CRAICVJul 2, 2024

A Method to Facilitate Membership Inference Attacks in Deep Learning Models

arXiv:2407.01919v110 citationsh-index: 42
Originality Highly original
AI Analysis

This work reveals a severe privacy vulnerability for data holders using off-the-shelf ML code, exposing a pitfall in current privacy auditing practices.

The authors tackled the problem of membership inference attacks in deep learning by demonstrating a new attack method that allows a malicious ML provider to reliably de-identify all training samples with over 99% true positive rate at low false positive rates, while causing less than 1% accuracy drop in the compromised models.

Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models. Today, even ordinary data holders who are not ML experts can apply off-the-shelf codebase to build high-performance ML models on their data, many of which are sensitive in nature (e.g., clinical records). In this work, we consider a malicious ML provider who supplies model-training code to the data holders, does not have access to the training process, and has only black-box query access to the resulting model. In this setting, we demonstrate a new form of membership inference attack that is strictly more powerful than prior art. Our attack empowers the adversary to reliably de-identify all the training samples (average >99% attack TPR@0.1% FPR), and the compromised models still maintain competitive performance as their uncorrupted counterparts (average <1% accuracy drop). Moreover, we show that the poisoned models can effectively disguise the amplified membership leakage under common membership privacy auditing, which can only be revealed by a set of secret samples known by the adversary. Overall, our study not only points to the worst-case membership privacy leakage, but also unveils a common pitfall underlying existing privacy auditing methods, which calls for future efforts to rethink the current practice of auditing membership privacy in machine learning models.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes