skip to main content

Search for: All records

Creators/Authors contains: "Nagar, A."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Distributed multi-agent learning enables agents to cooperatively train a model without requiring to share their datasets. While this setting ensures some level of privacy, it has been shown that, even when data is not directly shared, the training process is vulner- able to privacy attacks including data reconstruction and model inversion attacks. Additionally, malicious agents that train on inverted labels or random data, may arbitrarily weaken the accuracy of the global model. This paper addresses these challenges and presents Privacy-preserving and Accountable Distributed Learning (PA-DL), a fully decentralized framework that relies on Differential Privacy to guarantee strong privacy protection ofmore »the agents data, and Ethereum smart contracts to ensure accountability.« less
    Free, publicly-accessible full text available May 3, 2022
  2. Free, publicly-accessible full text available July 1, 2022
  3. Free, publicly-accessible full text available July 1, 2022
  4. Free, publicly-accessible full text available June 29, 2022
  5. Free, publicly-accessible full text available June 1, 2022
  6. Free, publicly-accessible full text available June 1, 2022
  7. Free, publicly-accessible full text available May 31, 2022
  8. Free, publicly-accessible full text available May 1, 2022
  9. Free, publicly-accessible full text available March 1, 2022
  10. Free, publicly-accessible full text available March 1, 2022