← Search

Tianliang Lu

2 accepted papers

2026

KINGUARD: HIERARCHICAL KINSHIP-AWARE FINGERPRINTING TO DEFEND AGAINST LARGE LANGUAGE MODEL STEALING

ICASSP 2026poster

Protecting the intellectual property of large language models requires robust ownership verification. Conventional backdoor fingerprinting, however, is flawed by a stealth-robustness paradox: to be robust, these methods force models to memorize fixed responses to high-perplexity triggers, but this t…

Cited by 0SourcePDFScholar
2026

Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation

ICASSP 2026poster

Entropy-based inference methods have gained traction for improving the reliability of Large Language Models (LLMs). However, many existing approaches, such as entropy minimization techniques, suffer from high computational overhead and fail to leverage historical token context effectively. To addres…

Cited by 0SourcePDFScholar