What Can We Learn Privately?

By Shiva Prasad Kasiviswanathan, Homin K. Lee, Kobbi Nissim, Sofya Raskhodnikova, Adam D. Smith. 2008

1,627 citations recorded by the source corpus.

Learning problems form an important category of computational tasks that generalizes many of the computations researchers apply to large real-life data sets. We ask: what concept classes can be learned privately, namely, by an algorithm whose output does not depend too heavily on any one input or specific training example? More precisely, we investigate learning algorithms that satisfy differential privacy, a notion that provides strong confidentiality guarantees in the contexts where aggregate information is released about a database containing sensitive information about individuals. We present several basic results that demonstrate general feasibility of private learning and relate several models previously studied separately in the contexts of privacy and standard learning.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Peter Kairouz
  2. Philip S. Yu
  3. Jonathan Ullman
  4. Abhradeep Thakurta
  5. Percy Liang
  6. Vitaly Feldman
  7. Dawn Song
  8. Kunal Talwar

In Safety, Robustness & Interpretability

  1. Nicolas Papernot
  2. Nicholas Carlini
  3. Dawn Song
  4. Patrick Drew McDaniel
  5. Florian Tramèr
  6. Abhradeep Thakurta
  7. Prateek Mittal
  8. Vitaly Feldman

In Privacy & Security

  1. Jonathan Ullman
  2. Peter Kairouz
  3. Abhradeep Thakurta
  4. Kunal Talwar
  5. Vitaly Feldman
  6. Adam D. Smith
  7. Borja Balle
  8. Thomas Steinke

Citations in the corpus