AI Paper Atlas

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

LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents

Zihe Yan, Zhuosheng Zhang, Jiaping Gui, Gongshen Liu

CVPR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: LLM jailbreak and injection defense · 4 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 attention scaling to the MLP scaling (scale both modules) (ablation)LaSM on Qwen2-VL-7B · Pop-up screenshotsDSR: 0.47 -> 84.80Improved
add MLP scaling to the attention scaling (scale both modules) (ablation)LaSM on Qwen2-VL-7B · Pop-up screenshotsDSR: 0.95 -> 84.80Improved
apply LaSM scaling to layers 7-18 vs naive scaling of layers 21-26 (ablation)Qwen2-VL-7B · Pop-up screenshotsDSR: 8.05 -> 84.80Improved
add LaSM to no-defense modelQwen2-VL-7B · Overlay injection (avg)DSR: 18.9 -> 66.4Improved
add LaSM to no-defense modelQwen2-VL-7B · Inductive injection (avg)DSR: 14.8 -> 68.3Improved
add LaSM to DPO-finetuned modelQwen2-VL-7B · Inductive injection (avg)DSR: 10.5 -> 65.2Improved
add LaSM to CoT alertQwen2-VL-7B · Inductive injection (avg)DSR: 92.7 -> 99.8Improved
add LaSM to CoT alertLLaVA-v1.6-Vicuna-13B · Overlay injection (avg)DSR: 84.7 -> 86.9Mixed
tune scaling coefficient alpha from 1.00 to 1.10 (ablation)LaSM on Qwen2-VL-7B · Pop-up screenshotsDSR: 1.42 -> 94.79Improved
tune scaling coefficient alpha from 1.00 to 1.20 (ablation)LaSM on LLaVA-v1.6-Vicuna-13B · Pop-up screenshotsDSR: 50.24 -> 89.57Improved
add LaSM to modelQwen2-VL-2B · Pop-up screenshotsDSR: 0.94 -> 23.20Improved
add LaSM to modelMAI-UI-8B · Pop-up screenshotsDSR: 15.17 -> 29.86Improved

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