arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.26537cs.CL
收藏

概念隐写术

Conceptual Steganography

University of Southern California Information Sciences Institute(南加州大学信息科学研究所)

Zhejian Zhou, Jonathan May

AI总结:

提出概念隐写术,通过思维链中的高级推理行为模式而非词汇选择嵌入信息,实验表明其对释义防御比标准关键词方法更鲁棒,且不影响推理效用。

摘要:

语言模型(LM)发出的思维链(CoT)驱动了其大部分能力。然而,承载有用推理的同一序列也可以隐蔽地传递信息:一个未对齐的模型可能在其CoT中嵌入隐蔽信息,从而逃避人类监督,这种隐写术形式被称为编码推理。先前的LM隐写术方案在词元或词汇空间操作,而内容保留释义器是近期工作中规范且有效的防御手段。我们引入了概念隐写术,其中CoT的每一步通过高级推理行为模式而非词汇选择来携带信息。在四个模型家族和两个推理领域中,这种后门通信渠道被证明比标准关键词方法对强释义防御具有更一致的鲁棒性,并且将信息编码到CoT中不会影响其在推理过程中的效用。在提高对这一新风险的认识后,我们进一步证明,一个策略感知的释义器可以关闭大部分渠道,强调了确保野外忠实LLM推理的新挑战和推荐防御措施。

英文摘要:

Language Models (LMs) emit Chains-of-Thought (CoTs) that drive much of their capability. However, the same sequence that carries useful reasoning can also covertly convey messages: a misaligned model may embed covert information in its CoT that slips through human supervision, a form of steganography known as encoded reasoning. Prior LM steganography schemes operate in the token or lexical space, and a content-preserving paraphraser is the canonical and effective defense in recent work. We introduce conceptual steganography, in which each step of a CoT carries information through patterns of high-level reasoning behavior, rather than through lexical choice. Across four model families and two reasoning domains, this backdoor communication channel is shown to be consistently more robust to a strong paraphrase defense than standard keyword approaches, and the encoding of information into CoTs does not affect their utility in the reasoning process. Having raised awareness of this new risk, we then demonstrate that a strategy-aware paraphraser can close much of the channel, highlighting new challenges and recommended defenses for ensuring faithful LLM reasoning in the wild.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑