Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
Haochun Tang, Yuliang Yan, Jiahua Lu +2
Cost-aware routing dynamically dispatches user queries to models of varying capability to balance performance and inference cost. However, the routing strategy introduces a new sec…
cs.CR2025
DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection
Yuliang Yan, Haochun Tang, Shuo Yan +1
Large language models (LLMs) are considered valuable Intellectual Properties (IP) for legitimate owners due to the enormous computational cost of training. It is crucial to protect…