all InfoSec news
Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
May 2, 2024, 4:11 a.m. | Haozhe Liu, Wentian Zhang, Bing Li, Bernard Ghanem, J\"urgen Schmidhuber
cs.CR updates on arXiv.org arxiv.org
Abstract: Foundational generative models should be traceable to protect their owners and facilitate safety regulation. To achieve this, traditional approaches embed identifiers based on supervisory trigger-response signals, which are commonly known as backdoor watermarks. They are prone to failure when the model is fine-tuned with nontrigger data. Our experiments show that this vulnerability is due to energetic changes in only a few 'busy' layers during fine-tuning. This yields a novel arbitrary-in-arbitrary-out (AIAO) strategy that makes watermarks …
arxiv backdoor cs.cr cs.cv data diffusion models failure foundational generative generative models protect regulation response safety signals traceable trigger watermarks
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Security Analyst
@ Halton Region | Oakville, Ontario, Canada
Senior Cyber Security Analyst
@ Valley Water | San Jose, CA
Consultant Sécurité SI Gouvernance - Risques - Conformité H/F - Strasbourg
@ Hifield | Strasbourg, France
Lead Security Specialist
@ KBR, Inc. | USA, Dallas, 8121 Lemmon Ave, Suite 550, Texas
Consultant SOC / CERT H/F
@ Hifield | Sèvres, France