MEraser: An Effective Fingerprint Erasure Approach for Large Language Models (2025 · 11 citations)
Backdoor-based fingerprinting lets LLM owners prove ownership through secret trigger–response pairs, but little work has tested how easily these marks can be removed.
CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor (2025 · 4 citations)
The paper tackles ownership verification for large language models that may be stolen and redistributed. Earlier fingerprinting approaches each have a weak spot. Rare-token triggers stand out under perplexity checks. Natural-looking triggers such as HashChain tend to vanish after fine-tuning or merging. Most…
AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing (2026 · 2 citations)
LLM role-playing systems often feel flat. They mostly generate dialogue, treat the surroundings as static backdrop, and assume one fixed scene with a fixed cast. AdaMARP tackles both problems. Each turn interleaves four marked elements: [Thought], (Action), <Environment> and plain Speech, so world states and events…
MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI (2026 · 1 citation)
Connecting LLM agents to external tools through the Model Context Protocol (MCP) opens new attack routes, including prompt injection, Tool Poisoning, Shadowing and data exfiltration.

All works

5 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

MEraser: An Effective Fingerprint Erasure Approach for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Jingxuan Zhang, Zhenhua Xu, Rui Hu, et al.2025 · 11 citations
CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation BackdoorConference on Empirical Methods in Natural Language Processing (EMNLP)Zhenhua Xu, Xixiang Zhao, Xubin Yue, et al.2025 · 4 citations
AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-PlayingFindings of the Association for Computational LinguisticsZhenhua Xu, Dongsheng Chen, Shuo Wang, et al.2026 · 2 citations
MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AIFindings of the Association for Computational LinguisticsWenpeng Xing, Zhonghao Qi, Yupeng Qin, et al.2026 · 1 citation
Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetWenpeng Xing et al.2026

Co-authors here

9 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 16 times (of the 149,439 papers whose bibliographies we read); 3 citing papers with a page here →.

Updated 1 November 2026