Do Defenses Against LLM Extraction Work Across Attacks? A Lifecycle Benchmark of Black-Box Model Extraction

arXiv:2610.00839v1 Announce Type: new Abstract: Large language models (LLMs) deployed through text-only APIs face model extraction risks, as adversaries can collect their responses to train surrogates that reproduce their capabilities. While prior work has developed diverse attacks and defenses, evaluations remain fragmented across access assumptions, model configurations, query budgets, and security objectives, limiting comparability across methods.

Read the full article at arXiv cs.CR →