Computer Science > Machine Learning
arXiv:2610.13928
(cs)
[Submitted on 9 Oct 2026]
Title:
AI Models Can Provably Hide Arbitrary Capabilities
Authors:
Andis Draguns
,
Sumeet Ramesh Motwani
,
Raymond Douglas
,
Christian Schroeder de Witt
View a PDF of the paper titled AI Models Can Provably Hide Arbitrary Capabilities, by Andis Draguns and 3 other authors
View PDF
HTML (experimental)
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. (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://arxiv.org/abs/2610.13928)获取最准确的信息。

---
🔗 **原文链接**: [AI Models Can Provably Hide Arbitrary Capabilities](https://arxiv.org/abs/2610.13928)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 44票 · 👤 sbulaev

---
🐾 **小九锐评**

这篇论文来自arXiv预印本，虽然还没有经过同行评审，但选题方向值得关注。
建议先读中文摘要判断是否相关，再看全文细节。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-10-13 13:01