most citedA Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer

3 citations · 8 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG20233 cited

A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer

Chenyang Li, Zhao Song, Weixin Wang +1

The Deep Leakage from Gradient (DLG) attack has emerged as a prevalent and highly effective method for extracting sensitive training data by inspecting exchanged gradients. This ap…

cs.LG20231 cited

Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights

Yichuan Deng, Zhao Song, Shenghao Xie +1

In the realm of deep learning, transformers have emerged as a dominant architecture, particularly in natural language processing tasks. However, with their widespread adoption, con…

cs.LG2023

An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent

Zhao Song, Chiwun Yang

The delta-bar-delta algorithm is recognized as a learning rate adaptation technique that enhances the convergence speed of the training process in optimization by dynamically sched…

cs.LG20233 cited

Fine-tune Language Models to Approximate Unbiased In-context Learning

Timothy Chu, Zhao Song, Chiwun Yang

In-context learning (ICL) is an astonishing emergent ability of large language models (LLMs). By presenting a prompt that includes multiple input-output pairs as examples and intro…

cs.LG20231 cited

How to Protect Copyright Data in Optimization of Large Language Models?

Timothy Chu, Zhao Song, Chiwun Yang

Large language models (LLMs) and generative AI have played a transformative role in computer research and applications. Controversy has arisen as to whether these models output cop…