First systematic security analysis of AI-Apps on pre-trained model hubs identifies five threat categories, ten attack vectors, three novel architectural flaws, and real-world prevalence of credential leaks and injection risks across 970k+ apps.
Large lan- guage model supply chain: Open problems from the security perspective.CoRR abs/2411.01604
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
ORPO is most effective at misaligning LLMs while DPO excels at realigning them, though it reduces utility, revealing an asymmetry between attack and defense methods.
citing papers explorer
-
Your Space is My Zone: Demystifying the Security Risks of AI-Powered Applications on Pre-Trained Model Hubs
First systematic security analysis of AI-Apps on pre-trained model hubs identifies five threat categories, ten attack vectors, three novel architectural flaws, and real-world prevalence of credential leaks and injection risks across 970k+ apps.
-
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
ORPO is most effective at misaligning LLMs while DPO excels at realigning them, though it reduces utility, revealing an asymmetry between attack and defense methods.