2 papers
cs.CL2025
Stealth Fine-Tuning: Efficiently Breaking Alignment in RVLMs Using Self-Generated CoT
Le Yu, Zhengyue Zhao, Yawen Zheng +1
Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfac…
cs.SE2025
iPanda: An LLM-based Agent for Automated Conformance Testing of Communication Protocols
Xikai Sun, Fan Dang, Shiqi Jiang +8
Conformance testing is essential for ensuring that protocol implementations comply with their specifications. However, traditional testing approaches involve manually creating nume…