Cover Image

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Du, Chenghao, Huang, Quanfeng, Tang, Tingxuan, Wang, Zihao, Nadkarni, Adwait, Xiao, Yue
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From base cases to backdoors: An Empirical Study of Unnatural Crypto-API Misuse
by: Olaiya, Victor, et al.
Published: (2025)

Understanding Human-AI Collaboration in Cybersecurity Competitions
by: Tang, Tingxuan, et al.
Published: (2026)

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
by: Zhuang, Haomin, et al.
Published: (2026)

"False negative -- that one is going to kill you": Understanding Industry Perspectives of Static Analysis based Security Testing
by: Ami, Amit Seal, et al.
Published: (2023)

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
by: Lv, Lijia, et al.
Published: (2026)

Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback
by: Yan, Lecheng, et al.
Published: (2026)

Blockchain-Enhanced Framework for Secure Third-Party Vendor Risk Management and Vigilant Security Controls
by: Gupta, Deepti, et al.
Published: (2024)

Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents
by: Xu, Zhen, et al.
Published: (2026)

Enabling Low-Cost Secure Computing on Untrusted In-Memory Architectures
by: Ghinani, Sahar Ghoflsaz, et al.
Published: (2025)

A Survey On Secure Machine Learning
by: Liao, Taobo, et al.
Published: (2025)

Mutation-based Evaluation of Cryptographic API Misuse Detectors
by: Ami, Amit Seal, et al.
Published: (2021)

Secure Combination of Untrusted Time information Based on Optimized Dempster-Shafer Theory
by: Li, Yang, et al.
Published: (2024)

PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
by: Li, Qinfeng, et al.
Published: (2026)

IDPFilter: Mitigating Interdependent Privacy Issues in Third-Party Apps
by: Liu, Shuaishuai, et al.
Published: (2024)

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
by: Wu, Liangxuan, et al.
Published: (2025)

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
by: Tessa, Melissa, et al.
Published: (2026)

SandboxEval: Towards Securing Test Environment for Untrusted Code
by: Rabin, Rafiqul, et al.
Published: (2025)

Starfish: Rebalancing Multi-Party Off-Chain Payment Channels
by: Xu, Minghui, et al.
Published: (2025)

When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins
by: Kaya, Yigitcan, et al.
Published: (2025)

LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training
by: Gong, Yuyang, et al.
Published: (2026)

Browsing without Third-Party Cookies: What Do You See?
by: Lin, Maxwell, et al.
Published: (2024)

An Interview Study on Third-Party Cyber Threat Hunting Processes in the U.S. Department of Homeland Security
by: Maxam III, William P., et al.
Published: (2024)

Private Aggregate Queries to Untrusted Databases
by: Hafiz, Syed Mahbub, et al.
Published: (2024)

Who's Watching You Zoom? Investigating Privacy of Third-Party Zoom Apps
by: Goenka, Saharsh, et al.
Published: (2025)

MAGE: Mutual Attestation for a Group of Enclaves without Trusted Third Parties
by: Chen, Guoxing, et al.
Published: (2020)

BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors
by: Hsu, Chia-Yi, et al.
Published: (2025)

Design Patterns for Securing LLM Agents against Prompt Injections
by: Beurer-Kellner, Luca, et al.
Published: (2025)

Byzantine-Secure Relying Party for Resilient RPKI
by: Friess, Jens, et al.
Published: (2024)

Assessing Privacy Compliance of Android Third-Party SDKs
by: Meng, Mark Huasong, et al.
Published: (2024)

DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents
by: Zhang, Fuyao, et al.
Published: (2025)

Cabin: Confining Untrusted Programs within Confidential VMs
by: Mei, Benshan, et al.
Published: (2024)

Covert Communication for Untrusted UAV-Assisted Wireless Systems
by: Gao, Chan, et al.
Published: (2024)

On the Communication Complexity of Secure Multi-Party Computation With Aborts
by: Bartusek, James, et al.
Published: (2024)

Applications of Secure Multi-Party Computation in Financial Services
by: Sedraoui, Brahim Khalil, et al.
Published: (2026)

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework
by: Wang, Zhuoshang, et al.
Published: (2026)

Agent Audit: A Security Analysis System for LLM Agent Applications
by: Zhang, Haiyue, et al.
Published: (2026)

\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party
by: Rahimi, Ali, et al.
Published: (2025)

Incentivized Third Party Collateralization for Stablecoins
by: Das, Souradeep, et al.
Published: (2023)

SMTFL: Secure Model Training to Untrusted Participants in Federated Learning
by: Zhao, Zhihui, et al.
Published: (2025)

Tracking GPTs Third Party Service: Automation, Analysis, and Insights
by: Yan, Chuan, et al.
Published: (2025)