Verifiable and Provably Secure Machine Unlearning

by   Thorsten Eisenhofer, et al.

Machine unlearning aims to remove points from the training dataset of a machine learning model after training; for example when a user requests their data to be deleted. While many machine unlearning methods have been proposed, none of them enable users to audit the unlearning procedure and verify that their data was indeed unlearned. To address this, we define the first cryptographic framework to formally capture the security of verifiable machine unlearning. While our framework is generally applicable to different approaches, its advantages are perhaps best illustrated by our instantiation for the canonical approach to unlearning: retraining the model without the data to be unlearned. In our cryptographic protocol, the server first computes a proof that the model was trained on a dataset D. Given a user data point d, the server then computes a proof of unlearning that shows that d ∉ D. We realize our protocol using a SNARK and Merkle trees to obtain proofs of update and unlearning on the data. Based on cryptographic assumptions, we then present a formal game-based proof that our instantiation is secure. Finally, we validate the practicality of our constructions for unlearning in linear regression, logistic regression, and neural networks.


Eluding Secure Aggregation in Federated Learning via Model Inconsistency

Federated learning allows a set of users to train a deep neural network ...

CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning

How to train a machine learning model while keeping the data private and...

A Security Verification Framework of Cryptographic Protocols Using Machine Learning

We propose a security verification framework for cryptographic protocols...

BLAZE: Blazing Fast Privacy-Preserving Machine Learning

Machine learning tools have illustrated their potential in many signific...

Machine Learning on Cloud with Blockchain: A Secure, Verifiable and Fair Approach to Outsource the Linear Regression

Linear Regression (LR) is a classical machine learning algorithm which h...

On the Fundamental Limits of Formally (Dis)Proving Robustness in Proof-of-Learning

Proof-of-learning (PoL) proposes a model owner use machine learning trai...

Privacy-Preserving Payment Splitting

Widely used payment splitting apps allow members of a group to keep trac...

Please sign up or login with your details

Forgot password? Click here to reset