all AI news
Low-Cost High-Power Membership Inference Attacks
Feb. 27, 2024, 5:44 a.m. | Sajjad Zarifzadeh, Philippe Liu, Reza Shokri
cs.LG updates on arXiv.org arxiv.org
Abstract: Membership inference attacks (MIA) aim to detect if a particular data point was used in training a machine learning model. Recent strong attacks have high computational costs and inconsistent performance under varying conditions, rendering them unreliable for practical privacy risk assessment. We design a novel, efficient, and robust membership inference attack (RMIA) which accurately differentiates between population data and training data of a model, with minimal computational overhead. We achieve this by a more accurate …
abstract aim arxiv assessment attacks computational cost costs cs.cr cs.lg data design inference low machine machine learning machine learning model novel performance power practical privacy rendering risk risk assessment robust stat.ml them training type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Robotics Technician - 3rd Shift
@ GXO Logistics | Perris, CA, US, 92571