3 papers
cs.CR2025
Touch to Pair: Secure and Usable IoT Pairing without Information Loss
Chuxiong Wu, Xiaopeng Li, Lannan Luo +1
Secure pairing is essential for trustworthy deployment and operation of Internet of Things (IoT) devices. However, traditional pairing methods are unsuitable due to the lack of use…
cs.CL2025
Impact of Fine-Tuning Methods on Memorization in Large Language Models
Jie Hou, Chuxiong Wu, Lannan Luo +1
As the capabilities of pre-trained large language models (LLMs) continue to advance, the "pre-train and fine-tune" paradigm has become increasingly mainstream, leading to the devel…
cs.CR2025
StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models
Ya Jiang, Chuxiong Wu, Massieh Kordi Boroujeny +2
Watermarking for large language models (LLMs) offers a promising approach to identifying AI-generated text. Existing approaches, however, either compromise the distribution of orig…