AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

DADet: Safeguarding Image Conditional Diffusion Models against Adversarial and Backdoor Attacks via Diffusion Anomaly Detection

Hongwei Yu, Xinlong Ding, Jiawei Li, Jinlong Wang, Yudong Zhang, Rongquan Wang, Huimin Ma, Jiansheng Chen

ICCV 2025 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 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
raise reverse step te above 800 (ablation)DADet · image variation (MS COCO)precision: recall remains constant while precision decreasesHurt
lower reverse step te below 800 (ablation)DADet · image variation (MS COCO)recall: precision unchanged while recall dropsHurt
vary threshold F-hat between 2.5 and 6.5 (ablation)DADet · image variation (MS COCO)F1 score: F1 greater than 0.9 across 2.5 to 6.5No clear effect
adversarial perturbation instead of random noise of equal norm in noise predictiondiscrepancy accumulation analysis · reverse process cosine similarity S400cosine similarity: 0.91 vs 0.28Improved
use only homogeneity metric for unconditional models (ablation)DADet · CIFAR-10 backdoorprecision/recall: performance comparable to ElijahNo clear effect
optimize adversarial samples to resemble the condition image (adaptive attack)DADet · adaptive attack evasiondetection evasionNo clear effect
use Stable Diffusion instead of Latent Diffusion for inpainting detectionDADet · Places365 inpainting, Photo guard 8/255F1 score: 0.90 -> 0.84Hurt
use Stable Diffusion instead of Latent Diffusion for inpainting detectionDADet · Places365 inpainting, LDM-R 16/255F1 score: 0.97 -> 0.86Hurt
use DADet with Invisible Backdoor 16/255 instead of 8/255DADet · MS COCO backdoor detection, Target HatF1 score: 0.98 -> 0.99Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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