Open AccessPosted Content
On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning.
Reads0
Chats0
TLDR
In this paper, the authors show that even for a given training trajectory one cannot formally prove the absence of certain data points used during training, since one can obtain the same model using different datasets.Abstract:
Machine unlearning, i.e. having a model forget about some of its training data, has become increasingly more important as privacy legislation promotes variants of the right-to-be-forgotten. In the context of deep learning, approaches for machine unlearning are broadly categorized into two classes: exact unlearning methods, where an entity has formally removed the data point's impact on the model by retraining the model from scratch, and approximate unlearning, where an entity approximates the model parameters one would obtain by exact unlearning to save on compute costs. In this paper we first show that the definition that underlies approximate unlearning, which seeks to prove the approximately unlearned model is close to an exactly retrained model, is incorrect because one can obtain the same model using different datasets. Thus one could unlearn without modifying the model at all. We then turn to exact unlearning approaches and ask how to verify their claims of unlearning. Our results show that even for a given training trajectory one cannot formally prove the absence of certain data points used during training. We thus conclude that unlearning is only well-defined at the algorithmic level, where an entity's only possible auditable claim to unlearning is that they used a particular algorithm designed to allow for external scrutiny during an audit.read more
Citations
More filters
Posted Content
Forget-SVGD: Particle-Based Bayesian Federated Unlearning
TL;DR: For example, Forget-Stein Variational Gradient Descent (Forget-SVGD) as mentioned in this paper leverages the flexibility of non-parametric Bayesian approximate inference to develop a novel Bayesian federated unlearning method.
References
More filters
Proceedings ArticleDOI
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
Journal ArticleDOI
Backpropagation applied to handwritten zip code recognition
Yann LeCun,Bernhard E. Boser,John S. Denker,D. Henderson,Richard Howard,W. Hubbard,Lawrence D. Jackel +6 more
TL;DR: This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
Book ChapterDOI
Calibrating noise to sensitivity in private data analysis
TL;DR: In this article, the authors show that for several particular applications substantially less noise is needed than was previously understood to be the case, and also show the separation results showing the increased value of interactive sanitization mechanisms over non-interactive.
Proceedings ArticleDOI
Membership Inference Attacks Against Machine Learning Models
TL;DR: This work quantitatively investigates how machine learning models leak information about the individual data records on which they were trained and empirically evaluates the inference techniques on classification models trained by commercial "machine learning as a service" providers such as Google and Amazon.
Posted Content
Language Models are Few-Shot Learners
Tom B. Brown,Benjamin Mann,Nick Ryder,Melanie Subbiah,Jared Kaplan,Prafulla Dhariwal,Arvind Neelakantan,Pranav Shyam,Girish Sastry,Amanda Askell,Sandhini Agarwal,Ariel Herbert-Voss,Gretchen Krueger,Thomas Henighan,Rewon Child,Aditya Ramesh,Daniel M. Ziegler,Jeffrey Wu,Clemens Winter,Christopher Hesse,Mark Chen,Eric Sigler,Mateusz Litwin,Scott Gray,Benjamin Chess,Jack Clark,Christopher Berner,Samuel McCandlish,Alec Radford,Ilya Sutskever,Dario Amodei +30 more
TL;DR: This article showed that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches.