Bootstrap Aggregation for Point-based Generalized Membership Inference Attacks

11/17/2020
by   Daniel L. Felps, et al.
0

An efficient scheme is introduced that extends the generalized membership inference attack to every point in a model's training data set. Our approach leverages data partitioning to create variable sized training sets for the reference models. We then train an attack model for every single training example for a reference model configuration based upon output for each individual point. This allows us to quantify the membership inference attack vulnerability of each training data point. Using this approach, we discovered that smaller amounts of reference model training data led to a stronger attack. Furthermore, the reference models do not need to be of the same architecture as the target model, providing additional attack efficiencies. The attack may also be performed by an adversary even when they do not have the complete original data set.

READ FULL TEXT
research
05/13/2022

l-Leaks: Membership Inference Attacks with Logits

Machine Learning (ML) has made unprecedented progress in the past severa...
research
08/07/2021

Membership Inference Attacks on Lottery Ticket Networks

The vulnerability of the Lottery Ticket Hypothesis has not been studied ...
research
10/28/2022

On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target Models

Membership Inference Attacks (MIAs) infer whether a data point is in the...
research
05/29/2023

Membership Inference Attacks against Language Models via Neighbourhood Comparison

Membership Inference attacks (MIAs) aim to predict whether a data sample...
research
02/21/2019

Learning requirements for stealth attacks

The learning data requirements are analyzed for the construction of stea...
research
09/14/2023

SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems

Membership inference attacks allow adversaries to determine whether a pa...
research
02/13/2018

Understanding Membership Inferences on Well-Generalized Learning Models

Membership Inference Attack (MIA) determines the presence of a record in...

Please sign up or login with your details

Forgot password? Click here to reset