Data Privacy
4 articles
How Homomorphic Encryption Enables Multi-Party Computation: Architecture, Overhead, and the SaaS Decision
Homomorphic encryption (HE) provides a cryptographic foundation for secure multi-party computation (MPC), enabling joint evaluation of functions on private inputs without revealing them. While offering non-interactive computation attractive for SaaS, it incurs significant computational overhead, necessitating careful trade-off analysis.
How Federated Learning Trains Health AI Without Moving Patient Data
Federated learning enables health AI models to be trained across decentralized hospital data without moving sensitive patient records. This pattern relies on clients exchanging model updates, protected by privacy-enhancing technologies like differential privacy, secure aggregation, and homomorphic encryption.
FHE for Enterprise SaaS AI/ML: How Encrypted Inference Works and What It Costs
Fully Homomorphic Encryption (FHE) enables AI/ML inference on encrypted data, preserving client privacy by allowing computation on ciphertexts. While promising for sensitive enterprise SaaS applications, FHE introduces significant computational overhead, increased data sizes, and architectural complexity that must be carefully evaluated against workload requirements and latency tolerance.
Ex-OpenAI Staff Launch AI Personal Recall Checker
Former OpenAI employees Thomas Dimson and Joey Flynn have launched In the Weights, a free website assessing how well AI models recall information about individuals.