安全、治理与可靠性 颠覆级 有讲解视频
发表时间
2026-08-10
arXiv
2608.09867

收录解读

本文针对大型语言模型(LLM)提供商隐藏思维链(CoT)以保护知识产权和限制信息泄露的现状,发现了一个架构性漏洞:加密的推理轨迹块在不同会话、用户甚至模型之间完全兼容且可互换。这一特性使得攻击者能够利用同一提供商的较弱、防护较弱的模型来解密并输出加密的推理轨迹,从而绕过对高性能模型的直接越狱限制。

核心方法是一种可扩展的解密越狱攻击:将目标模型生成的加密推理轨迹注入到同一提供商的较弱模型中,迫使弱模型逐字解码并输出明文轨迹。该攻击无需直接攻击强模型,即可实现多种恶意目的,包括窃取专有推理过程、大规模提取私有数据、揭示危险隐藏信息以及嵌入不可见提示注入。

实验在Anthropic、OpenAI和Google等主流提供商上验证了攻击有效性。从公开仓库中抓取的315,320个推理块中成功解密出367个PII工件和182个凭证,并展示了四个攻击向量的实际威胁。此外,作者还提出了针对性的密码学和系统级缓解措施,并进行了负责任披露。

该工作首次揭示了加密推理轨迹的可互换性这一系统性安全缺陷,对LLM服务的安全设计具有重要警示意义。它改变了人们对客户端加密数据安全的认知,但尚局限于特定实现机制,未形成普适的防御框架,因此属于颠覆性成果而非范式转变。

原始摘要

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are fully compatible and interchangeable across different sessions, users, and models within a provider's ecosystem. We exploit this compatibility to develop a scalable decryption jailbreak. By injecting an encrypted reasoning trace from a given model into a weaker, and less safeguarded model from the same provider, we force it to decode and output the trace verbatim in plaintext, without ever jailbreaking the more capable model directly. This vulnerability enables four distinct attack vectors. First, it circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning, as we demonstrate across Anthropic, OpenAI, and Google. Second, it allows for large-scale private data extraction. Developers frequently share session logs publicly, unaware of contents of the encrypted blocks. By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials. Third, it inadvertently reveals hazardous information hidden within the reasoning process, even in cases where the model's final, visible output safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible disclosure, we propose concrete cryptographic and system-level mitigations to secure client-side reasoning.

解读视频

相关论文

链接