Cover Image

The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Chaoran, Zhang, Zhiping, Guo, Bingcan, Ma, Shang, Khalilov, Ibrahim, Gebreegziabher, Simret A, Ye, Yanfang, Xiao, Ziang, Yao, Yaxing, Li, Tianshi, Li, Toby Jia-Jun
Format:	Preprint
Published:	2025
Subjects:	Human-Computer Interaction Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents
by: Chen, Chaoran, et al.
Published: (2025)

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
by: Tang, Jingyu, et al.
Published: (2025)

Comparing Human Oversight Strategies for Computer-Use Agents
by: Chen, Chaoran, et al.
Published: (2026)

Beyond Permissions: Investigating Mobile Personalization with Simulated Personas
by: Khalilov, Ibrahim, et al.
Published: (2025)

PriviSense: A Frida-Based Framework for Multi-Sensor Spoofing on Android
by: Khalilov, Ibrahim, et al.
Published: (2026)

The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes
by: Gebreegziabher, Simret Araya, et al.
Published: (2026)

Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent
by: Zhang, Zhiping, et al.
Published: (2024)

Stayin' Aligned Over Time: Towards Longitudinal Human-LLM Alignment via Contextual Reflection and Privacy-Preserving Behavioral Data
by: Gebreegziabher, Simret Araya, et al.
Published: (2026)

Why am I seeing this: Democratizing End User Auditing for Online Content Recommendations
by: Chen, Chaoran, et al.
Published: (2024)

CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applications
by: Chen, Chaoran, et al.
Published: (2024)

Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theories
by: Gebreegziabher, Simret Araya, et al.
Published: (2024)

Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning
by: Gebreegziabher, Simret Araya, et al.
Published: (2024)

An Empathy-Based Sandbox Approach to Bridge the Privacy Gap among Attitudes, Goals, Knowledge, and Behaviors
by: Chen, Chaoran, et al.
Published: (2023)

Designing Staged Evaluation Workflows for LLMs: Integrating Domain Experts, Lay Users, and Model-Generated Evaluation Criteria
by: Szymanski, Annalisa, et al.
Published: (2024)

A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration
by: Gao, Jie, et al.
Published: (2024)

MultEval: Supporting Collaborative Alignment for LLM-as-a-Judge Evaluation Criteria
by: Chiang, Charles, et al.
Published: (2026)

My Favorite Streamer is an LLM: Discovering, Bonding, and Co-Creating in AI VTuber Fandom
by: Ye, Jiayi, et al.
Published: (2025)

Privy: From Fine Print to Fair Practice in Privacy Rights Exercise
by: Sun, Qi, et al.
Published: (2026)

Disclose with Care: Designing Privacy Controls in Interview Chatbots
by: Li, Ziwen, et al.
Published: (2026)

Not My Agent, Not My Boundary? Elicitation of Personal Privacy Boundaries in AI-Delegated Information Sharing
by: Guo, Bingcan, et al.
Published: (2025)

CoCo Matrix: Taxonomy of Cognitive Contributions in Co-writing with Intelligent Agents
by: Wan, Ruyuan, et al.
Published: (2024)

Secret Use of Large Language Model (LLM)
by: Zhang, Zhiping, et al.
Published: (2024)

The Invisible Threat: Evaluating the Vulnerability of Cross-Spectral Face Recognition to Presentation Attacks
by: George, Anjith, et al.
Published: (2025)

"I'm categorizing LLM as a productivity tool": Examining ethics of LLM use in HCI research practices
by: Kapania, Shivani, et al.
Published: (2024)

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents
by: Zhang, Zhiping, et al.
Published: (2025)

Unveiling the Invisible: Powering Security Threat Detection in WSN With AI
by: K. P. Uvarajan, et al.
Published: (2025)

Careful About What App Promotion Ads Recommend! Detecting and Explaining Malware Promotion via App Promotion Graph
by: Ma, Shang, et al.
Published: (2024)

Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Dataset
by: Li, Tianshi
Published: (2026)

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
by: Wang, Peiran, et al.
Published: (2026)

Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents
by: Chen, Chaoran, et al.
Published: (2025)

Invisible Languages of the LLM Universe
by: Khanna, Saurabh, et al.
Published: (2025)

Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots
by: Zhou, Jijie, et al.
Published: (2024)

Obvious Independence of Clones
by: Berker, Ratip Emin, et al.
Published: (2022)

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
by: Cheng, Pengzhou, et al.
Published: (2025)

LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects
by: Liu, Guangyi, et al.
Published: (2025)

Families' Vision of Generative AI Agents for Household Safety Against Digital and Physical Threats
by: Wen, Zikai, et al.
Published: (2025)

LLM Anonymization Against Agentic Re-Identification
by: Li, Ziwen, et al.
Published: (2026)

Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments
by: Zhang, Yitong, et al.
Published: (2025)

Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks
by: Maloyan, Narek, et al.
Published: (2025)

GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning
by: Li, Junlong, et al.
Published: (2026)