collaborators

12 papers

cs.CR2026

KinGuard: Hierarchical Kinship-Aware Fingerprinting to Defend Against Large Language Model Stealing

Zhenhua Xu, Xiaoning Tian, Wenjun Zeng +5

Protecting the intellectual property of large language models requires robust ownership verification. Conventional backdoor fingerprinting, however, is flawed by a stealth-robustne…

cs.CR2026

DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection

Zhenhua Xu, Yiran Zhao, Mengting Zhong +4

The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either re…

cs.CR2026

ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models

Zhenhua Xu, Haobo Zhang, Zhebo Wang +4

Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activa…

eess.AS2025

Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation

Xining Song, Zhihua Wei, Rui Wang +3

Identity, accent, style, and emotions are essential components of human speech. Voice conversion (VC) techniques process the speech signals of two input speakers and other modaliti…

cs.CL2025

CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor

Zhenhua Xu, Xixiang Zhao, Xubin Yue +3

The widespread deployment of large language models (LLMs) has intensified concerns around intellectual property (IP) protection, as model theft and unauthorized redistribution beco…

cs.LG2025

MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors

Xin Tong, Zhi Lin, Jingya Wang +2

Large language models (LLMs) enforce safety alignment to reliably refuse malicious requests, yet the same blanket safeguards also block legitimate uses in policing, defense, and ot…