AI Paper Atlas

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

Two Modalities Are Better Than One: Efficient Adversarial Purification via Multimodal Diffusion Models

Mingyuan Bai, Wei Huang, Tenghui Li, Andong Wang, Chao Li, Cesar F Caiafa, Junbin Gao, Qibin Zhao

ICML 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification

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
learn class-agnostic prompt instead of hand-crafted "a photo of a" template (ablation)MultiDAP · CIFAR-10 AutoAttack l_infrobust accuracy (%): 70.29 -> 72.38Improved
learn class-agnostic prompt instead of hand-crafted template (ablation)MultiDAP · CIFAR-100 AutoAttack l_infrobust accuracy (%): 35.70 -> 38.15Improved
learn class-agnostic prompt instead of hand-crafted template (ablation)MultiDAP · ImageNet-1K AutoAttackrobust accuracy (%): 38.65 -> 41.26Improved
add learned semantic prompt to unimodal likelihood maximizationLM · CIFAR-10 AutoAttack l_2robust accuracy (%): 75.00 -> 76.05Improved
increase purification steps from 5 to 50 (ablation)MultiDAP · CIFAR-10 AutoAttack l_infrobust accuracy (%): 72.38 -> 53.75Hurt
increase purification steps from 1 to 5 (ablation)MultiDAP · CIFAR-10 AutoAttack l_infrobust accuracy (%): 62.31 -> 72.38Improved
increase steps from 5 to 10 (ablation)MultiDAP · CIFAR-10 AutoAttack l_infrobust accuracy (%): 72.38 -> 71.88No clear effect
use mid-range timestep range [400,600] instead of [100,200] (ablation)MultiDAP · CIFAR-10 AutoAttack l_infrobust accuracy (%): 58.44 -> 72.38Improved
use very large timestep range [800,999] instead of [400,600] (ablation)MultiDAP · CIFAR-10 AutoAttack l_infrobust accuracy (%): 72.38 -> 60.27Hurt
increase prompt length from 4 to 16 (ablation)MultiDAP · CIFAR-10 AutoAttack l_infrobust accuracy (%): 71.19 -> 72.38Improved
increase prompt length from 16 to 32 (ablation)MultiDAP · CIFAR-10 AutoAttack l_infrobust accuracy (%): 72.38 -> 72.04No clear effect
add proximity regularization lambda 0.9 vs none (ablation)MultiDAP · CIFAR-10 AutoAttack l_infrobust accuracy (%): 70.17 -> 72.38Improved

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