Unlearnable Examples Detection via Iterative Filtering
This addresses data poisoning attacks that compromise model training for machine learning practitioners, though it appears to be an incremental improvement over existing detection methods.
The paper tackles the problem of detecting unlearnable examples (poisoned samples) in mixed datasets by proposing an Iterative Filtering approach that exploits differences in how models adapt to clean versus poisoned data, achieving significant reductions in Half Total Error Rate (HTER) compared to state-of-the-art methods.
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.