RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
RiskChainBench introduces RiskChainBench, pairing 3,600 synthetic token-text restoration inputs from 600 source sessions with 600 corresponding human-labeled local web environments that produces a frozen, evidence-cited risk report without message-side semantics or domain-reputation cues.
Zhuo-Xin Liu, Zhi-Ming Ma, Ying Zhang et al.
· 0 citations