Jinta Weng — accepted AI-conference papers

2026

Steering Representations, Safeguarding Privacy: A Cross-Modal Privacy Protection Method for Generative AI

Jie Zhang, Chenxu Niu, Zhefeng Nan, Yangyan Xu, Jinta Weng

AAAI 2026technical

Privacy concerns have long been a critical issue in AI models. With the rapid advancement of generative AI, the privacy awareness of models has drawn attention, raising new challenges for privacy protection that is independent of data and tasks. This paper introduces a novel framework for enhancing

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models

Chenxu Niu, Jie Zhang, Yanbing Liu, Yunpeng Li, Jinta Weng, Yue Hu

NeurIPS 2025poster

Backdoor attacks pose a significant threat to large language models (LLMs) by embedding malicious triggers that manipulate model behavior. However, existing defenses primarily rely on prior knowledge of backdoor triggers or targets and offer only superficial mitigation strategies, thus struggling to…

Cited by 0 Source ↗Scholar ↗