Machine Unlearning
62 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Machine Unlearning
Most implemented papers
Machine Unlearning for Random Forests
The upper levels of DaRE trees use random nodes, which choose split attributes and thresholds uniformly at random.
Towards Adversarial Evaluations for Inexact Machine Unlearning
shash42/evaluating-inexact-unlearning
•
•
Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias.
Machine Unlearning
cleverhans-lab/machine-unlearning
•
•
Once users have shared their data online, it is generally difficult for them to revoke access and ask for the data to be deleted.
Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
ChrisWaites/descent-to-delete
•
•
We study the data deletion problem for convex models.
How to Combine Membership-Inference Attacks on Multiple Updated Models
Our results on four public datasets show that our attacks are effective at using update information to give the adversary a significant advantage over attacks on standalone models, but also compared to a prior MI attack that takes advantage of model updates in a related machine-unlearning setting.
Zero-Shot Machine Unlearning at Scale via Lipschitz Regularization
jwf40/zeroshot-unlearning-at-scale
•
•
The key challenge in unlearning is forgetting the necessary data in a timely manner, while preserving model performance.
Towards Probabilistic Verification of Machine Unlearning
inspire-group/unlearning-verification
•
•
In this work, we take the first step in proposing a formal framework to study the design of such verification mechanisms for data deletion requests -- also known as machine unlearning -- in the context of systems that provide machine learning as a service (MLaaS).
When Machine Unlearning Jeopardizes Privacy
More importantly, we show that our attack in multiple cases outperforms the classical membership inference attack on the original ML model, which indicates that machine unlearning can have counterproductive effects on privacy.
Graph Unlearning
MinChen00/Graph-Unlearning
•
•
In this paper, we propose GraphEraser, a novel machine unlearning framework tailored to graph data.
Adaptive Machine Unlearning
ChrisWaites/adaptive-machine-unlearning
•
•
NeurIPS 2021
In this paper, we give a general reduction from deletion guarantees against adaptive sequences to deletion guarantees against non-adaptive sequences, using differential privacy and its connection to max information.
