Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.14421 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917148533719040 |
|---|---|
| author | Dombrowski, Mischa Nützel, Felix Kainz, Bernhard |
| author_facet | Dombrowski, Mischa Nützel, Felix Kainz, Bernhard |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14421 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LCMem: A Universal Model for Robust Image Memorization Detection Dombrowski, Mischa Nützel, Felix Kainz, Bernhard Computer Vision and Pattern Recognition 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. |
| title | LCMem: A Universal Model for Robust Image Memorization Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.14421 |