Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models
Face recognition models represent each face as an embedding vector on the unit hypersphere by clustering embeddings of the same identity while pushing different identities apart through angular-margin losses. Because these losses act only on training identities, non-member identities may form clusters with different geometric properties. In this paper, we quantify the magnitude of this difference and what training-time factors control it. We compute four statistics based on cluster geometry across 180 face recognition models in a factorial design over IResNet backbone size, loss head, training duration, and the number of training identities, and evaluate each configuration on nine benchmarks. Our results indicate that the number of training identities has the largest effect on member/non-member separability, while backbone and loss head contribute far less, and that, on a same-domain held-out reference, the geometric membership signal decreases monotonically as more identities are added to training. We provide an analysis of cross-domain (pose, age, quality, ethnicity) non-member benchmarks and report that these inflate the apparent membership signal. Finally, we fuse all four statistics with a learned classifier to reveal additional membership information beyond the best individual statistic.
Code (0)
등록된 구현이 없습니다.
Tasks
Face RecognitionSimilar Papers 제목 키워드 기반
Hyperspherical Embedding for Point Cloud Completion
Most real-world 3D measurements from depth sensors are incomplete, and to address this issue the point cloud completion task aims to predict the complete shapes of objects from partial observations. Previous works often …
DecoderMulti-Task LearningPoint Cloud CompletionHyperspherical Query Likelihood Models with Word Embeddings
This paper presents an initial study on hyperspherical query likelihood models (QLMs) for information retrieval (IR). Our motivation is to naturally utilize pre-trained word embeddings for probabilistic IR. To this end, …
Information RetrievalLanguage ModelingLanguage ModellingRetrieval+2Modelling and Quantifying Membership Information Leakage in Machine Learning
Machine learning models have been shown to be vulnerable to membership inference attacks, i.e., inferring whether individuals' data have been used for training models. The lack of understanding about factors contributing…
BIG-bench Machine LearningTwo-sample testingSphereRE: Distinguishing Lexical Relations with Hyperspherical Relation Embeddings
Lexical relations describe how meanings of terms relate to each other. Typical examples include hypernymy, synonymy, meronymy, etc. Automatic distinction of lexical relations is vital for NLP applications, and also chall…
RelationRepresentation LearningGeometry-Preserving Aggregation for Mixture-of-Experts Embedding Models
Mixture-of-Experts (MoE) embedding models combine expert outputs using weighted linear summation, implicitly assuming a linear subspace structure in the embedding space. This assumption is shown to be inconsistent with t…
Semantic Similarity