AI Paper Atlas

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

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation

Changyue Li, Jiaying Li, Youliang Yuan, Jiaming He, Zhicong Huang, Pinjia He

ICML 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial prompts for language models · 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
add Normalized Space Optimization (optimize in normalized space instead of pixel space) (ablation)SORT · ImageNet 5 targets frameattack success rate (test): near zero -> 66% (Qwen)Improved
add Semantic Separation Optimization (margin loss) (ablation)SORT · ImageNet 5 targetsattack success rate (test): average ASR gain of 6%Improved
add margin loss with only two targets (ablation)SORT · ImageNet 2 targetsattack success rate (test): Qwen frame 0.93 -> 0.93No clear effect
add SORT instead of single-target image hijacking baseline (ablation)Qwen · ImageNet 2 targets frameattack success rate (test): 0.00 -> 0.93Improved
increase number of targets (ablation)SAUP on Qwen, frame · ImageNetattack success rate (test): 93% (2 targets) -> 31% (9 targets)Hurt
use corner patch (1,600 pixels) instead of frame (7,056 pixels) (ablation)SAUP · ImageNet many targetsattack success rate: Corner ASR drops to 0% on Llava and Qwen at 8 targetsHurt
increase target length in words (ablation)SAUP · ImageNet 2 targetsattack success rate (test): 83% at 10 words; 78% Qwen, 83% Intern at 15 wordsNo clear effect
train on small 50-image RIST training setSAUP on InternVL3 · RIST AutoDrivingattack success rate: 100% train -> 61% testHurt
increase number of targets (2 to 5) with fine-grained RIST semanticsSAUP · RISTaverage attack success rate (test): 72% -> 62%Hurt
slightly increase perturbed area (ablation)SAUP · ImageNetattack success rateImproved

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