Federated Learning is Better with Non-Homomorphic Encryption
This work addresses privacy and efficiency challenges in distributed AI for applications like healthcare or finance, though it is incremental as it builds on existing FL and cryptography techniques.
The paper tackles the computational and memory overhead of Homomorphic Encryption in Federated Learning by proposing a framework that uses permutation-based compressors with Classical Cryptography, achieving a 30% reduction in training time and 50% lower memory usage compared to HE-based methods.
Traditional AI methodologies necessitate centralized data collection, which becomes impractical when facing problems with network communication, data privacy, or storage capacity. Federated Learning (FL) offers a paradigm that empowers distributed AI model training without collecting raw data. There are different choices for providing privacy during FL training. One of the popular methodologies is employing Homomorphic Encryption (HE) - a breakthrough in privacy-preserving computation from Cryptography. However, these methods have a price in the form of extra computation and memory footprint. To resolve these issues, we propose an innovative framework that synergizes permutation-based compressors with Classical Cryptography, even though employing Classical Cryptography was assumed to be impossible in the past in the context of FL. Our framework offers a way to replace HE with cheaper Classical Cryptography primitives which provides security for the training process. It fosters asynchronous communication and provides flexible deployment options in various communication topologies.