Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain

Large Language Models (LLMs) are increasingly deployed in finance, where unsafe behavior can lead to serious compliance and regulatory risks.However, most red-teaming research focuses on overtly harmful content and overlooks attacks that appear legitimate on the surface yet induce compliance-violating responses.We address this gap by introducing a controllable black-box multi-turn riskconcealed red-teaming framework (CoRT) that progressively conceals surface-level risk while exploiting non-compliant behaviors.CoRT contains two key components: (i) a Risk Concealment Attacker (RCA) that generates multi-turn prompts via iterative refinement, and (ii) a Risk Concealment Controller (RCC) that predicts a turn-level Risk Concealment Score (RCS) to steer RCA's follow-up style.We also build a domain-specific benchmark, FIN-Bench, with 522 instructions spanning six financial risk categories.Experiments on nine widely used LLMs show that CoRT (RCA) achieves 93.19% average attack success rate (ASR), and CoRT (RCA+RCC) further improves the average ASR to 95.00%.