跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 09:10 — 2026-11-19 09:10(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

26,871 已收录论文22,375 AI 相关8,156 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2604.15559

Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation

Jacob Dang, Brian Y. Xie, Omar G. Younis

原文摘要

Recent work on subliminal learning has shown that language models can transmit semantic traits through data with no apparent connection to those traits. Whether this phenomenon extends to agentic systems, where policies are learned from trajectories rather than static text, remains an open question with critical safety implications. We present the first empirical evidence that unsafe agent behaviors transfer subliminally through model distillation, demonstrated across several settings. In the primary setting, we construct a teacher agent with a deletion bias, a tendency to perform destructive file-system actions through an API-style tool interface, and distill it into a student using only trajectories from ostensibly safe tasks, with all explicit deletion keywords filtered. In the secondary setting, we replicate the threat model with shell commands, replacing API calls with shell commands and operationalizing the bias as a preference for chmod over semantically equivalent alternatives (e.g., chown, setfacl) when issuing the first permission-related command. Despite sanitation, students inherit measurable biases. Over 1,500 trials per configuration, the API student chooses a destructive action first on 35.5% of ambiguous tasks (vs. 1.2% baseline), and the Bash student's chmod-first rate reaches 30-55% (vs. 0-10% baseline). In a multi-turn environment where tool calls execute, 33.9% of student episodes end with a resource irreversibly destroyed (vs. 6.4% baseline). On TerminalBench we observe a smaller effect (7.7% vs. 0% baseline). Explicit data sanitation is therefore insufficient as a defense; mitigating behavioral bias transfer in agentic systems will require fundamentally new strategies.

cs.AI