Dormant Backdoor: Weaponizing Model Finetuning for Feasible Backdoor Attacks Against Pretrained Models
Ruitao Li, Jiakai Wang, Hairong Chen, Huihu Ding, Jinghan Zhou, Renshuai Tao
Abstract
As the pretraining-finetuning paradigm becomes dominant in modern AI, the security of model supply chains faces new risks from backdoor attacks. Existing work primarily studies backdoors injected during pretraining and treats subsequent finetuning with clean data as a defense, while recent finetuning-activated attacks assume white-box access to the downstream data distribution, which is rarely realistic in practice. We introduce Dormant Backdoor, a finetuning-activated attack that requires no prior knowledge of downstream tasks. Instead of binding the backdoor to static input patterns, Dormant Backdoor exploits the universal dynamics of gradient-based optimization as a process-as-trigger mechanism. We formulate the attack as a bilevel optimization problem that simulates the victim
BibTeX
@inproceedings{aaai2026_dormantbackdoorw,
title = {Dormant Backdoor: Weaponizing Model Finetuning for Feasible Backdoor Attacks Against Pretrained Models},
author = {Ruitao Li and Jiakai Wang and Hairong Chen and Huihu Ding and Jinghan Zhou and Renshuai Tao},
booktitle = {AAAI 2026},
year = {2026}
}