Face Identity Unlearning for Retrieval via Embedding Dispersion
By: Mikhail Zakharov
Potential Business Impact:
Removes specific faces from recognition systems.
Face recognition systems rely on learning highly discriminative and compact identity clusters to enable accurate retrieval. However, as with other surveillance-oriented technologies, such systems raise serious privacy concerns due to their potential for unauthorized identity tracking. While several works have explored machine unlearning as a means of privacy protection, their applicability to face retrieval - especially for modern embedding-based recognition models - remains largely unexplored. In this work, we study the problem of face identity unlearning for retrieval systems and present its inherent challenges. The goal is to make selected identities unretrievable by dispersing their embeddings on the hypersphere and preventing the formation of compact identity clusters that enable re-identification in the gallery. The primary challenge is to achieve this forgetting effect while preserving the discriminative structure of the embedding space and the retrieval performance of the model for the remaining identities. To address this, we evaluate several existing approximate class unlearning methods (e.g., Random Labeling, Gradient Ascent, Boundary Unlearning, and other recent approaches) in the context of face retrieval and propose a simple yet effective dispersion-based unlearning approach. Extensive experiments on standard benchmarks (VGGFace2, CelebA) demonstrate that our method achieves superior forgetting behavior while preserving retrieval utility.
Similar Papers
Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized
CV and Pattern Recognition
Stops AI from copying art it learned from.
CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition Systems
CV and Pattern Recognition
Removes your face data from AI without hurting it.
Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting
CV and Pattern Recognition
Fixes computer "seeing" to be fair.