Model adaptation tackles the distribution shift problem with a pre-trained model instead of raw data, becoming a popular paradigm due to its great privacy protection. Existing methods always assume adapting to a clean target domain, overlooking the security risks of unlabeled samples. In this paper, we explore the potential backdoor attacks on model adaptation launched by well-designed poisoning target data. Concretely, we provide two backdoor triggers with two poisoning strategies for different prior knowledge owned by attackers. These attacks achieve a high success rate and keep the normal performance on clean samples in the test stage. To defend against backdoor embedding, we propose a plug-and-play method named MixAdapt, combining it with existing adaptation algorithms. Experiments across commonly used benchmarks and adaptation methods demonstrate the effectiveness of MixAdapt. We hope this work will shed light on the safety of learning with unlabeled data.
翻译:暂无翻译