AI Paper Atlas

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

DualMirage: Hunting Stealthy Multimodal LLM Agents via CAPTCHAs with Contour and Adversarial Illusions

Bei Chen, Gaolei Li, Jun Wu, Jianhua Li

CVPR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness

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 contour illusion (no adversarial) (ablation)DualMirage · Illusion-Selfie2Anime vs GPT-4oABR: 0.0 -> 78.0Improved
add adversarial illusion to contour illusion (ablation)DualMirage · Illusion-Selfie2Anime vs GPT-4oASR: 0.0 -> 44.0Improved
add contour illusion to adversarial illusion (ablation)DualMirage · Illusion-Selfie2Anime vs GPT-4oABR: 36.0 -> 96.0Improved
add contour illusion to adversarial illusion (ablation)DualMirage · Illusion-MNIST l=10 vs GPT-4oASR: 16.0 -> 18.0No clear effect
add adversarial illusion to contour illusion (ablation)DualMirage · Illusion-Selfie2Anime vs LLaVA-v1.5-7bASR: 0.0 -> 100.0Improved
apply JPEG, blur or cropping to the challenge image (ablation)DualMirage · Robustness (avg)ASR: 45.6 -> 15.2 (JPEG)Hurt
apply JPEG compression (ablation)DualMirage · Robustness (avg)ABR: 90.6 -> 100.0Improved
attacker uses few-shot learning or adversarial training (ablation)DualMirage · Robustness (avg)ABR: 90.6 -> 90.0 (FL), 91.0 (AT)No clear effect
use more attempts for humansDualMirage · Human usabilityHSR: 95.78 -> 97.48Improved
use Illusion-Selfie2Anime instead of Illusion-MNISTDualMirage · black-box MLLMsASR: 9.0 -> 44.0 (GPT-4o, l=3 vs Selfie2Anime)Improved

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