Haihua Shen

ContextFuzz: A Framework for Discovering Speculative Fetch Attacks

IGBFuzz: Unified RTL Security Fuzzing via Graph-Aware Bandit Scheduling

ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents

Results show that a terminal policy label is not a sufficient statistic for operational post-exposure containment; evaluations should report endpoint, stage-stratified trajectory, and utility evidence separately, and should promote recovery evidence to comparative claims only where the corresponding controls are valid.

ContainmentBench: Trace-Based Evaluation of Post-Exposure Containment in Tool-Using LLM Agents

ContainmentBench, a sandboxed benchmark comprising a 504-scenario specification dataset, a shared rollout-trace schema, and stage-scoped metrics for endpoint violations, logged propagation, and explicitly authorized taint-exposed proposals that commit, is introduced.