arXiv cs.AI· Zane Fu, Yanzhao Zheng, Jinze Liu, Ziting Qin, Qianshan Wei, Jihuai Zhu, Yipeng Yu, Baohua Dong, Hangcheng Zhu, Ruohui Huang·· 2 小时前AI 评分47
学生模型持续部署中,视觉后门威胁不断增长:On-Policy 蒸馏的安全风险研究
As Student Rollouts Continue, Visual Backdoors Keep Growing
AI 导读
一篇 arXiv 论文揭示 On-Policy Distillation(OPD)在视觉-语言模型训练中存在被忽视的视觉后门传播风险。研究发现低投毒比例下后门很少出现,但一旦超过临界阈值,攻击成功率迅速接近 100%,且传播不依赖显式恶意响应,而由教师模型分配的异常概率质量持续累积驱动。基于此作者提出新型触发器设计,实现零显式触发注入的视觉后门传播。
正文 · 原文
Abstract:Conventional knowledge distillation can facilitate the propagation of backdoors from teacher models to student models. However, how this risk manifests in On-Policy Distillation (OPD) remains insufficiently studied. OPD has recently emerged as an important post-training paradigm for Vision-Language Models (VLMs). Unlike traditional offline distillation, OPD does not require teacher-generated responses. Instead, it uses the teacher's probability distributions to supervise response trajectories generated online by the student. Since the initial student model typically generates benign responses and receives no explicit supervision from malicious target responses, OPD appears to offer some inherent resistance to backdoor propagation.
In this paper, we challenge this intuition and reveal a more subtle risk of visual backdoor propagation in OPD. Through experiments across multiple model families and datasets, together with theoretical analysis, we identify three main findings. First, unlike the relatively gradual propagation observed in traditional offline distillation, backdoors rarely emerge in OPD at low poisoning ratios. However, the attack success rate rapidly approaches 100% once a critical threshold is exceeded. Second, backdoor propagation does not depend on explicit malicious responses. Instead, it is driven by the continuous accumulation of anomalous probability mass assigned by the teacher. Finally, based on these findings, we propose a novel trigger design that enables visual backdoor propagation with zero explicit trigger injection. These findings further reveal an overlooked mechanism of backdoor propagation in OPD and highlight its potential security risks.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22446 [cs.CV] |
| (or arXiv:2611.22446v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22446 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zane Fu [view email]
[v1]
Tue, 17 Nov 2026 09:15:01 UTC (343 KB)
来源:arXiv cs.AI · arxiv.org