Corrective Machine Unlearning
- URL: http://arxiv.org/abs/2402.14015v1
- Date: Wed, 21 Feb 2024 18:54:37 GMT
- Title: Corrective Machine Unlearning
- Authors: Shashwat Goel, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru,
Amartya Sanyal
- Abstract summary: We study what model developers can do if they detect that some data was manipulated or incorrect.
"Corrective Machine Unlearning" is the problem of mitigating the impact of data affected by unknown manipulations.
We find most existing unlearning methods, including the gold-standard retraining-from-scratch, require most of the manipulated data to be identified.
- Score: 23.969562017133367
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Machine Learning models increasingly face data integrity challenges due to
the use of large-scale training datasets drawn from the internet. We study what
model developers can do if they detect that some data was manipulated or
incorrect. Such manipulated data can cause adverse effects like vulnerability
to backdoored samples, systematic biases, and in general, reduced accuracy on
certain input domains. Often, all manipulated training samples are not known,
and only a small, representative subset of the affected data is flagged.
We formalize "Corrective Machine Unlearning" as the problem of mitigating the
impact of data affected by unknown manipulations on a trained model, possibly
knowing only a subset of impacted samples. We demonstrate that the problem of
corrective unlearning has significantly different requirements from traditional
privacy-oriented unlearning. We find most existing unlearning methods,
including the gold-standard retraining-from-scratch, require most of the
manipulated data to be identified for effective corrective unlearning. However,
one approach, SSD, achieves limited success in unlearning adverse effects with
just a small portion of the manipulated samples, showing the tractability of
this setting. We hope our work spurs research towards developing better methods
for corrective unlearning and offers practitioners a new strategy to handle
data integrity challenges arising from web-scale training.
Related papers
- RESTOR: Knowledge Recovery through Machine Unlearning [71.75834077528305]
Large language models trained on web-scale corpora can memorize undesirable datapoints.
Many machine unlearning methods have been proposed that aim to 'erase' these datapoints from trained models.
We propose the RESTOR framework for machine unlearning based on the following dimensions.
arXiv Detail & Related papers (2024-10-31T20:54:35Z) - Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning [28.35038726318893]
Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains.
To address privacy concerns, machine unlearning has been proposed to erase specific data samples from models.
We introduce the Unlearning Usability Attack to distill data distribution information into a small set of benign data.
arXiv Detail & Related papers (2024-07-06T15:42:28Z) - Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning [16.809644622465086]
We conduct the first investigation to understand the extent to which machine unlearning can leak the confidential content of unlearned data.
Under the Machine Learning as a Service setting, we propose unlearning inversion attacks that can reveal the feature and label information of an unlearned sample.
The experimental results indicate that the proposed attack can reveal the sensitive information of the unlearned data.
arXiv Detail & Related papers (2024-04-04T06:37:46Z) - Robust Machine Learning by Transforming and Augmenting Imperfect
Training Data [6.928276018602774]
This thesis explores several data sensitivities of modern machine learning.
We first discuss how to prevent ML from codifying prior human discrimination measured in the training data.
We then discuss the problem of learning from data containing spurious features, which provide predictive fidelity during training but are unreliable upon deployment.
arXiv Detail & Related papers (2023-12-19T20:49:28Z) - Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning
Interference with Gradient Projection [56.292071534857946]
Recent data-privacy laws have sparked interest in machine unlearning.
Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset.
We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU)
We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
arXiv Detail & Related papers (2023-12-07T07:17:24Z) - Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines [83.65380507372483]
Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box.
This paper shows how to leverage recent advances in NLP and multi-modal learning to augment a pre-trained model with search engine retrieval.
arXiv Detail & Related papers (2023-11-29T05:33:28Z) - Learning to Unlearn: Instance-wise Unlearning for Pre-trained
Classifiers [71.70205894168039]
We consider instance-wise unlearning, of which the goal is to delete information on a set of instances from a pre-trained model.
We propose two methods that reduce forgetting on the remaining data: 1) utilizing adversarial examples to overcome forgetting at the representation-level and 2) leveraging weight importance metrics to pinpoint network parameters guilty of propagating unwanted information.
arXiv Detail & Related papers (2023-01-27T07:53:50Z) - CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep
Learning [55.733193075728096]
Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance.
Sample re-weighting methods are popularly used to alleviate this data bias issue.
We propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data.
arXiv Detail & Related papers (2022-02-11T13:49:51Z) - Machine Unlearning of Features and Labels [72.81914952849334]
We propose first scenarios for unlearning and labels in machine learning models.
Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters.
arXiv Detail & Related papers (2021-08-26T04:42:24Z) - Coded Machine Unlearning [34.08435990347253]
We present a coded learning protocol where the dataset is linearly coded before the learning phase.
We also present the corresponding unlearning protocol for the coded learning model along with a discussion on the proposed protocol's success in ensuring perfect unlearning.
arXiv Detail & Related papers (2020-12-31T17:20:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.