all InfoSec news
Recovering Private Text in Federated Learning of Language Models. (arXiv:2205.08514v1 [cs.CL])
May 18, 2022, 1:20 a.m. | Samyak Gupta, Yangsibo Huang, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen
cs.CR updates on arXiv.org arxiv.org
Federated learning allows distributed users to collaboratively train a model
while keeping each user's data private. Recently, a growing body of work has
demonstrated that an eavesdropping attacker can effectively recover image data
from gradients transmitted during federated learning. However, little progress
has been made in recovering text data. In this paper, we present a novel attack
method FILM for federated learning of language models -- for the first time, we
show the feasibility of recovering text from large batch …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Information Security Engineers
@ D. E. Shaw Research | New York City
Information Systems Security Officer (ISSO), Junior
@ Dark Wolf Solutions | Remote / Dark Wolf Locations
Cloud Security Engineer
@ ManTech | REMT - Remote Worker Location
SAP Security & GRC Consultant
@ NTT DATA | HYDERABAD, TG, IN
Security Engineer 2 - Adversary Simulation Operations
@ Datadog | New York City, USA