Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space
This addresses privacy threats by enabling model inversion in more challenging scenarios, though it is incremental as it builds on existing methods for black-box attacks.
The paper tackled the problem of reconstructing facial images from black-box recognition models using only similarity scores, and DarkerBB achieved state-of-the-art verification accuracies on benchmarks like LFW, AgeDB-30, and CFP-FP.
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.