AI Paper Atlas

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

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection

Wenkui Yang, chao jin, Haisu Zhu, Weilin Luo, Derek Yuen, Kun Shao, Junxian Duan, Huaibo Huang, Jie Cao, Ran He

ECCV 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: LLM jailbreak and injection defense · 1 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
use LLM-guided strategic icon injection instead of random injectionClaude-Sonnet-4.6 victim · GUI grounding 885 splitL1-ASR: 3.23 -> 22.24Improved
use LLM-guided strategic injection instead of random injectionGUI-Owl-7B victim · GUI grounding 885 splitL1-ASR: 23.36 -> 51.65Improved
transfer icons optimized on GUI-Owl-7B to UI-TARS-1.5-7B instead of on-target (ablation)UT/GO-opt. · UI-TARS-1.5-7BL1-ASR: 32.99 -> 34.43No clear effect
replace LLM-proposed bounding boxes with random placement (ablation)Strategic editor · UI-TARS-1.5-7BL1-ASR: 27.4 -> 33.0Improved
use iterative carry-forward Depth x Pass@N instead of GPTFuzz-UI / LLM-Bank-Square-UIStrategic editor · UI-TARS-1.5-7BL1-ASR: 18.3 -> 33.0Improved
increase parallel width from pass@1 to pass@3 (ablation)Strategic editor · GUI-Owl-7B D=1L1-ASR: 11.07 -> 24.18Improved
increase parallel width from pass@1 to pass@3 at depth 5 (ablation)Strategic editor · GUI-Owl-7B D=5L1-ASR: 49.15 -> 50.96No clear effect
use Claude-Sonnet-4.6 as editor instead of Qwen3-VL-Plus (ablation)Strategic editor · UI-TARS-1.5-7BL1-ASR: 33.0 -> 42.4Improved
use same-family editor as victim (Claude editor vs Claude victim) (ablation)Strategic editor · Claude-Sonnet-4.6 victimL1-ASR: 22.2 -> 26.9Improved
increase model size within Qwen3-VLVictim · Qwen3-VLL1-ASR: 38.54 -> 25.47 (2B vs 32B, lower ASR is more robust)Improved
increase model size within specialist OpenCUAVictim · OpenCUAL1-ASR: 51.71 -> 57.72 (avg ASR, 7B vs 32B)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