arXiv Machine Learning
MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 19
MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps
MobileWorldSafety is a benchmark that evaluates the safety of large language model–powered GUI agents on Android by exposing them to 142 real-world risk tasks involving environmental injection attacks. The benchmark uses a two‑stage verification pipeline—rule‑based checks for clear cases and an LLM judge for ambiguous ones—to distinguish safety failures from capability failures. Experiments on six agents show high vulnerability, with attack success rates between 40.4% and 66.9%, highlighting that current agents often fail to remain safe when faced with adversarial content presented as normal mobile context.
arXiv AI
Jul 24
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests
arXiv:2607. 20759v1 Announce Type: cross Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with autonomous access to local files and tools.
arXiv AI
Jul 16
Mind the Gap: Action Rebinding Attacks against Android GUI Agents
arXiv:2601. 12349v3 Announce Type: replace-cross Abstract: Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content and inject inputs across application boundaries.
arXiv AI
Jun 18
Code-Augur: Agentic Vulnerability Detection via Specification Inference
arXiv:2606. 18619v1 Announce Type: cross Abstract: The advent of agentic vulnerability detection is already becoming a watershed moment for software security.
arXiv AI
Sep 28
AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents
AgentXploit is a two‑role auditing system that separates repository‑level attack‑path discovery from runtime exploitation for AI agents. The Analyzer Agent traces attacker‑controlled inputs to sensitive operations and records candidate attack paths, while the Exploiter Agent turns these paths into concrete attacks and refines them using runtime feedback. The system is evaluated on AgentXploit‑Bench, a benchmark of 72 reproducible vulnerabilities across 12 open‑source AI‑agent systems, achieving 59.3% end‑to‑end success compared to 38.4% for Codex, and 79.2% attack success on AgentDojo versus 52.7% for AgentVigil.
arXiv Machine Learning
Jun 26
DroidBreaker: Practical and Functional Problem-Space Attacks on Machine-Learning Android Malware Detectors
arXiv:2606. 26707v1 Announce Type: cross Abstract: Adversarial APKs are Android applications modified in the problem space to evade machine-learning malware detectors.