Defending Against Neural Network Model Inversion Attacks via Data Poisoning

TL;DR

This paper proposes a novel data poisoning-based defense mechanism against neural network model inversion attacks, effectively protecting privacy without retraining and maintaining classifier utility.

Contribution

It introduces two data poisoning strategies, LPA and LFP, that hinder data reconstruction attacks while preserving model utility, outperforming existing defenses.

Findings

LPA significantly increases difficulty of data reconstruction.

LFP effectively perturbs a subset of outputs with minimal utility loss.

Defense outperforms current state-of-the-art methods.

Abstract

Model inversion attacks pose a significant privacy threat to machine learning models by reconstructing sensitive data from their outputs. While various defenses have been proposed to counteract these attacks, they often come at the cost of the classifier's utility, thus creating a challenging trade-off between privacy protection and model utility. Moreover, most existing defenses require retraining the classifier for enhanced robustness, which is impractical for large-scale, well-established models. This paper introduces a novel defense mechanism to better balance privacy and utility, particularly against adversaries who employ a machine learning model (i.e., inversion model) to reconstruct private data. Drawing inspiration from data poisoning attacks, which can compromise the performance of machine learning models, we propose a strategy that leverages data poisoning to contaminate the training data of inversion models, thereby preventing model inversion attacks. Two defense methods are presented. The first, termed label-preserving poisoning attacks for all output vectors (LPA), involves subtle perturbations to all output vectors while preserving their labels. Our findings demonstrate that these minor perturbations, introduced through a data poisoning approach, significantly increase the difficulty of data reconstruction without compromising the utility of the classifier. Subsequently, we introduce a second method, label-flipping poisoning for partial output vectors (LFP), which selectively perturbs a small subset of output vectors and alters their labels during the process. Empirical results indicate that LPA is notably effective, outperforming the current state-of-the-art defenses. Our data poisoning-based defense provides a new retraining-free defense paradigm that preserves the victim classifier's utility.