Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models

29 January 2022

Papers citing "Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models"

6 / 6 papers shown

Title
ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models Jin Xie Ruishi He Songze Li Xiaojun Jia Shouling Ji SILM AAML 48 0 0 29 Apr 2025
When the Curious Abandon Honesty: Federated Learning Is Not Private Franziska Boenisch Adam Dziedzic R. Schuster Ali Shahin Shamsabadi Ilia Shumailov Nicolas Papernot FedML AAML 62 143 0 06 Dec 2021
A Field Guide to Federated Optimization Jianyu Wang Zachary B. Charles Zheng Xu Gauri Joshi H. B. McMahan ... Mi Zhang Tong Zhang Chunxiang Zheng Chen Zhu Wennan Zhu FedML 139 358 0 14 Jul 2021
Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications Matthias Paulik M. Seigel Henry Mason Dominic Telaar Joris Kluivers ... Dominic Hughes O. Javidbakht Fei Dong Rehan Rishi Stanley Hung FedML 141 111 0 16 Feb 2021
Extracting Training Data from Large Language Models Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown D. Song Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 241 1,386 0 14 Dec 2020
When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning? Gavin Brown Mark Bun Vitaly Feldman Adam D. Smith Kunal Talwar 206 80 0 11 Dec 2020