Dataset Obfuscation: Its Applications to and Impacts on Edge Machine Learning

08/08/2022

∙

Obfuscating a dataset by adding random noises to protect the privacy of sensitive samples in the training dataset is crucial to prevent data leakage to untrusted parties for edge applications. We conduct comprehensive experiments to investigate how the dataset obfuscation can affect the resultant model weights - in terms of the model accuracy, Frobenius-norm (F-norm)-based model distance, and level of data privacy - and discuss the potential applications with the proposed Privacy, Utility, and Distinguishability (PUD)-triangle diagram to visualize the requirement preferences. Our experiments are based on the popular MNIST and CIFAR-10 datasets under both independent and identically distributed (IID) and non-IID settings. Significant results include a trade-off between the model accuracy and privacy level and a trade-off between the model difference and privacy level. The results indicate broad application prospects for training outsourcing in edge computing and guarding against attacks in Federated Learning among edge devices.

READ FULL TEXT

Dataset Obfuscation: Its Applications to and Impacts on Edge Machine Learning

Asynchronous Federated Learning with Differential Privacy for Edge Intelligence

Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devices

Privacy-preserving Machine Learning through Data Obfuscation

No free lunch theorem for security and utility in federated learning

Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing

FedParking: A Federated Learning based Parking Space Estimation with Parked Vehicle assisted Edge Computing

FedCSD: A Federated Learning Based Approach for Code-Smell Detection

Dataset Obfuscation: Its Applications to and Impacts on Edge Machine Learning

Related Research

Asynchronous Federated Learning with Differential Privacy for Edge Intelligence

Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devices

Privacy-preserving Machine Learning through Data Obfuscation

No free lunch theorem for security and utility in federated learning

Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing

FedParking: A Federated Learning based Parking Space Estimation with Parked Vehicle assisted Edge Computing

FedCSD: A Federated Learning Based Approach for Code-Smell Detection