基于树形对话强化策略优化的红队攻击

摘要

尽管人工智能安全领域近期取得了快速进展，当前的大型语言模型在多轮交互场景中仍易受对抗性攻击，攻击者会在对话轮次间策略性地调整提示，构成更为严峻且现实的挑战。现有发现安全漏洞的方法要么依赖人工红队测试与专家合作，要么采用基于预定义模板和人工整理的攻击数据的自动化方法，且大多聚焦于单轮攻击。然而，这些方法未能探索多轮攻击的广阔可能性空间，忽视了复杂对话动态和策略性对话规划中涌现的新型攻击轨迹。鉴于最新研究发现，与单轮攻击相比，大型语言模型对多轮攻击表现出显著更高的脆弱性，这一空白尤为关键。我们提出了DialTree-RPO，一种与树搜索相结合的在线策略强化学习框架，通过将对话视为序列决策问题，自主发现多样化的多轮攻击策略，无需人工整理数据即可实现系统化探索。通过大量实验，我们的方法不仅在10个目标模型上比之前最先进的方法实现了超过25.9%的攻击成功率提升，还通过学习最大化多轮攻击成功的最优对话策略，有效揭示了新的攻击策略。

English

Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction settings, where attackers strategically adapt their prompts across conversation turns and pose a more critical yet realistic challenge. Existing approaches that discover safety vulnerabilities either rely on manual red-teaming with human experts or employ automated methods using pre-defined templates and human-curated attack data, with most focusing on single-turn attacks. However, these methods did not explore the vast space of possible multi-turn attacks, failing to consider novel attack trajectories that emerge from complex dialogue dynamics and strategic conversation planning. This gap is particularly critical given recent findings that LLMs exhibit significantly higher vulnerability to multi-turn attacks compared to single-turn attacks. We propose DialTree-RPO, an on-policy reinforcement learning framework integrated with tree search that autonomously discovers diverse multi-turn attack strategies by treating the dialogue as a sequential decision-making problem, enabling systematic exploration without manually curated data. Through extensive experiments, our approach not only achieves more than 25.9% higher ASR across 10 target models compared to previous state-of-the-art approaches, but also effectively uncovers new attack strategies by learning optimal dialogue policies that maximize attack success across multiple turns.

基于树形对话强化策略优化的红队攻击

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks

摘要

Support