all InfoSec news
Amplifying Membership Exposure via Data Poisoning. (arXiv:2211.00463v1 [cs.CR])
Nov. 2, 2022, 1:24 a.m. | Yufei Chen, Chao Shen, Yun Shen, Cong Wang, Yang Zhang
cs.CR updates on arXiv.org arxiv.org
As in-the-wild data are increasingly involved in the training stage, machine
learning applications become more susceptible to data poisoning attacks. Such
attacks typically lead to test-time accuracy degradation or controlled
misprediction. In this paper, we investigate the third type of exploitation of
data poisoning - increasing the risks of privacy leakage of benign training
samples. To this end, we demonstrate a set of data poisoning attacks to amplify
the membership exposure of the targeted class. We first propose a generic …
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
Cloud Technical Solutions Engineer, Security
@ Google | Mexico City, CDMX, Mexico
Assoc Eng Equipment Engineering
@ GlobalFoundries | SGP - Woodlands
Staff Security Engineer, Cloud Infrastructure
@ Flexport | Bellevue, WA; San Francisco, CA
Software Engineer III, Google Cloud Security and Privacy
@ Google | Sunnyvale, CA, USA
Software Engineering Manager II, Infrastructure, Google Cloud Security and Privacy
@ Google | San Francisco, CA, USA; Sunnyvale, CA, USA