June 11, 2024, 4:13 a.m. | Zihao Luo, Xilie Xu, Feng Liu, Yun Sing Koh, Di Wang, Jingfeng Zhang

cs.CR updates on arXiv.org arxiv.org

arXiv:2402.11989v2 Announce Type: replace-cross
Abstract: Low-rank adaptation (LoRA) is an efficient strategy for adapting latent diffusion models (LDMs) on a private dataset to generate specific images by minimizing the adaptation loss. However, the LoRA-adapted LDMs are vulnerable to membership inference (MI) attacks that can judge whether a particular data point belongs to the private dataset, thus leading to the privacy leakage. To defend against MI attacks, we first propose a straightforward solution: Membership-Privacy-preserving LoRA (MP-LoRA). MP-LoRA is formulated as a …

adaptation arxiv cs.cr cs.cv cs.lg diffusion models low privacy

Director of IT & Information Security

@ Outside | Boulder, CO

Information Security Governance Manager

@ Informa Group Plc. | London, United Kingdom

Senior Risk Analyst - Application Security (Remote, United States)

@ Dynatrace | Waltham, MA, United States

Security Software Engineer (Starshield) - Top Secret Clearance

@ SpaceX | Washington, DC

Network & Security Specialist (IT24055)

@ TMEIC | Roanoke, Virginia, United States

Senior Security Engineer - Application Security (F/M/N)

@ Swile | Paris, France