Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

methodology-1

Machine Unlearning

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in machine-unlearning-3

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find machine-unlearning-3 models and implementations

Datasets

No datasets available.

Subtasks

Continual Forgetting

Most implemented papers

Machine Unlearning for Random Forests

Jonathan Brophy, Daniel Lowd•Thu Sep 10 2020

Data removal-enabled (DaRE) forests are introduced, a variant of random forests that enables the removal of training data with minimal retraining, and are found to delete data orders of magnitude faster than retraining from scratch while sacrificing little to no predictive power.

199

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Towards Adversarial Evaluations for Inexact Machine Unlearning

Philip H. S. Torr, Ameya Prabhu, P. Kumaraguru, S. Lim, Shashwat Goel, Amartya Sanyal•Sun Jan 16 2022

A stronger black-box evaluation method called the Interclass Confusion (IC) test which adversarially manipulates data during training to detect the insufficiency of unlearning procedures is designed.

78 0

Paper Graph

Descent-to-Delete: Gradient-Based Methods for Machine Unlearning

Aaron Roth, Seth Neel, Saeed Sharifi-Malvajerdi•Sun Jul 05 2020

This work gives the first data deletion algorithms that are able to handle an arbitrarily long sequence of adversarial updates while promising both per-deletion run-time and steady-state error that do not grow with the length of the update sequence.

347 0

Paper Graph

How to Combine Membership-Inference Attacks on Multiple Updated Models

Matthew Jagielski, Stanley Wu, Alina Oprea, Jonathan Ullman, Roxana Geambasu•Wed May 11 2022

This paper develops the rst black-box MI attack algorithms that combine information from previously known standalone MI attacks to let the adversary take advantage of access to both the original model and one or more updated models to improve MI on the update set.

10 0

Paper Graph

Towards Probabilistic Verification of Machine Unlearning

Liwei Song, Prateek Mittal, David M. Sommer, Sameer Wagh•Sun Mar 08 2020

This work proposes a backdoor-based verification mechanism and demonstrates its effectiveness in certifying data deletion with high confidence using the above framework and makes a novel use of backdoor attacks in ML as a basis for quantitatively inferring machine unlearning.

80 0

Paper Graph

When Machine Unlearning Jeopardizes Privacy

M. Backes, Yang Zhang, Mathias Humbert, Min Chen, Zhikun Zhang, Tianhao Wang•Mon May 04 2020

This paper proposes a novel membership inference attack that leverages the different outputs of an ML model's two versions to infer whether a target sample is part of the training set of the original model but out of theTraining set of a corresponding unlearned model.

293 0

Paper Graph

Adaptive Machine Unlearning

Aaron Roth, Seth Neel, Varun Gupta, Christopher Jung, Saeed Sharifi-Malvajerdi, Chris Waites•Mon Jun 07 2021

This paper shows in theory how prior work for non-convex models fails against adaptive deletion sequences, and uses this intuition to design a practical attack against the SISA algorithm of Bourtoule et al.

221 0

Paper Graph

Adding a benchmark result helps the community track progress.

Machine Unlearning | State-of-the-Art