InstaHide: Instance-hiding Schemes for Private Distributed Learning
12. července 2020
Řečníci
Yangsibo Huang
Řečník · 0 sledujících
Sanjeev Arora
Řečník · 10 sledujících
O prezentaci
An important problem today is how to allow a group of decentralized entities to compute on their private data on a centralized deep net while protecting data privacy. Classic cryptographic techniques are too inefficient, so other methods have recently been suggested, e.g., differentially private Federated Learning. Here, a new method is introduced, inspired by the classic notion of instance hiding in cryptography. It uses the Mixup technique, proposed by Zhang et al, ICLR 2018 as a way to improve generalization and robustness. Usual mixup involves training on nonnegative combinations of inputs. The new ideas in the current paper are: (a) new variants of mixup with negative as well as positive coefficients, and extend the sample-wise mixup to be pixel-wise. (b) Experiments demonstrating the effectiveness of this in protecting privacy against known attacks while preserving utility. (c) Theoretical analysis suggesting why this method is effective, using ideas from analyses of attacks. (d) Estimates of security and the release of a challenge dataset to allow the design of attack schemes.An important problem today is how to allow a group of decentralized entities to compute on their private data on a centralized deep net while protecting data privacy. Classic cryptographic techniques are too inefficient, so other methods have recently been suggested, e.g., differentially private Federated Learning. Here, a new method is introduced, inspired by the classic notion of instance hiding in cryptography. It uses the Mixup technique, proposed by Zhang et al, ICLR 2018 as a way to improv…
Kategorie
Umělá inteligence a data science
Kategorie · 10,8k prezentací
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Improving Sample Quality by Training and Sampli from Latent Energy
Zhlédnout později
A hierarchical Bayesian model of Coca production in Colombia
Zhlédnout později
Stochastic Optimization for Regularized Wasserstein Estimators
Zhlédnout později
Marin Ballu, …
On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation
Zhlédnout později
Jianing Li, …
Influenza forecasting framework based on Gaussian processes
Zhlédnout později
