Face Identity Unlearning for Retrieval via Embedding Dispersion

• URL: http://arxiv.org/abs/2512.13317v1
• Date: Mon, 15 Dec 2025 13:35:28 GMT
• Title: Face Identity Unlearning for Retrieval via Embedding Dispersion
• Authors: Mikhail Zakharov,
• Abstract summary: Face recognition systems rely on learning highly discriminative and compact identity clusters to enable accurate retrieval.<n>In this work, we study the problem of face identity unlearning for retrieval systems and present its inherent challenges.<n>The primary challenge is to achieve this forgetting effect while preserving the discriminative structure of the embedding space.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition Systems [0.0]
  We introduce CURE, the first unsupervised unlearning framework for facial recognition systems.<n>CURE effectively removes targeted samples while preserving overall performance.<n>We also propose a novel metric, the Unlearning Efficiency Score (UES), which balances forgetting and retention stability.
  arXiv  Detail & Related papers  (2025-09-23T20:42:40Z)
• Deep Learning Models for Robust Facial Liveness Detection [56.08694048252482]
  This study introduces a robust solution through novel deep learning models addressing the deficiencies in contemporary anti-spoofing techniques.<n>By innovatively integrating texture analysis and reflective properties associated with genuine human traits, our models distinguish authentic presence from replicas with remarkable precision.
  arXiv  Detail & Related papers  (2025-08-12T17:19:20Z)
• FRIDAY: Mitigating Unintentional Facial Identity in Deepfake Detectors Guided by Facial Recognizers [16.702284414478292]
  Previous Deepfake detection methods perform well within their training domains, but their effectiveness diminishes significantly with new synthesis techniques.<n>Recent studies have revealed that detection models often create decision boundaries based on facial identity rather than synthetic artifacts.<n>We propose Facial Recognition Identity Attenuation (FRIDAY), a novel training method that mitigates facial identity influence using a face recognizer.
  arXiv  Detail & Related papers  (2024-12-19T08:21:28Z)
• Local Features Meet Stochastic Anonymization: Revolutionizing Privacy-Preserving Face Recognition for Black-Box Models [54.88064975480573]
  The task of privacy-preserving face recognition (PPFR) currently faces two major unsolved challenges.<n>By disrupting global features while enhancing local features, we achieve effective recognition even in black-box environments.<n>Our method achieves an average recognition accuracy of 94.21% on black-box models, outperforming existing methods in both privacy protection and anti-reconstruction capabilities.
  arXiv  Detail & Related papers  (2024-12-11T10:49:15Z)
• CLFace: A Scalable and Resource-Efficient Continual Learning Framework for Lifelong Face Recognition [0.0]
  CLFace is a continual learning framework designed to preserve and incrementally extend the learned knowledge. It eliminates the classification layer, resulting in a resource-efficient FR model that remains fixed throughout lifelong learning. It incorporates a geometry-preserving distillation scheme to maintain the orientation of the teacher model's feature embedding.
  arXiv  Detail & Related papers  (2024-11-21T06:55:43Z)
• Pose-Transformation and Radial Distance Clustering for Unsupervised Person Re-identification [5.522856885199346]
  Person re-identification (re-ID) aims to tackle the problem of matching identities across non-overlapping cameras. Supervised approaches require identity information that may be difficult to obtain and are inherently biased towards the dataset they are trained on. We propose an unsupervised approach to the person re-ID setup. Having zero knowledge of true labels, our proposed method enhances the discriminating ability of the learned features.
  arXiv  Detail & Related papers  (2024-11-06T20:55:30Z)
• Time-Aware Face Anti-Spoofing with Rotation Invariant Local Binary Patterns and Deep Learning [50.79277723970418]
  imitation attacks can lead to erroneous identification and subsequent authentication of attackers. Similar to face recognition, imitation attacks can also be detected with Machine Learning. We propose a novel approach that promises high classification accuracy by combining previously unused features with time-aware deep learning strategies.
  arXiv  Detail & Related papers  (2024-08-27T07:26:10Z)
• UniForensics: Face Forgery Detection via General Facial Representation [60.5421627990707]
  High-level semantic features are less susceptible to perturbations and not limited to forgery-specific artifacts, thus having stronger generalization. We introduce UniForensics, a novel deepfake detection framework that leverages a transformer-based video network, with a meta-functional face classification for enriched facial representation.
  arXiv  Detail & Related papers  (2024-07-26T20:51:54Z)
• Disguise without Disruption: Utility-Preserving Face De-Identification [40.484745636190034]
  We introduce Disguise, a novel algorithm that seamlessly de-identifies facial images while ensuring the usability of the modified data. Our method involves extracting and substituting depicted identities with synthetic ones, generated using variational mechanisms to maximize obfuscation and non-invertibility. We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks.
  arXiv  Detail & Related papers  (2023-03-23T13:50:46Z)
• Towards Intrinsic Common Discriminative Features Learning for Face Forgery Detection using Adversarial Learning [59.548960057358435]
  We propose a novel method which utilizes adversarial learning to eliminate the negative effect of different forgery methods and facial identities. Our face forgery detection model learns to extract common discriminative features through eliminating the effect of forgery methods and facial identities.
  arXiv  Detail & Related papers  (2022-07-08T09:23:59Z)
• Federated Learning for Face Recognition with Gradient Correction [52.896286647898386]
  In this work, we introduce a framework, FedGC, to tackle federated learning for face recognition. We show that FedGC constitutes a valid loss function similar to standard softmax.
  arXiv  Detail & Related papers  (2021-12-14T09:19:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.