← Search

Chenxi Dai

2 accepted papers

2025

Stealing Training Data from Large Language Models in Decentralized Training through Activation Inversion Attack

ACL 2025long

Decentralized training has become a resource-efficient framework to democratize the training of large language models (LLMs). However, the privacy risks associated with this framework, particularly due to the potential inclusion of sensitive data in training datasets, remain unexplored. This paper i…

2024

Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training

ICML 2024poster

Modern machine learning applications increasingly demand greater computational resources for training large models. Decentralized training has emerged as an effective means to democratize this technology. However, the potential threats associated with this approach remain inadequately discussed, pos…