Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework
Knowledge distillation (KD) has been widely used for model compression and knowledge transfer. Typically, a big teacher model trained on sufficient data transfers knowledge to a small student model. However, despite the success of KD, little effort has been made to study whether KD leaks the training data of the teacher model. In this paper, we experimentally reveal that KD suffers from the risk of privacy leakage. To alleviate this issue, we propose a novel knowledge distillation method, swing distillation, which can effectively protect the private information of the teacher model from flowing to the student model. In our framework, the temperature coefficient is dynamically and adaptively adjusted according to the degree of private information contained in the data, rather than a predefined constant hyperparameter. It assigns different temperatures to tokens according to the likelihood that a token in a position contains private information. In addition, we inject noise into soft targets provided to the student model, in order to avoid unshielded knowledge transfer. Experiments on multiple datasets and tasks demonstrate that the proposed swing distillation can significantly reduce (by over 80% in terms of canary exposure) the risk of privacy leakage in comparison to KD with competitive or better performance. Furthermore, swing distillation is robust against the increasing privacy budget.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge DistillationModel CompressionPrivacy PreservingTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation
Federated Learning (FL) is a machine learning paradigm where local nodes collaboratively train a central model while the training data remains decentralized. Existing FL methods typically share model parameters or employ…
Federated Learningimage-classificationImage ClassificationKnowledge Distillation+3Federated Learning with Privacy-Preserving Ensemble Attention Distillation
Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications s…
Federated Learningimage-classificationImage ClassificationKnowledge Distillation+1On Membership Inference Attacks in Knowledge Distillation
Nowadays, Large Language Models (LLMs) are trained on huge datasets, some including sensitive information. This poses a serious privacy concern because privacy attacks such as Membership Inference Attacks (MIAs) may dete…
Knowledge DistillationPrivacy PreservingSelective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher
While federated learning is promising for privacy-preserving collaborative learning without revealing local data, it remains vulnerable to white-box attacks and struggles to adapt to heterogeneous clients. Federated dist…
Federated LearningKnowledge DistillationPrivacy PreservingTransfer LearningBetter Knowledge Enhancement for Privacy-Preserving Cross-Project Defect Prediction
Cross-Project Defect Prediction (CPDP) poses a non-trivial challenge to construct a reliable defect predictor by leveraging data from other projects, particularly when data owners are concerned about data privacy. In rec…
Federated LearningKnowledge DistillationPrivacy Preserving