On the Capacity of Distinguishable Synthetic Identity Generation under Face Verification

• URL: http://arxiv.org/abs/2604.10641v1
• Date: Sun, 12 Apr 2026 13:42:39 GMT
• Title: On the Capacity of Distinguishable Synthetic Identity Generation under Face Verification
• Abstract summary: We study how many synthetic identities can be generated so that a face verifier declares same-identity pairs as matches and different-identity pairs as non-matches at a fixed threshold $$.<n>We define the capacity of distinguishable identity generation as the largest number of latent identities whose induced embedding satisfy prescribed same-identity and different-identity verification constraints.
• Score: 4.832750949021042
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study how many synthetic identities can be generated so that a face verifier declares same-identity pairs as matches and different-identity pairs as non-matches at a fixed threshold $τ$. We formalize this question for a generative face-recognition pipeline consisting of a generator followed by a normalized recognition map with outputs on the unit hypersphere. We define the capacity of distinguishable identity generation as the largest number of latent identities whose induced embedding distributions satisfy prescribed same-identity and different-identity verification constraints. In the deterministic view-invariant regime, we show that this capacity is characterized by a spherical-code problem over the realizable set of embeddings, and reduces to the classical spherical-code quantity under a full angular expressivity assumption. For stochastic identity generation, we introduce a centered model and derive a sufficient admissibility condition in which the required separation between identity centers is $\arccos(τ)+2ρ$, where $ρ$ is a within-identity concentration radius. Under full angular expressivity, this yields spherical-code-based achievable lower bounds and a positive asymptotic lower bound on the exponential growth rate with embedding dimension. We also introduce a prior-constrained random-code capacity, in which latent identities are sampled independently from a given prior, and derive high-probability lower bounds in terms of pairwise separation-failure probabilities of the induced identity centers. Under a stronger full-cap-support model, we obtain a converse and an exact spherical-code characterization.

Related papers

• Picture the Epsilon: Pursuing Identity-Level Privacy Guarantees for Images [3.0335372695849157]
  Image-to-image face generators are widely used, and visual dissimilarity between their outputs and source images is sometimes treated as evidence of privacy.<n>We present a comparative study of four such audits applicable to pre-trained, black-box face generators.
  arXiv  Detail & Related papers  (2026-08-17T21:30:06Z)
• Identity from the Outside: A Conceptual Framework and Research Program for AI Personality Clones [0.0]
  AI "personality clones" force a re-examination of personal identity in operational terms.<n>We distinguish three criteria that "identity" conflates: fidelity to a target person, generic human-likeness, and individuality.<n>We propose a six-term factorization of observed identity with a state-space formulation.
  arXiv  Detail & Related papers  (2026-07-27T18:18:21Z)
• The Resolution of the Identity as a Generator of Exact Integral Identities: A Coherent-State Approach [0.0]
  We show that the resolution of the identity associated with Glauber coherent states is a direct generator of exact complex Gaussian integral identities.<n>We highlight an intriguing non-commuting behavior in the parameter limits of the master identity.<n>This approach offers a transparent and visually intuitive illustration of how Hilbert-space completeness inherently encodes vast libraries of exact, solvable mathematical relations.
  arXiv  Detail & Related papers  (2026-07-14T14:35:09Z)
• DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation [52.23323703015865]
  We propose a post-training framework called DivRL that jointly optimize identity consistency and structural diversity simultaneously.<n>We introduce a Negative Self-Similarity Measure (nSSM) to quantify structural diversity, and Visual Semantic Matching (VSM) to evaluate identity consistency.
  arXiv  Detail & Related papers  (2026-06-22T21:22:42Z)
• Computational Identifiability [58.12019389497595]
  'Identical identifiability' assumes properties, infinite data, or other mathematically idealized conditions.<n>'Computational identifiability' is to instead define a finite computational search procedure for an empirical estimator.<n>We show how this framework allows us to answer fine-grained, practical identification questions.
  arXiv  Detail & Related papers  (2026-06-08T19:39:59Z)
• Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models [51.56484100374058]
  We develop a framework for estimating how many near-orthogonal directions a model can support.<n>Applying this metric across dozens of open-source models reveals two classes: models with high $varepsilon$ whose embeddings lack near-orthogonal structure, and models with low $varepsilon$ that maintain it.
  arXiv  Detail & Related papers  (2026-06-01T18:28:56Z)
• Identity-Decoupled Anonymization for Visual Evidence in Multi-modal Retrieval-Augmented Generation [9.39195684989942]
  Identity-Decoupled MRAG is a framework that interposes a generative anonymization module between retrieval and generation.<n>Our approach consists of three components: (i)a disentangled variational encoder that factorizes each face into an identity code and a spatially-structured attribute code, regularized by a mutual-information penalty and a gradient-based independence term; (ii)a manifold-aware rejection sampler that replaces the identity code with a synthetic one guaranteed to be both distinct from the original and realistic; and (iii)a conditional latent diffusion generator that synthesizes the anonymized face from the replacement identity and the
  arXiv  Detail & Related papers  (2026-04-26T07:42:33Z)
• Homogenized Transformers [5.290251602267728]
  We study a random model of deep multi-head self-attention in which the weights are resampled independently across layers and heads.<n>We prove that, under suitable joint scalings of the depth, the residual step size, and the number of heads, this dynamics admits a nontrivialed limit.
  arXiv  Detail & Related papers  (2026-04-02T12:39:27Z)
• AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation [55.94507360511886]
  We propose AnyCrowd, a Transformer-based video generation framework capable of scaling to an arbitrary number of characters.<n>Specifically, we first introduce an Instance-Isolated Latent Representation (IILR), which encodes character instances independently prior to DiT processing to prevent latent identity entanglement.<n>Building on this disentangled representation, we further propose Tri-Stage Decoupled Attention (TSDA) to bind identities to driving poses by decomposing self-attention into: (i) instance-aware foreground attention, (ii) background-centric interaction, and (iii) global-background coordination.
  arXiv  Detail & Related papers  (2026-03-16T15:25:04Z)
• Sample Complexity of Causal Identification with Temporal Heterogeneity [6.5822033630228916]
  We show that temporal structure is shown to effectively substitute for missing environmental diversity.<n>This work shifts the focus from whether causal structure is identifiable to whether it is statistically recoverable in practice.
  arXiv  Detail & Related papers  (2026-02-06T17:44:00Z)
• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization [55.29071072675132]
  Face anonymization aims to conceal identity information while preserving non-identity attributes.<n>We propose textbfIDsuperscript2Face, a training-centric anonymization framework.<n>We show that IDtextsuperscript2Face outperforms existing methods in visual quality, identity suppression, and utility preservation.
  arXiv  Detail & Related papers  (2025-10-28T09:28:12Z)
• WithAnyone: Towards Controllable and ID Consistent Image Generation [83.55786496542062]
  Identity-consistent generation has become an important focus in text-to-image research.<n>We develop a large-scale paired dataset tailored for multi-person scenarios.<n>We propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity.
  arXiv  Detail & Related papers  (2025-10-16T17:59:54Z)
• From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization [9.614305363044737]
  Person re-identification (ReID) aims to extract accurate identity representation features.<n>We propose a Training-Free Feature Centralization ReID framework (Pose2ID) to reduce individual noise.<n>Our method sets new state-of-the-art results across standard, cross-modality, and occluded ReID tasks.
  arXiv  Detail & Related papers  (2025-03-02T15:31:48Z)
• ID$^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition [60.15830516741776]
  Synthetic face recognition (SFR) aims to generate datasets that mimic the distribution of real face data. We introduce a diffusion-fueled SFR model termed $textID3$. $textID3$ employs an ID-preserving loss to generate diverse yet identity-consistent facial appearances.
  arXiv  Detail & Related papers  (2024-09-26T06:46:40Z)
• Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation [27.149540844056023]
  We tackle the problems of latent variables identification and out-of-support'' image generation in representation learning. We show that both are possible for a class of decoders that we call additive. We show theoretically that additive decoders can generate novel images by recombining observed factors of variations in novel ways.
  arXiv  Detail & Related papers  (2023-07-05T18:48:20Z)
• Posterior Collapse and Latent Variable Non-identifiability [54.842098835445]
  We propose a class of latent-identifiable variational autoencoders, deep generative models which enforce identifiability without sacrificing flexibility. Across synthetic and real datasets, latent-identifiable variational autoencoders outperform existing methods in mitigating posterior collapse and providing meaningful representations of the data.
  arXiv  Detail & Related papers  (2023-01-02T06:16:56Z)

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.