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

arXiv:2608.17147 · cs.CR, cs.LG · Submitted 2026-08-17 · Read on arXiv

cs.CR, cs.LG

Submitted: 2026-08-17

Updated: 2026-09-04

Comments: 18 pages, 5 figures, 8 tables

Code: https://github.com/deepinsight/insightface

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Differential Privacy — 20× in this paper · explained in 4 episodes
• AUC — 16× in this paper · explained in 2 episodes
• Calibration — 11× in this paper · explained in 7 episodes
• Embeddings — 11× in this paper · explained in 2 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Differentially Private — 3× in this paper · explained in 3 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Provenance — 3× in this paper · explained in 4 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Hilbert Space — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Heteroscedasticity — 1× in this paper · explained in 2 episodes

Sources

• InstantID: Zero-shot Identity-Preserving Generation in Seconds
• DP-Image: Differential Privacy for Image Data in Feature Space
• Auditing Differential Privacy in High Dimensions with the Kernel Quantum R'enyi Divergence
• Membership Inference of Diffusion Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs