activity
20232026
most citedRegret-Based Defense in Adversarial Reinforcement Learning

1 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Robust Critics: Defending LLMs Against Multi-Turn Attacks

Roman Belaire, Arunesh Sinha, Pradeep Varakantham

When a user asks a language model something harmful, is it a genuine attack or a misunderstood but well-meaning question? This ambiguity is one of the central challenges of LLM saf…