Cover Image

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Liangxuan, Wang, Chao, Liu, Tianming, Zhao, Yanjie, Wang, Haoyu
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Human-Computer Interaction
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

"It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents
by: Zhang, Zhiping, et al.
Published: (2023)

Current state of LLM Risks and AI Guardrails
by: Ayyamperumal, Suriya Ganesh, et al.
Published: (2024)

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
by: Chang, Zhiyuan, et al.
Published: (2024)

Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents
by: Sun, Bolun, et al.
Published: (2024)

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

Cyri: A Conversational AI-based Assistant for Supporting the Human User in Detecting and Responding to Phishing Attacks
by: La Torre, Antonio, et al.
Published: (2025)

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

Adversarial VR: An Open-Source Testbed for Evaluating Adversarial Robustness of VR Cybersickness Detection and Mitigation
by: Ahmed, Istiak, et al.
Published: (2025)

Understanding User Privacy Perceptions of GenAI Smartphones
by: Jin, Ran, et al.
Published: (2026)

Learned, Lagged, LLM-splained: LLM Responses to End User Security Questions
by: Prakash, Vijay, et al.
Published: (2024)

Listen to the Voices of Everyday Users: Democratizing Privacy Ratings for Sensitive Data Access in Mobile Apps
by: Wang, Liu, et al.
Published: (2026)

Towards Secure AI-driven Industrial Metaverse with NFT Digital Twins
by: Prakash, Ravi, et al.
Published: (2024)

InjectLab: A Tactical Framework for Adversarial Threat Modeling Against Large Language Models
by: Howard, Austin
Published: (2025)

AI-Assisted Adaptive Rendering for High-Frequency Security Telemetry in Web Interfaces
by: Rajhans, Mona
Published: (2026)

Human-AI Collaboration in Cloud Security: Cognitive Hierarchy-Driven Deep Reinforcement Learning
by: Aref, Zahra, et al.
Published: (2025)

Human-Centered Explainability in AI-Enhanced UI Security Interfaces: Designing Trustworthy Copilots for Cybersecurity Analysts
by: Rajhans, Mona
Published: (2026)

From Preventive to Reactive: How AI Coding Assistants Transform Developers' Security Awareness
by: Bappy, Faisal Haque, et al.
Published: (2026)

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework
by: Dassanayake, Rishane, et al.
Published: (2025)

"Impressively Scary:" Exploring User Perceptions and Reactions to Unraveling Machine Learning Models in Social Media Applications
by: West, Jack, et al.
Published: (2025)

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)

Adversarial Attacks on Machine Learning-Aided Visualizations
by: Fujiwara, Takanori, et al.
Published: (2024)

Securing the AI Supply Chain: What Can We Learn From Developer-Reported Security Issues and Solutions of AI Projects?
by: Nguyen, The Anh, et al.
Published: (2025)

Exploring User Security and Privacy Attitudes and Concerns Toward the Use of General-Purpose LLM Chatbots for Mental Health
by: Kwesi, Jabari, et al.
Published: (2025)

BounTCHA: A CAPTCHA Utilizing Boundary Identification in Guided Generative AI-extended Videos
by: Lin, Lehao, et al.
Published: (2025)

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
by: Lugoloobi, William, et al.
Published: (2026)

LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses
by: Lin, Weiran, et al.
Published: (2024)

Security Risks of AI Agents Hiring Humans: An Empirical Marketplace Study
by: Mehta, Pulak
Published: (2026)

Human-Centered Privacy Research in the Age of Large Language Models
by: Li, Tianshi, et al.
Published: (2024)

Personhood Credentials: Human-Centered Design Recommendation Balancing Security, Usability, and Trust
by: Ide, Ayae, et al.
Published: (2025)

What Security and Privacy Transparency Users Need from Consumer-Facing Generative AI
by: Cao, Jiaxun, et al.
Published: (2026)

On the Suitability of LLM-Driven Agents for Dark Pattern Audits
by: Sun, Chen, et al.
Published: (2026)

On the (In)Security of LLM App Stores
by: Hou, Xinyi, et al.
Published: (2024)

A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models
by: Derner, Erik, et al.
Published: (2023)

Towards Automating Data Access Permissions in AI Agents
by: Wu, Yuhao, et al.
Published: (2025)

"Think First, Verify Always": Training Humans to Face AI Risks
by: Aydin, Yuksel
Published: (2025)

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
by: Wang, Jiongxiao, et al.
Published: (2023)

Beyond Words: On Large Language Models Actionability in Mission-Critical Risk Analysis
by: Esposito, Matteo, et al.
Published: (2024)

When Ads Become Profiles: Uncovering the Invisible Risk of Web Advertising at Scale with LLMs
by: Chen, Baiyu, et al.
Published: (2025)

PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy
by: Kundu, Ripan Kumar, et al.
Published: (2025)

Agentic AI and the Industrialization of Cyber Offense: Forecast, Consequences, and Defensive Priorities for Enterprises and the Mittelstand
by: Koch, Christopher
Published: (2026)