Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Zhe Liu

Zhe Liu

5 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Crypto×4AI×3NLP×2Sound×1Networking×1Multiagent×1

Frequent co-authors

Jing Yang1×
Vijay Govindarajan1×
Saad Arif1×
Xu Xu1×
Mohamed Kallel1×
Zaffar Ahmed Shaikh1×

Research Timeline

2026
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

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: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing

OrchJail introduces an orchestration-guided fuzzing framework to systematically jailbreak tool-calling text-to-image agents by exploiting unsafe multi-step tool-orchestration patterns.

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

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.

SwarmSense-DNN: A Trustworthy and Decentralized Neural Framework for Proactive Anomaly Defense in Consumer IoT

The paper proposes SwarmSense-DNN, a decentralized neural framework for secure, cooperative anomaly detection in IoT environments.

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.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIcs.SDEmpiricalRecentAug 13, 2026

Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation

Zhe Liu

The paper proposes a semantic-aware framework for evaluating fairness in Large Audio Language Models using semantic embeddings and speaker identity as random effects.

View →
cs.CRcs.NIEmpirical
Recent
Jun 10, 2026

SwarmSense-DNN: A Trustworthy and Decentralized Neural Framework for Proactive Anomaly Defense in Consumer IoT

Jing Yang, Vijay Govindarajan, Saad Arif, Xu Xu +5 more

The paper proposes SwarmSense-DNN, a decentralized neural framework for secure, cooperative anomaly detection in IoT environments.

View →
cs.CRcs.CLMay 11, 2026

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

Chiyu Zhang, Huiqin Yang, Bendong Jiang, Xiaolei Zhang +7 more

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 ex…

View →
cs.MAcs.AIcs.CRMay 8, 2026

OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing

Jianming Chen, Yawen Wang, Junjie Wang, Zhe Liu +2 more

OrchJail introduces an orchestration-guided fuzzing framework to systematically jailbreak tool-calling text-to-image agents by exploiting unsafe multi-step tool-orchestration patterns.

View →
cs.CRcs.AIMay 7, 2026

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

Zhe Liu, Zonghao Ying, Wenxin Zhang, Quanchen Zou +4 more

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.

View →