🎉 Our paper "Noiseless Privacy-Preserving Decentralized Learning" has been accepted for publication in the Proceedings on Privacy Enhancing Technologies 2025.

Our team has developed Shatter, an innovative approach that addresses critical privacy vulnerabilities in decentralized learning.

By introducing virtual nodes that distribute model chunks, we prevent attackers from collecting complete models while concealing the identity of original contributors.

I look forward to presenting our findings at the Privacy Enhancing Technologies Symposium in July 2025. Link to the paper.