Proceedings of the AAAI Conference on Artificial Intelligence · 2024 · 13 citations · 49 references
ComputingComputer ScienceCybersecurityComputer SecurityFeature EngineeringMachine LearningData De-identificationData SecurityAccuracyBackdoor RemovalBackdoor TechniquesData SanitizationDiffusion ModelsGround Truth LabelingLabelsSanitization
Dataset sanitization is a widely adopted proactive defense against poisoning-based backdoor attacks, aimed at filtering out and removing poisoned samples from training datasets. However, existing methods have shown limited efficacy in countering the ever-evolving trigger functions, and often leading to considerable degradation of benign accuracy. In this paper, we propose DataElixir, a novel sanitization approach tailored to purify poisoned datasets. We leverage diffusion models to eliminate trigger features and restore benign features, thereby turning the poisoned samples into benign ones. Specifically, with multiple iterations of the forward and reverse process, we extract intermediary images and their predicted labels for each sample in the original dataset. Then, we identify anomalous samples in terms of the presence of label transition of the intermediary images, detect the target label by quantifying distribution discrepancy, select their purified images considering pixel and feature distance, and determine their ground-truth labels by training a benign model. Experiments conducted on 9 popular attacks demonstrates that DataElixir effectively mitigates various complex attacks while exerting minimal impact on benign accuracy, surpassing the performance of baseline defense methods.
49
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan C. Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing · 2004 · 56K citations
On Information and Sufficiency
S. Kullback, R. A. Leibler · The Annals of Mathematical Statistics · 1951 · 20K citations · Full text
Deep Learning Face Attributes in the Wild
Ziwei Liu, Ping Luo, Xiaogang Wang et al. · 2015 · 7.7K citations