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

arXiv: https://arxiv.org/abs/2509.10546 · HTML: https://mlsanity.com/paper/2509.10546/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 7 Sep 2025.

## Placed in

- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 28 of 28)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack](https://mlsanity.com/paper/2404.01833/) (2024)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily](https://mlsanity.com/paper/2311.08268/) (2023)
- [Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment](https://mlsanity.com/paper/2308.09662/) (2023)
- [PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance](https://mlsanity.com/paper/2306.05443/) (2023)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization](https://mlsanity.com/paper/2311.09096/) (2023)
- [X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents](https://mlsanity.com/paper/2504.13203/) (2025)
- [A Survey of Large Language Models in Finance (FinLLMs)](https://mlsanity.com/paper/2402.02315/) (2024)
- [Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM](https://mlsanity.com/paper/2405.05610/) (2024)
- [JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models](https://mlsanity.com/paper/2407.01599/) (2024)
- [AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications](https://mlsanity.com/paper/2311.08592/) (2023)
- [Foot-In-The-Door: A Multi-turn Jailbreak for LLMs](https://mlsanity.com/paper/2502.19820/) (2025)
- [MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue](https://mlsanity.com/paper/2411.03814/) (2024)
- [FinLlama: Financial Sentiment Classification for Algorithmic Trading Applications](https://mlsanity.com/paper/2403.12285/) (2024)
- [Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models](https://mlsanity.com/paper/2501.13772/) (2025)
- [Understanding and Mitigating Risks of Generative AI in Financial Services](https://mlsanity.com/paper/2504.20086/) (2025)
- [Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation](https://mlsanity.com/paper/2505.18556/) (2025)

## Built on by (most cited first, 6 of 6)

- [TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?](https://mlsanity.com/paper/2512.02261/) (2025)
- [Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services](https://mlsanity.com/paper/2603.10807/) (2026)
- [PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models](https://mlsanity.com/paper/2606.25442/) (2026)
- [MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems](https://mlsanity.com/paper/2606.30602/) (2026)
- [Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models](https://mlsanity.com/paper/2608.09551/) (2026)
- [SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes](https://mlsanity.com/paper/2609.19705/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly deployed in finance, where unsafe behavior can lead to serious regulatory risks. However, most red-teaming research focuses on overtly harmful content and overlooks attacks that appear legitimate on the surface yet induce regulatory-violating responses. We address this gap by introducing a controllable black-box multi-turn risk-concealed red-teaming framework (CoRT) that progressively conceals surface-level risk while exploiting regulatory-violating 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 built a domain-specific benchmark, FinRisk-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%. Our code and FinRisk-Bench are available at https://github.com/gcheng128/CoRT.