安全、治理与可靠性 颠覆级 暂无讲解视频
发表时间
2026-07-28
arXiv
2607.23496

收录解读

大型语言模型虽经安全对齐训练,但在特定场景下仍可能被绕过,现有红队方法主要依赖实际攻击结果发现有效场景,缺乏对场景削弱拒绝机制的因果理解。

本文发现场景包裹提示会激活内部场景方向,其因果干预持续降低拒绝分数。基于此提出Concept2Scenario框架,利用稀疏自编码器实例化概念空间,通过概念归因识别拒绝抑制的关键概念,并转化为可解释的自然语言场景,进一步通过交互归因发现协同场景组合。

在三个开源模型、两个安全基准和六种黑盒越狱方法上,发现的可复用场景将平均攻击成功率提升多达18.2个百分点。场景组合优于单个成分,且迭代攻击所需轮数更少。场景可迁移至GPT-5、Claude-Haiku-4.5和Gemini-3-Flash。

该工作建立了一个可解释的漏洞发现框架,揭示了场景级拒绝脆弱性的共享性,对安全对齐和红队评估有重要价值。但尚未成为全新的安全范式,仍需更广泛的理论构建。

原始摘要

Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teaming methods empirically identify effective scenarios through observed attack outcomes, but why particular scenarios weaken refusal remains mechanistically unclear. Meanwhile, mechanistic interpretability studies have characterized both refusal directions and jailbreak-associated features, without explaining the relationship between the two representations. In this work, we show that scenario-wrapped prompts activate internal scenario directions whose causal steering consistently reduces refusal scores. Building on this finding, we propose \textsc{Concept2Scenario}, a concept-based attribution framework for vulnerable scenario discovery. It instantiates a broad concept space with a sparse autoencoder, attributes refusal suppression to individual concepts, translates the identified concepts into interpretable natural-language scenarios, and identifies synergistic scenario combinations through interaction attribution. Across three open-source models, two safety benchmarks, and six black-box jailbreak methods, the discovered scenarios serve as reusable priors that improve average attack success rates by up to $18.2$ percentage points. They also transfer to GPT-5, Claude-Haiku-4.5, and Gemini-3-Flash, suggesting that some scenario-level refusal vulnerabilities are shared across model families. Moreover, the identified combinations outperform their individual constituents and enable iterative attacks to succeed in fewer turns.

相关论文

链接