Hacker News· sbulaev·· 4 小时前精选AI 评分54
研究称 AI 模型可证明地隐藏任意能力
AI Models Can Provably Hide Arbitrary Capabilities
AI 导读
arXiv:2610.13928 提出基于密码学假设的后门构造，证明 AI 模型可在权重中嵌入加密子网来隐藏任意能力，仅在收到秘密触发器时才激活执行。该论文已被 NeurIPS 2026 接收，作者以化学反应预测为 CBRN 代理任务测试微调、权重加噪、基于梯度的触发器搜索和潜在对抗训练等 elicitation 方法，结果显示这些方法难以恢复隐藏能力，并公开权重以支持防御研究。
推荐理由
论文用基于密码学的后门构造证明 AI 模型可隐藏任意能力，揭示 elicitation 类能力审计存在固有局限。
正文 · 原文
Abstract:Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions by constructing backdoor attacks that embed encrypted neural networks within host model weights, decrypting and executing them only upon receiving a secret trigger. Using digital lockers, these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights, extending prior work from hiding fixed strings to arbitrary computations. We implement our proof of concept constructions in PyTorch and evaluate elicitation through fine-tuning, weight noising, gradient-based trigger search, and latent adversarial training on a small chemical reaction prediction task - a proxy for CBRN-relevant capabilities. Our results demonstrate resistance to these methods and, together with our cryptographic guarantees, reveal a limit of elicitation-based capability audits. We release our models to support the improvement of defenses.
| Comments: | 22 pages, 6 figures, 3 tables. Accepted at NeurIPS 2026 |
| Subjects: | Machine Learning (cs.LG); Cryptography and Security (cs.CR) |
| Cite as: | arXiv:2610.13928 [cs.LG] |
| (or arXiv:2610.13928v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13928 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andis Draguns [view email]
[v1]
Fri, 9 Oct 2026 17:55:06 UTC (878 KB)
来源：Hacker News · arxiv.org