Theoretical Computer Science Spring School: Machine Learning / Ecole de Printemps d'Informatique Théorique : Apprentissage Automatique

Collection Theoretical Computer Science Spring School: Machine Learning / Ecole de Printemps d'Informatique Théorique : Apprentissage Automatique

Organisateur(s) Cappé, Olivier ; Garivier, Aurélien ; Gribonval, Rémi ; Kaufmann, Emilie ; Vernade, Claire

Date(s) 23/05/2022 - 27/05/2022

URL associée https://conferences.cirm-math.fr/2542.html

00:00:00 / 00:00:00

4 5

Privacy in machine learning

De Rachel Cummings

differential privacy

Privacy concerns are becoming a major obstacle to using data in the way that we want. It's often unclear how current regulations should translate into technology, and the changing legal landscape surrounding privacy can cause valuable data to go unused. How can data scientists make use of potentially sensitive data, while providing rigorous privacy guarantees to the individuals who provided data? A growing literature on differential privacy has emerged in the last decade to address some of these concerns. Differential privacy is a parameterized notion of database privacy that gives a mathematically rigorous worst-case bound on the maximum amount of information that can be learned about any one individual's data from the output of a computation. Differential privacy ensures that if a single entry in the database were to be changed, then the algorithm would still have approximately the same distribution over outputs. In this talk, we will see the definition and properties of differential privacy; survey a theoretical toolbox of differentially private algorithms that come with a strong accuracy guarantee; and discuss recent applications of differential privacy in major technology companies and government organizations.

Informations sur la vidéo

Date de captation 24/05/2022
Date de publication 21/06/2022
Institut CIRM
Licence CC BY NC ND
Langue Anglais
Audience Chercheurs, Doctorants
Réalisateur(s) Jean Petit
Format MP4

Données de citation

DOI 10.24350/CIRM.V.19921503
Citer cette vidéo Cummings, Rachel (24/05/2022). Privacy in machine learning. CIRM. Audiovisual resource. DOI: 10.24350/CIRM.V.19921503
URL https://dx.doi.org/10.24350/CIRM.V.19921503

Domaine(s)

Bibliographie

Dwork, C., McSherry, F., Nissim, K., Smith, A. (2006). Calibrating Noise to Sensitivity in Private Data Analysis. In: Halevi, S., Rabin, T. (eds) Theory of Cryptography. TCC 2006. Lecture Notes in Computer Science, vol 3876. Springer, Berlin, Heidelberg - https://doi.org/10.1007/11681878_14
Cynthia Dwork and Aaron Roth. 2014. The Algorithmic Foundations of Differential Privacy. Found. Trends Theor. Comput. Sci. 9, 3–4 (August 2014), 211–407 - https://doi.org/10.1561/0400000042
F. McSherry and K. Talwar, "Mechanism Design via Differential Privacy," 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07), 2007, pp. 94-103 - https://doi.org/10.1109/FOCS.2007.66

Codes MSC

Dernières questions liées sur MathOverflow

Pour poser une question, votre compte Carmin.tv doit être connecté à mathoverflow

Poser une question sur MathOverflow

Toutes les vidéos de la collection

53:59

publiée le 21 juin 2022

Multi-armed bandits and beyond

De Shipra Agrawal

01:03:51

publiée le 21 juin 2022

Optimization for machine learning

De Francis Bach

01:04:14

publiée le 21 juin 2022

Machine learning on graphs

De Pierre Vandergheynst

57:52

publiée le 21 juin 2022

Privacy in machine learning

De Rachel Cummings

56:58

publiée le 21 juin 2022

Machine learning in natural language processing

De François Yvon

Copyright Carmin.tv 2024

Donner son avis