paper-with-me

홈 › Papers

Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework

2022-12-16 · Junzhuo Li, Xinwei Wu, Weilong Dong, Shuangzhi Wu, Chao Bian, Deyi Xiong

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.

📄 PDF Abstract BibTeX arXiv:2212.08349

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationModel CompressionPrivacy PreservingTransfer Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation

2022-09-10 · Xuan Gong, Abhishek Sharma, Srikrishna Karanam, Ziyan Wu 외

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+3

Federated Learning with Privacy-Preserving Ensemble Attention Distillation

2022-10-16 · Xuan Gong, Liangchen Song, Rishi Vedula, Abhishek Sharma 외

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+1

On Membership Inference Attacks in Knowledge Distillation

2025-05-17 · Ziyao Cui, Minxing Zhang, Jian Pei

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 Preserving

Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher

2023-04-04 · Jiawei Shao, Fangzhao Wu, Jun Zhang

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 Learning

Better Knowledge Enhancement for Privacy-Preserving Cross-Project Defect Prediction

2024-12-23 · Yuying Wang, Yichen Li, Haozhao Wang, Lei Zhao 외

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