Picture the Epsilon: Pursuing Identity-Level Privacy Guarantees for Images

• URL: http://arxiv.org/abs/2608.17147v1
• Date: Mon, 17 Aug 2026 21:30:06 GMT
• Title: Picture the Epsilon: Pursuing Identity-Level Privacy Guarantees for Images
• Abstract summary: 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.
• Score: 3.0335372695849157
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image-to-image face generators are widely used, and visual dissimilarity between their outputs and source images is sometimes treated as evidence of privacy. Auditing whether these systems satisfy formal identity-level (epsilon, delta)-differential privacy requires choosing among several distinct routes for converting embedding-space observations into estimates or bounds on the differential privacy parameter epsilon. We present a comparative study of four such audits applicable to pre-trained, black-box face generators: a Gaussian-mechanism reading of per-identity sensitivity (GaussMech); a per-dimension kernel-density log-ratio aggregated by basic composition (KDE-LR); an analytical population-level lower bound on pure-DP epsilon derived from the maximum mean discrepancy via the total variation distance (MMD-TV); and a hypothesis-testing evaluation of a cross-validated classifier's out-of-fold ROC (ROC-HT). For each method we make explicit its assumptions, hyperparameter dependence, finite-sample limitations, and the regime in which its epsilon estimate is informative. Applied to FaceFusion and InstantID across multiple identity encoders and reference datasets, the audits consistently reveal substantial identity distinguishability while reporting markedly different epsilon estimates that reflect each method's distinct assumptions and finite-sample treatment. In this high-distinguishability regime, the experiments do not support a reliable ranking of the four methods. Their relative trade-offs should be evaluated on partially private mechanisms, which we identify as the natural next study. The resulting framework places these audits in a shared identity-level audit setting and clarifies how their assumptions and finite-sample treatments shape the resulting differential privacy estimates.

Related papers

• 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)
• Locally Private Parametric Methods for Change-Point Detection [11.057090535856839]
  We study parametric change-point detection, where the goal is to identify distributional changes in time series under local differential privacy.<n>In the non-private setting, we derive improved finite-sample accuracy guarantees for a change-point detection algorithm based on the generalized log-likelihood ratio test.<n>In the private setting, we propose two locally differentially private algorithms based on randomized response and binary mechanisms.
  arXiv  Detail & Related papers  (2026-02-14T06:11:54Z)
• Federated Learning of Quantile Inference under Local Differential Privacy [2.8462768598083823]
  We investigate learning for quantile inference under local differential privacy (LDP)<n>We propose an estimator based on local gradient descent (SGD), whose local are perturbed via a randomized mechanism with global parameters.<n>We establish normality for our estimator as well as a functional central limit theorem.
  arXiv  Detail & Related papers  (2025-09-26T02:56:39Z)
• A Sample Efficient Conditional Independence Test in the Presence of Discretization [54.047334792855345]
  Conditional Independence (CI) tests directly to discretized data can lead to incorrect conclusions.<n>Recent advancements have sought to infer the correct CI relationship between the latent variables through binarizing observed data.<n>Motivated by this, this paper introduces a sample-efficient CI test that does not rely on the binarization process.
  arXiv  Detail & Related papers  (2025-06-10T12:41:26Z)
• From Randomized Response to Randomized Index: Answering Subset Counting Queries with Local Differential Privacy [27.59934932590226]
  Local Differential Privacy (LDP) is the predominant privacy model for safeguarding individual data privacy.<n>We propose an alternative approach -- instead of perturbing values, we apply randomization to indexes of values.<n>Inspired by the deniability of randomized indexes, we present CRIAD for answering subset counting queries on set-value data.
  arXiv  Detail & Related papers  (2025-04-24T13:08:11Z)
• Differentially Private Random Feature Model [47.35176457481132]
  We produce a differentially private random feature model for privacy-preserving kernel machines.<n>We show that our method preserves privacy and derive a generalization error bound for the method.
  arXiv  Detail & Related papers  (2024-12-06T05:31:08Z)
• Mitigating LLM Hallucinations via Conformal Abstention [70.83870602967625]
  We develop a principled procedure for determining when a large language model should abstain from responding in a general domain. We leverage conformal prediction techniques to develop an abstention procedure that benefits from rigorous theoretical guarantees on the hallucination rate (error rate) Experimentally, our resulting conformal abstention method reliably bounds the hallucination rate on various closed-book, open-domain generative question answering datasets.
  arXiv  Detail & Related papers  (2024-04-04T11:32:03Z)
• Improving the Variance of Differentially Private Randomized Experiments through Clustering [16.166525280886578]
  We propose a new differentially private mechanism, "Cluster-DP"<n>We demonstrate that selecting higher-quality clusters, according to a quality metric we introduce, can decrease the variance penalty without compromising privacy guarantees.
  arXiv  Detail & Related papers  (2023-08-02T05:51:57Z)
• Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy [51.11280118806893]
  We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability. We study the local differential privacy guarantees of discrete-valued mechanisms with finite output space through the lens of $f$-differential privacy (DP) More specifically, we advance the existing literature by deriving tight $f$-DP guarantees for a variety of discrete-valued mechanisms.
  arXiv  Detail & Related papers  (2023-02-19T16:58:53Z)
• Differentially Private Federated Clustering over Non-IID Data [59.611244450530315]
  clustering clusters (FedC) problem aims to accurately partition unlabeled data samples distributed over massive clients into finite clients under the orchestration of a server. We propose a novel FedC algorithm using differential privacy convergence technique, referred to as DP-Fed, in which partial participation and multiple clients are also considered. Various attributes of the proposed DP-Fed are obtained through theoretical analyses of privacy protection, especially for the case of non-identically and independently distributed (non-i.i.d.) data.
  arXiv  Detail & Related papers  (2023-01-03T05:38:43Z)
• Partial sensitivity analysis in differential privacy [58.730520380312676]
  We investigate the impact of each input feature on the individual's privacy loss. We experimentally evaluate our approach on queries over private databases. We also explore our findings in the context of neural network training on synthetic data.
  arXiv  Detail & Related papers  (2021-09-22T08:29:16Z)
• Non-parametric Differentially Private Confidence Intervals for the Median [3.205141100055992]
  This paper proposes and evaluates several strategies to compute valid differentially private confidence intervals for the median. We also illustrate that addressing both sources of uncertainty--the error from sampling and the error from protecting the output--should be preferred over simpler approaches that incorporate the uncertainty in a sequential fashion.
  arXiv  Detail & Related papers  (2021-06-18T19:45:37Z)
• UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders [81.5490760424213]
  We propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Inspired by the saliency data labeling process, we propose probabilistic RGB-D saliency detection network.
  arXiv  Detail & Related papers  (2020-04-13T04:12:59Z)

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.