Author

Litian Zhang

Observed name: Zhang, Litian

Institution: Beijing University of Posts and Telecommunications

Observed institution: Beijing University of Posts and Telecommunications

OpenAlex ID: A5140848503

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

2026 · Liu, Songyang, Li, Chaozhuo, et al. · arXiv (Cornell University) · 6

Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS

2026 · Bingyu Yan, Xiaoming Zhang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2

A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors

2026 · Li, Pengxun, Zhang, Litian, et al. · arXiv (Cornell University)

GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities

2026 · Bu, Haoran, Chen, Zejian, et al. · arXiv (Cornell University)

Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM Agents

2026 · Yan, Bingyu, Zhang, Xiaoming, et al. · arXiv (Cornell University)

Towards Personalized Differentially Private Learning for Decentralized Local Graphs

2026 · He, Longzhu, Tang, Peng, et al. · arXiv (Cornell University)

OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attacks

2026 · Litian Zhang, Chaozhuo Li, et al. · Preprints.org

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning

2026 · Association for Computational Linguistics 2026, Ha, Rui, et al. · Underline Science Inc.

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS

2026 · Association for Computational Linguistics 2026, Hei, Yiming, et al. · Underline Science Inc.

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS

2026 · Yan, Bingyu, Zhang, Xiaoming, et al. · arXiv (Cornell University)

S-BGM: Stable Self-Evolving LLMs via Cognitive Bipartite Graph Modeling

2026 · Songyang Liu, Chaozhuo Li, et al. · Preprints.org

OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attacks

2026 · Zhang, Litian, Li, Chaozhuo, et al. · arXiv (Cornell University)

PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation

2026 · Yan, Bingyu, Zhang, Xiaoming, et al. · arXiv (Cornell University)

Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents

2026 · Bu, Haoran, Zhang, Litian, et al. · arXiv (Cornell University)

MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting

2026 · Association for Artificial Intelligence 2026, Ha, Rui, et al. · Underline Science Inc.

Works count: 15

Citation count: 2

H-index: 1

I10-index: