MobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware Injection
cs.CR, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- MAI-UI Technical Report: Real-World Centric Foundation GUI Agents
- Mobile-Agent-v3: Fundamental Agents for GUI Automation
- GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?
- MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments
- On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
- From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
- Systematic Categorization, Construction and Evaluation of New Attacks against Multi-modal Mobile GUI Agents
- Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels
- MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments
- CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation
- D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies
- Mind the Gap: Action Rebinding Attacks against Android GUI Agents
- AdvAgent: Controllable Blackbox Red-teaming on Web Agents
- Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
- EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks
- T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data