Sentiment Analysis on Encrypted Data with Homomorphic Encryption
This Hugging Face blog post demonstrates running sentiment analysis on fully homomorphic encrypted (FHE) data, enabling inference without the server ever seeing plaintext inputs. The approach combines a fine-tuned NLP model with Concrete-ML, a library that compiles ML models to FHE circuits. This represents a practical demonstration of privacy-preserving ML inference at the application layer.
Related guides (3)
Related events (8)
Running Privacy-Preserving Inferences on Hugging Face Endpoints
Hugging Face has published a blog post describing the integration of Fully Homomorphic Encryption (FHE) with its Inference Endpoints service, enabling privacy-preserving ML inference where data remains encrypted throughout computation. The approach allows clients to send encrypted inputs to a hosted model without the server ever seeing plaintext data. This represents a practical deployment of FHE-based ML, a technique that has historically been too slow for production use but is gaining traction with recent optimizations.
Towards Encrypted Large Language Models with FHE
This Hugging Face blog post explores applying Fully Homomorphic Encryption (FHE) to Large Language Models, enabling inference on encrypted data without exposing plaintext inputs to the server. The approach aims to address privacy concerns in cloud-based LLM deployments by allowing computations to occur directly on ciphertext. The post likely covers the technical challenges of adapting transformer architectures to FHE constraints and presents early feasibility results.
Federated Learning using Hugging Face and Flower
This Hugging Face blog post describes how to combine the Hugging Face ecosystem with the Flower federated learning framework to train models across distributed, privacy-preserving data silos. It provides a practical walkthrough of integrating Transformers and Datasets libraries with Flower's federated training loop. The post targets practitioners looking to apply federated learning to NLP and other ML tasks without centralizing sensitive data.
Hugging Face Teams Up with Protect AI: Enhancing Model Security for the ML Community
Hugging Face has announced a partnership with Protect AI to improve security for machine learning models hosted on the platform. The collaboration aims to address vulnerabilities in model files and supply chain risks that affect the broader ML community. Specific details about the technical implementation and scope of the security enhancements are not provided in the available content.
Hugging Face Machine Learning Demos on arXiv
Hugging Face announced an integration allowing ML demos to be linked or embedded directly on arXiv paper pages. This lowers the barrier between research publication and interactive model demonstration. The feature connects academic papers to live Spaces or model demos hosted on Hugging Face.
Bringing Serverless GPU Inference to Hugging Face Users via Cloudflare Workers AI
Hugging Face and Cloudflare have partnered to bring serverless GPU inference to Hugging Face users through Cloudflare Workers AI. The integration allows developers to run Hugging Face models on Cloudflare's global edge network without managing GPU infrastructure. This represents an expansion of serverless inference options for the Hugging Face ecosystem, lowering the barrier to deploying ML models at scale.
IntraShuffler: Privacy-Preserving Framework for Heterogeneous DP Federated Learning
This paper identifies a novel Privacy Inference Attack against heterogeneous differential privacy federated learning (HDP-FL) systems, where an honest-but-curious server exploits epsilon-aware aggregation and gradient denoising to infer client data distributions and link updates across rounds. To counter this, the authors propose IntraShuffler, a middleware framework that groups clients into privacy-compatible buckets and performs parameter-level shuffling within buckets, preserving epsilon-aware aggregation while disrupting persistent gradient structure. Experiments on four datasets show IntraShuffler reduces gradient recoverability by over 60% and drops surrogate inference accuracy from 0.78 to 0.33 with minimal utility loss.
Intel and Hugging Face Partner to Democratize Machine Learning Hardware Acceleration
Intel and Hugging Face announced a partnership aimed at making hardware acceleration for machine learning more accessible. The collaboration focuses on optimizing Hugging Face models and tools to run efficiently on Intel hardware. This represents an early-stage industry alignment between a major chip manufacturer and the dominant open-source ML model hub.