all InfoSec news
Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
March 14, 2024, 4:11 a.m. | Ana-Maria Cretu, Daniel Jones, Yves-Alexandre de Montjoye, Shruti Tople
cs.CR updates on arXiv.org arxiv.org
Abstract: Machine learning models have been shown to leak sensitive information about their training datasets. Models are increasingly deployed on devices, raising concerns that white-box access to the model parameters increases the attack surface compared to black-box access which only provides query access. Directly extending the shadow modelling technique from the black-box to the white-box setting has been shown, in general, not to perform better than black-box only attacks. A potential reason is misalignment, a known …
access arxiv attack attack surface box cs.cr cs.lg datasets devices effect information leak machine machine learning machine learning models privacy query sensitive sensitive information training
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Social Engineer For Reverse Engineering Exploit Study
@ Independent study | Remote
Senior Software Engineer, Security
@ Niantic | Zürich, Switzerland
Consultant expert en sécurité des systèmes industriels (H/F)
@ Devoteam | Levallois-Perret, France
Cybersecurity Analyst
@ Bally's | Providence, Rhode Island, United States
Digital Trust Cyber Defense Executive
@ KPMG India | Gurgaon, Haryana, India
Program Manager - Cybersecurity Assessment Services
@ TestPros | Remote (and DMV), DC