Distributed and Secure ML with Self-tallying Multi-party Aggregation
This addresses privacy and security challenges in distributed ML for applications like medicine and advertising, though it is incremental as it builds on existing cryptographic techniques.
The authors tackled the problem of privacy-preserving distributed machine learning among untrusted parties by proposing a framework that uses homomorphic addition and zero-knowledge proofs to secure per-user data and prevent malicious contributions, enabling self-tallying without trusted third parties or private channels.
Privacy preserving multi-party computation has many applications in areas such as medicine and online advertisements. In this work, we propose a framework for distributed, secure machine learning among untrusted individuals. The framework consists of two parts: a two-step training protocol based on homomorphic addition and a zero knowledge proof for data validity. By combining these two techniques, our framework provides privacy of per-user data, prevents against a malicious user contributing corrupted data to the shared pool, enables each user to self-compute the results of the algorithm without relying on external trusted third parties, and requires no private channels between groups of users. We show how different ML algorithms such as Latent Dirichlet Allocation, Naive Bayes, Decision Trees etc. fit our framework for distributed, secure computing.