1 code implementation • 2 Mar 2024 • Minh N. Vu, Truc Nguyen, Tre' R. Jeter, My T. Thai
With the rapid adoption of Federated Learning (FL) as the training and tuning protocol for applications utilizing Large Language Models (LLMs), recent research highlights the need for significant modifications to FL to accommodate the large-scale of LLMs.
no code implementations • 23 Nov 2023 • Tre' R. Jeter, Truc Nguyen, Raed Alharbi, My T. Thai
We first uncover the core principle of gradient inversion that enables these attacks and theoretically identify the main conditions by which the defense can be robust regardless of the attack strategies.
no code implementations • 11 May 2022 • Truc Nguyen, Phuc Thai, Tre' R. Jeter, Thang N. Dinh, My T. Thai
However, we show that, by manipulating the client selection process, the server can circumvent the secure aggregation to learn the local models of a victim client, indicating that secure aggregation alone is inadequate for privacy protection.