2 papers
cs.CR2026
Agent Safety Should Be a Runtime Contract
Albus W. Ng, Yi Han, Jusheng Zhang +1
The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI. We argue this is structurally insufficient for auton…
cs.CR2026
DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction
Xuyang Liu, Yibin Han, Zhenwei Zhang +8
Large Language Model (LLM) agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions…