paper
NAMESAKES: Probing Identity Memorization in Text-to-Image Models
paperactiveprovisional
namesakes-probing-identity-memorization-in-text-to-image-models-55eec01c·1 events·first seen 2d agoAliases: NAMESAKES: Probing Identity Memorization in Text-to-Image Models
Co-occurring entities
More like this (12)
text-to-image modelsRecalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented ModelsA Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images from GPT-Image-2embedding modelsModeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language ModelsMatryoshka Representation LearningLanguage Models Need Sleep: Learning to Self-Modify and Consolidate MemoriesConnecting Speech to Words through ImagesSubject-driven Image GenerationRepresentational Similarity AnalysisExpert-Aware Causal Tracing of Factual Recall in Sparse MoE Language ModelsFrom Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models
Recent events (1)
NAMESAKES: Black-box probe for identity memorization in text-to-image models
Researchers introduce NAMESAKES, a black-box behavioral probe and accompanying dataset for detecting whether text-to-image models have memorized specific individuals' likenesses from training data. The approach requires no reference photos, training data access, or model internals, making it broadly applicable. The dataset covers over one thousand public figures across fame levels, and experiments on state-of-the-art T2I models show the probe reliably distinguishes memorized from unrecognized identities. The work addresses a concrete privacy concern about facial memorization in generative models.