Searcharxiv⌕ Search

arXiv subjects

Ziting Qin

Publications and source records attributed to Ziting Qin.

2 recordsLinked to original sources

As Student Rollouts Continue, Visual Backdoors Keep Growing

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.

cs.CV↗

On-policy distillation as a Backdoor Propagation Channel

On-policy distillation (OPD) is emerging as an important paradigm for the post training of large language models, improving student models by leveraging supervision generated online by teacher models. However, whether this process also transfers latent security risks from teacher models to student models remains insufficiently studied. In this work, we reveal a new security risk in which an attacker first implants a conditional backdoor into the teacher model through supervised fine tuning (SFT), after which OPD can transfer the backdoor to the student model with only an extremely small proportion of trigger prompt exposure. More concerningly, we find that such backdoor transfer is substantially stronger under OPD than under conventional distillation methods, suggesting that OPD may provide an efficient channel for propagating backdoors across models. Our mechanistic analysis shows that the backdoor signal is primarily transmitted through anomalous differences in the conditional probabilities produced by the teacher model for triggered and clean inputs, and is gradually internalized into the internal representations of the student model during training. Furthermore, we investigate how to suppress such anomalous conditional probability signals at the source of distillation supervision and, based on this analysis, propose an OPD training method tailored to this conditional backdoor propagation setting to mitigate the risk of backdoor transfer induced by untrusted teacher supervision.

cs.LG↗