AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters

Liangwei Lyu, Jiaqi Xu, Jianwei Ding, Qiyao Deng

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Inference-time T2I improvement · 2 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 contrastive embedding remapping and time-weighted MSE (vs standard LoRA training on poisoned data)MasqLoRA SD v1.5 · Scenario 1 object backdoor (car -> cat/dog/plane)ASR (%): 5.4 -> 99.8Improved
add contrastive loss weight lambda from 0 to 1.0 (ablation)MasqLoRA SD v1.5 · Scenario 1 object backdoor (car -> cat/dog/plane)ASRImproved
raise lambda beyond 1.0 (ablation)MasqLoRA SD v1.5 · Scenario 1 object backdoor (car -> cat/dog/plane)FIDHurt
train beyond 25 epochs (ablation)MasqLoRA SD v1.5 · Scenario 1 object backdoor (car -> cat/dog/plane)FIDHurt
raise timestep weighting alpha from 0 to 5.0 (ablation)MasqLoRA SD v1.5 · Scenario 1 object backdoor (car -> cat/dog/plane)ASRImproved
raise alpha above 5.0 (ablation)MasqLoRA SD v1.5 · Scenario 1 object backdoor (car -> cat/dog/plane)ASRHurt
stack four MasqLoRA modules instead of one (object) (ablation)MasqLoRA SD v1.5 · Composability, Scenario 1ASR (%): 99.8 -> 91.6Hurt
stack four MasqLoRA modules instead of one (style) (ablation)MasqLoRA SD v1.5 · Composability, Scenario 2 (style)ASR (%): 81.4 -> 65.5Hurt
use MasqLoRA instead of EvilEditSD v1.5 · Scenario 1 object backdoor (car -> cat/dog/plane)ASR (%): 98.3 -> 99.8Improved
use MasqLoRA instead of Benign LoRA on benign promptsSD v1.5 · Scenario 1 object backdoor (car -> cat/dog/plane)CLIP Score: 32.36 -> 31.42No clear effect

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