Weijian Wang — accepted AI-conference papers

2026

Echoes within the Reasoning: Stealth and Effective Watermarking via Chain of Thought

Jiacheng Lu, Yiming Li, Tao Song, Weijian Wang, Wenjie Qu, Haibing Guan +1

ICML 2026poster

Large Language Models (LLMs) with proprietary Chain-of-Thought (CoT) capabilities constitute high-value intellectual property, yet protecting them against unauthorized theft and unlicensed commercialization remains a critical challenge. Existing watermarking paradigms are ill-suited for safeguarding…

Cited by 0 Source ↗Scholar ↗

2025

Adversarial-Inspired Backdoor Defense via Bridging Backdoor and Adversarial Attacks

Jia-Li Yin, Weijian Wang, Lyhwa, Wei Lin, Ximeng Liu

AAAI 2025technical

Backdoor attacks and adversarial attacks are two major security threats to deep neural networks (DNNs), with the former one is a training-time data poisoning attack that aims to implant backdoor triggers into models by injecting trigger patterns into training samples, and the latter one is a testing…

Cited by 0 Source ↗PDF ↗Scholar ↗