AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Dormant Backdoor: Weaponizing Model Finetuning for Feasible Backdoor Attacks Against Pretrained Models

Ruitao Li, Jiakai Wang, Hairong Chen, Huihu Ding, Jinghan Zhou, Renshuai Tao

AAAI 2026 · Adversarial robustness and security › Backdoor and poisoning · approach: Backdoors in large multimodal models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add bilevel optimization simulating finetuning (ablation)Dormant Backdoor · Caltech101 (unseen classes)ASRb: 84.95 -> 0.28Improved
add bilevel optimization (ablation)Dormant Backdoor · Caltech101 (unseen classes)CA: 89.12 -> 93.83Improved
add stealth (KL distillation) loss (ablation)Dormant Backdoor · Caltech101 (unseen classes)ASRb: 99.21 -> 0.28Improved
add utility loss (ablation)Dormant Backdoor · Caltech101 (unseen classes)CA: 52.43 -> 93.83Improved
add utility loss (ablation)Dormant Backdoor · Caltech101 (unseen classes)ASRa: 100.0 -> 99.52No clear effect
use full finetuning instead of LoRA (ablation)Dormant Backdoor · Caltech101 (ViT-B/16)ASRa: 99.52 -> 96.50Hurt
use prompt tuning instead of LoRA (ablation)Dormant Backdoor · Caltech101 (ViT-B/16)ASRa: 99.52 -> 94.14Hurt
raise victim learning rate from 2e-4 to 2e-3 (ablation)Dormant Backdoor · Caltech101 (ViT-B/16)ASRa: 99.52 -> 95.72Hurt
scale backbone from ViT-B/16 to ViT-L/14 (ablation)Dormant Backdoor · Caltech101ASRa: 99.52 -> 99.93No clear effect
use Dormant Backdoor instead of BadCLIPBadCLIP · Caltech101-Flowers102-Food101-OxfordPets-SUN397 (unseen datasets)ASRa: e.g. SUN397 74.21 -> 99.67Improved
use Dormant Backdoor instead of static-trigger BadNets/BlendedBadNets/Blended · Caltech101 (unseen datasets)ASRa: BadNets 4.49, Blended 28.72 -> 99.16Improved
use Dormant Backdoor instead of BadCLIPBadCLIP · seven backdoor detectorsdetection evasion: BadCLIP evades 4/7; ours evades 7/7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy