Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors

arXiv:2402.12626v1 Announce Type: new
Abstract: Machine learning models have achieved great success in supervised learning tasks for end-to-end training, which requires a large amount of labeled data that is not always feasible. Recently, many practitioners have shifted to self-supervised learning methods that utilize cheap unlabeled data to learn a general feature extractor via pre-training, which can be further applied to personalized downstream tasks by simply training an additional linear layer with limited labeled data. However, such a process may also …

abstract arxiv attacks cs.cr cs.lg data data poisoning feature general learn machine machine learning machine learning models poisoning attacks self-supervised learning success supervised learning tasks training type