LCMem: A Universal Model for Robust Image Memorization Detection

TL;DR

LCMem is a novel cross-domain model that significantly improves the reliability and scalability of image memorization detection, addressing privacy concerns in generative image modeling.

Contribution

Introduces LCMem, a unified two-stage model for robust image memorization detection across domains, combining re-identification and copy detection tasks.

Findings

Up to 16% improvement in re-identification accuracy

Up to 30% improvement in copy detection accuracy

Sets new standards for cross-domain privacy auditing

Abstract

Recent advances in generative image modeling have achieved visual realism sufficient to deceive human experts, yet their potential for privacy preserving data sharing remains insufficiently understood. A central obstacle is the absence of reliable memorization detection mechanisms, limited quantitative evaluation, and poor generalization of existing privacy auditing methods across domains. To address this, we propose to view memorization detection as a unified problem at the intersection of re-identification and copy detection, whose complementary goals cover both identity consistency and augmentation-robust duplication, and introduce Latent Contrastive Memorization Network (LCMem), a cross-domain model evaluated jointly on both tasks. LCMem achieves this through a two-stage training strategy that first learns identity consistency before incorporating augmentation-robust copy detection. Across six benchmark datasets, LCMem achieves improvements of up to 16 percentage points on re-identification and 30 percentage points on copy detection, enabling substantially more reliable memorization detection at scale. Our results show that existing privacy filters provide limited performance and robustness, highlighting the need for stronger protection mechanisms. We show that LCMem sets a new standard for cross-domain privacy auditing, offering reliable and scalable memorization detection. Code and model is publicly available at https://github.com/MischaD/LCMem.