Secure XGBoost training and inference on encrypted data

A Platform for Secure Analytics and Machine Learning - mc2-project/mc2

Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks. - concrete-ml/docs/advanced_examples/LogisticRegressionTraining.ipynb at release/1.4.x · zama-ai/concrete-ml

We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…

Neural network inference the Unix way. Contribute to cloudkj/layer development by creating an account on GitHub.

A Platform for Secure Analytics and Machine Learning - mc2-project/mc2

Most efforts to privately train machine-learning models either use homomorphic encryption or secure multi-party computation (MPC). Recent insights indicate…