Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Zihe, Gui, Jiaping, Zhang, Zhuosheng, Liu, Gongshen
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents
by: Xu, Wenpeng
Published: (2026)

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
by: Wu, Zongru, et al.
Published: (2024)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
by: Cheng, Pengzhou, et al.
Published: (2024)

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
by: Wu, Zongru, et al.
Published: (2024)

Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks
by: Tsai, Yu-Che, et al.
Published: (2026)

DRIP: Defending Prompt Injection via Token-wise Representation Editing and Residual Instruction Fusion
by: Liu, Ruofan, et al.
Published: (2025)

No Free Lunch for Defending Against Prefilling Attack by In-Context Learning
by: Xue, Zhiyu, et al.
Published: (2024)

DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs
by: Zhou, Ranyang, et al.
Published: (2023)

Local Layer-wise Differential Privacy in Federated Learning
by: Li, Yunbo, et al.
Published: (2026)

Your Agent Can Defend Itself against Backdoor Attacks
by: Changjiang, Li, et al.
Published: (2025)

MKF-ADS: Multi-Knowledge Fusion Based Self-supervised Anomaly Detection System for Control Area Network
by: Cheng, Pengzhou, et al.
Published: (2024)

Defending Against Beta Poisoning Attacks in Machine Learning Models
by: Gulciftci, Nilufer, et al.
Published: (2025)

Mobile GUI Agents under Real-world Threats: Are We There Yet?
by: Liu, Guohong, et al.
Published: (2025)

RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process
by: Wang, Peiran, et al.
Published: (2024)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
by: Liu, Fan, et al.
Published: (2024)

UOR: Universal Backdoor Attacks on Pre-trained Language Models
by: Du, Wei, et al.
Published: (2023)

To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack
by: Zhuo, Terry Yue, et al.
Published: (2026)

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks
by: Jin, Haotian, et al.
Published: (2025)

BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks
by: Lee, Hanyong, et al.
Published: (2025)

Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
by: Lin, Zhixin, et al.
Published: (2026)

Are We There Yet? Unraveling the State-of-the-Art Graph Network Intrusion Detection Systems
by: Wang, Chenglong, et al.
Published: (2025)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
by: Zhao, Haodong, et al.
Published: (2024)

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
by: Wang, Xunguang, et al.
Published: (2024)

GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?
by: Chen, Chiyu, et al.
Published: (2025)

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
by: Zhong, Peter Yong, et al.
Published: (2025)

Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
by: Peng, Wanli, et al.
Published: (2025)

BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
by: Yu, Haiyang, et al.
Published: (2024)

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
by: Lin, Junda, et al.
Published: (2026)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
by: Zhu, Pengyu, et al.
Published: (2025)

CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered Agents
by: Liu, Zesen, et al.
Published: (2025)

A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning
by: Yu, Yinbo, et al.
Published: (2024)

Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
by: Lyu, Xingyu, et al.
Published: (2025)

Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack
by: Yue, Murong, et al.
Published: (2025)

Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
by: Pang, Yan, et al.
Published: (2025)

AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents
by: Luo, Yutao, et al.
Published: (2026)

Learning to Defend by Attacking (and Vice-Versa): Transfer of Learning in Cybersecurity Games
by: Malloy, Tailia, et al.
Published: (2023)

On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
by: Li, Zhengyi, et al.
Published: (2026)

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
by: Cao, Tri, et al.
Published: (2025)

Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions
by: Xiang, Qiuchi, et al.
Published: (2026)

AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
by: Wu, Yixin, et al.
Published: (2025)