Junfeng Yang
← Publications

Research work

Towards Making Systems Forget with Machine Unlearning

Yinzhi Cao, Junfeng Yang

Proceedings of the 36th IEEE Symposium on Security and Privacy (IEEE S&P), 2015

Abstract

Today’s systems produce a rapidly exploding amount of data, and the data further derives more data, forming a complex data propagation network that we call the data’s lineage. There are many reasons that users want systems to forget certain data including its lineage. From a privacy perspective, users who become concerned with new privacy risks of a system often want the system to forget their data and lineage. From a security perspective, if an attacker pollutes an anomaly detector by injecting manually crafted data into the training data set, the detector must forget the injected data to regain security. From a usability perspective, a user can remove noise and incorrect entries so that a recommendation engine gives useful recommendations. Therefore, we envision forgetting systems, capable of forgetting certain data and their lineages, completely and quickly. This paper focuses on making learning systems forget, the process of which we call machine unlearning, or simply unlearning. We present a general, efficient unlearning approach by transforming learning algorithms used by a system into a summation form. To forget a training data sample, our approach simply updates a small number of summations – asymptotically faster than retraining from scratch. Our approach is general, because the summation form is from the statistical query learning in which many machine learning algorithms can be implemented. Our approach also applies to all stages of machine learning, including feature selection and modeling. Our evaluation, on four diverse learning systems and real-world workloads, shows that our approach is general, effective, fast, and easy to use.

Recognition

Coverage

  1. The Atlantic Teaching a Computer to Forget
  2. The Stack Machine Unlearning: How Can Information Be Forgotten in the Age of Viral Data Spread?
  3. KurzweilAI New Machine Unlearning Technique Deletes Unwanted Data
  4. ACM TechNews Machine Unlearning: How Can Information Be Forgotten in the Age of Viral Data Spread?
  5. EurekAlert New Machine Unlearning Technique Wipes Out Unwanted Data Quickly and Completely
  6. Lehigh News Machine Unlearning
  7. Lehigh Engineering Helping Machines Forget
  8. Columbia Computer Science Four Professors Recognized with Test of Time Awards
  9. Johns Hopkins Information Security Institute Yinzhi Cao Receives Distinguished Paper Award and Test-of-Time Award at IEEE Security and Privacy 2025
  10. IEEE Cipher Security and Privacy Symposium Test of Time Awards
  11. Columbia Engineering Magazine Machine Learning 2.0
  12. Columbia Engineering Luca Carloni and Junfeng Yang Elected 2025 ACM Fellows