数就能逆推人脸图像，突破黑箱识别系统隐私防线。
Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space
- 在主成分分析的特征空间中进行零阶优化，无需嵌入向量
- 在LFW、AgeDB-30等数据集上实现顶尖的识别准确率
- 适用于研究模型隐私漏洞或对抗攻击的学者
从黑箱人脸识别模型中重构面部图像构成重大隐私威胁。尽管许多方法依赖于嵌入向量，本文针对更困难的仅使用相似度分数的场景提出DarkerBB。该方法在由PCA生成的特征空间中执行零阶优化，重建彩色人脸图像。即使信息极度受限，实验表明DarkerBB在LFW、AgeDB-30和CFP-FP基准测试中均达到相似度仅设置下的最先进验证准确率，并具备良好的查询效率。
原文摘要 · Abstract (English)
Reconstructing facial images from black-box recognition models poses a significant privacy threat. While many methods require access to embeddings, we address the more challenging scenario of model inversion using only similarity scores. This paper introduces DarkerBB, a novel approach that reconstructs color faces by performing zero-order optimization within a PCA-derived eigenface space. Despite this highly limited information, experiments on LFW, AgeDB-30, and CFP-FP benchmarks demonstrate that DarkerBB achieves state-of-the-art verification accuracies in the similarity-only setting, with competitive query efficiency.
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。