Zhe Liu
5 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
SafeHarbor is a novel, hierarchical memory-augmented framework that establishes context-aware decision boundaries for LLM agents, achieving state-of-the-art safety while minimizing over-refusal.
OrchJail introduces an orchestration-guided fuzzing framework to systematically jailbreak tool-calling text-to-image agents by exploiting unsafe multi-step tool-orchestration patterns.
The paper introduces LITMUS, a novel benchmark that rigorously tests LLM agents for dangerous, physical-layer behavioral jailbreaks in real OS environments, revealing that current agents frequently execute high-risk operations despite safety guardrails.
The paper proposes SwarmSense-DNN, a decentralized neural framework for secure, cooperative anomaly detection in IoT environments.
The paper proposes a semantic-aware framework for evaluating fairness in Large Audio Language Models using semantic embeddings and speaker identity as random effects.
Papers
Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation
The paper proposes a semantic-aware framework for evaluating fairness in Large Audio Language Models using semantic embeddings and speaker identity as random effects.