Membership Inference Attacks on Lottery Ticket Networks

08/07/2021
by   Aadesh Bagmar, et al.
0

The vulnerability of the Lottery Ticket Hypothesis has not been studied from the purview of Membership Inference Attacks. Through this work, we are the first to empirically show that the lottery ticket networks are equally vulnerable to membership inference attacks. A Membership Inference Attack (MIA) is the process of determining whether a data sample belongs to a training set of a trained model or not. Membership Inference Attacks could leak critical information about the training data that can be used for targeted attacks. Recent deep learning models often have very large memory footprints and a high computational cost associated with training and drawing inferences. Lottery Ticket Hypothesis is used to prune the networks to find smaller sub-networks that at least match the performance of the original model in terms of test accuracy in a similar number of iterations. We used CIFAR-10, CIFAR-100, and ImageNet datasets to perform image classification tasks and observe that the attack accuracies are similar. We also see that the attack accuracy varies directly according to the number of classes in the dataset and the sparsity of the network. We demonstrate that these attacks are transferable across models with high accuracy.

READ FULL TEXT
research
01/12/2020

Membership Inference Attacks Against Object Detection Models

Machine learning models can leak information about the dataset they trai...
research
11/18/2021

Enhanced Membership Inference Attacks against Machine Learning Models

How much does a given trained model leak about each individual data reco...
research
05/27/2020

Towards the Infeasibility of Membership Inference on Deep Models

Recent studies propose membership inference (MI) attacks on deep models....
research
11/17/2020

Bootstrap Aggregation for Point-based Generalized Membership Inference Attacks

An efficient scheme is introduced that extends the generalized membershi...
research
08/28/2020

MCMIA: Model Compression Against Membership Inference Attack in Deep Neural Networks

Deep learning or deep neural networks (DNNs) have nowadays enabled high ...
research
10/17/2022

A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information

Unlike traditional static deep neural networks (DNNs), dynamic neural ne...
research
03/04/2022

User-Level Membership Inference Attack against Metric Embedding Learning

Membership inference (MI) determines if a sample was part of a victim mo...

Please sign up or login with your details

Forgot password? Click here to reset