Making AI Forget You: Data Deletion in Machine Learning

Abstract

Intense recent discussions have focused on how to provide individuals with control over when their data can and cannot be used --- the EU's Right To Be Forgotten regulation is an example of this effort. In this paper we initiate a framework studying what to do when it is no longer permissible to deploy models derivative from specific user data. In particular, we formulate the problem of efficiently deleting individual data points from trained machine learning models. For many standard ML models, the only way to completely remove an individual's data is to retrain the whole model from scratch on the remaining data, which is often not computationally practical. We investigate algorithmic principles that enable efficient data deletion in ML. For the specific setting of k-means clustering, we propose two provably efficient deletion algorithms which achieve an average of over 100X improvement in deletion efficiency across 6 datasets, while producing clusters of comparable statistical quality to a canonical k-means++ baseline.

arXiv commentTo appear in NeurIPS 2019

References in corpus (8)

• Scikit-learn: Machine Learning in Python
• The NumPy array: a structure for efficient numerical computation
• Deep Learning with Differential Privacy
• Fixed Point Quantization of Deep Convolutional Networks
• Training deep neural networks with low precision multiplications
• Algorithms that Remember: Model Inversion Attacks and Data Protection Law
• Distributed k-Means and k-Median Clustering on General Topologies
• Quantized Compressive K-Means

Cited by in corpus (14)

• On the Opportunities and Risks of Foundation Models
• When Machine Unlearning Jeopardizes Privacy
• Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
• Adaptive Machine Unlearning
• Approximate Data Deletion from Machine Learning Models
• Certified Data Removal from Machine Learning Models
• On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning
• Feature Unlearning for Pre-trained GANs and VAEs
• Lightweight machine unlearning in neural network
• MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes
• ModelPred: A Framework for Predicting Trained Model from Training Data
• Knowledge-Adaptation Priors
• Minimax Optimization: The Case of Convex-Submodular
• Bayesian Variational Federated Learning and Unlearning in Decentralized Networks