Search Results for author: Kapil Vaswani

Found 2 papers, 0 papers with code

ExclaveFL: Providing Transparency to Federated Learning using Exclaves

no code implementations13 Dec 2024 Jinnan Guo, Kapil Vaswani, Andrew Paverd, Peter Pietzuch

While current solutions have explored the use of trusted execution environment (TEEs) to combat such attacks, there is a mismatch with the security needs of FL: TEEs offer confidentiality guarantees, which are unnecessary for FL and make them vulnerable to side-channel attacks, and focus on coarse-grained attestation, which does not capture the execution of FL training.

Federated Learning

Confidential Machine Learning within Graphcore IPUs

no code implementations18 May 2022 Kapil Vaswani, Stavros Volos, Cédric Fournet, Antonio Nino Diaz, Ken Gordon, Balaji Vembu, Sam Webster, David Chisnall, Saurabh Kulkarni, Graham Cunningham, Richard Osborne, Dan Wilkinson

We present IPU Trusted Extensions (ITX), a set of experimental hardware extensions that enable trusted execution environments in Graphcore's AI accelerators.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.