Showing 1–15 of 15 results
/ Date/ Name
Jun 10, 2025ZTaint-Havoc: From Havoc Mode to Zero-Execution Fuzzing-Driven Taint InferenceSep 6, 2025Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security AssessmentApr 6, 2026Scaling Coding Agents via Atomic SkillsSep 29, 2025JSProtect: A Scalable Obfuscation Framework for Mini-Games in WeChatMar 22, 2026WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-MakingFeb 9, 2026On Protecting Agentic Systems' Intellectual Property via WatermarkingOct 27, 2025QueryIPI: Query-agnostic Indirect Prompt Injection on Coding AgentsFeb 2, 2026Kimi K2.5: Visual Agentic IntelligenceSep 8, 2025Parasites in the Toolchain: A Large-Scale Analysis of Attacks on the MCP EcosystemJun 6, 2024FOX: Coverage-guided Fuzzing as Online Stochastic ControlFeb 19, 2026KLong: Training LLM Agent for Extremely Long-horizon TasksSep 13, 2024A Low-Field Magnetic Resonance Signal Transmission and Reception Processing PlatformJan 30, 2026From Similarity to Vulnerability: Key Collision Attack on LLM Semantic CachingOct 27, 2025CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered AgentsFeb 26, 2026RandSet: Randomized Corpus Reduction for Fuzzing Seed Scheduling