Unlearnable Examples Detection via Iterative Filtering

TL;DR

This paper introduces an iterative filtering method to detect unlearnable poisoned examples in datasets, improving identification accuracy without extra info and outperforming existing approaches across various scenarios.

Contribution

The proposed iterative filtering approach effectively detects unlearnable examples without additional data, enhancing robustness against data poisoning attacks.

Findings

Outperforms state-of-the-art detection methods

Reduces Half Total Error Rate significantly

Works across various datasets and attack types

Abstract

Deep neural networks are proven to be vulnerable to data poisoning attacks. Recently, a specific type of data poisoning attack known as availability attacks has led to the failure of data utilization for model learning by adding imperceptible perturbations to images. Consequently, it is quite beneficial and challenging to detect poisoned samples, also known as Unlearnable Examples (UEs), from a mixed dataset. In response, we propose an Iterative Filtering approach for UEs identification. This method leverages the distinction between the inherent semantic mapping rules and shortcuts, without the need for any additional information. We verify that when training a classifier on a mixed dataset containing both UEs and clean data, the model tends to quickly adapt to the UEs compared to the clean data. Due to the accuracy gaps between training with clean/poisoned samples, we employ a model to misclassify clean samples while correctly identifying the poisoned ones. The incorporation of additional classes and iterative refinement enhances the model's ability to differentiate between clean and poisoned samples. Extensive experiments demonstrate the superiority of our method over state-of-the-art detection approaches across various attacks, datasets, and poison ratios, significantly reducing the Half Total Error Rate (HTER) compared to existing methods.