3 papers
cs.CR2026
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
Yizhe Zeng, Wei Zhang, Yunpeng Li +3
While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack s…
cs.AI2026
ClawSafety: "Safe" LLMs, Unsafe Agents
Bowen Wei, Yunbei Zhang, Jinhao Pan +5
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transact…
cs.DC2026
ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness
Wenxing Zhu, Simeng Qi, Junkui Chen +7
We present ACE-Bench (Azure SDK Coding Evaluation Benchmark), an execution-free benchmark that provides fast, reproducible pass or fail signals for whether large language model (LL…