AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Unleashing Stealthy Backdoor Pandemic by Infecting a Single Diffusion Model

Mohaiminul Al Nahian, Abeer Matar Almalky, Sabbir Ahmed, Abdullah Al Arafat, Mamshad Nayeem Rizve, Adnan Siraj Rakin

CVPR 2026 · Adversarial robustness and security › Backdoor and poisoning · approach: Trigger-based backdoor attacks

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 synthetic images from the attacked SD model to limited real labelsCIFAR-10 classifiers · CIFAR-10 (8% labels)accuracy: 80.01 -> 82.85 (ResNet-20)Improved
add synthetic images from the attacked SD model to limited real labelsCIFAR-100 classifiers · CIFAR-100 (8% labels)accuracy: 40.33 -> 49.23 (ResNet-20)Improved
add synthetic images from the attacked SD model to limited real labelsTinyImageNet classifiers · TinyImageNet (8% labels)accuracy: 34.54 -> 43.55 (ResNet-18)Improved
put the pre-trained VAE in the trigger optimization loop (ablation)Eidolon trigger optimization · Trigger fidelity after UNet trainingtrigger distribution matchImproved
use Eidolon instead of prior diffusion backdoors (SBA, BadT2I, TPA)Stable Diffusion data augmentation · CIFAR-10, ResNet-20ASR (%): 12.89 -> 99.66 (best prior BadT2I Pixel vs Eidolon)Improved
swap the UNet-based SD for MMDiT SD-3-medium (ablation)Eidolon · CIFAR-10, ResNet-20ASR (%): 99.66 -> 91.30Hurt
optimize trigger against a zero-shot classifierEidolon triggered images · BLIP label checktarget label predicted rate: 97.22%Improved
use ViT/Swin instead of CNNs as downstream classifierEidolon on TinyImageNet · TinyImageNet (8% labels)ASR (%): 97.78 (ResNet-18) -> 90.67 (ViT-B), 88.44 (Swin-T)Hurt

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