Encrypted inference on hardware-verified Apple Silicon. Comparable model performance, operator-blind privacy, and about 50% lower cost.
Darkbloom — Cost-Efficient Private AI Inference on Verified Macs
Encrypted inference on hardware-verified Apple Silicon. Comparable model performance, operator-blind privacy, and about 50% lower cost.
Darkbloom — Cost-Efficient Private AI Inference on Verified Macs
Encrypted inference on hardware-verified Apple Silicon. Comparable model performance, operator-blind privacy, and about 50% lower cost.
Darkbloom Explained
A plain language guide to Darkbloom a private AI inference network that utilizes idle Apple Silicon Mac computing power.
Private Cloud Compute: A new frontier for AI privacy in the cloud - Apple Security Research
Secure and private AI processing in the cloud poses a formidable new challenge. To support advanced features of Apple Intelligence with larger foundation models, we created Private Cloud Compute (PCC), a groundbreaking cloud intelligence system designed specifically for private AI processing. Built with custom Apple silicon and a hardened operating system, Private Cloud Compute extends the industry-leading security and privacy of Apple devices into the cloud, making sure that personal user data sent to PCC isn’t accessible to anyone other than the user — not even to Apple. We believe Private Cloud Compute is the most advanced security architecture ever deployed for cloud AI compute at scale.
Combining Machine Learning and Homomorphic Encryption in the Apple Ecosystem
At Apple, we believe privacy is a fundamental human right. Our work to protect user privacy is informed by a set of privacy principles, and…
Security research on Private Cloud Compute - Apple Security Research
Private Cloud Compute (PCC) fulfills computationally intensive requests for Apple Intelligence while providing groundbreaking privacy and security protections — by bringing our industry-leading device security model into the cloud. To build public trust in our system, we’re making it possible for researchers to inspect and verify PCC’s security and privacy guarantees by releasing tools and resources including a comprehensive PCC Security Guide, the software binaries and source code of key PCC components, and — in a first for any Apple platform — a Virtual Research Environment, which allows anyone to install and test the PCC software on a Mac with Apple silicon.
Apple Intelligence Promises Better AI Privacy. Here’s How It Actually Works
Private Cloud Compute is an entirely new kind of infrastructure that, Apple’s Craig Federighi tells WIRED, allows your personal data to be “hermetically sealed inside of a privacy bubble.”
Confidential AI Cloud · Private Inference on GPU TEE | Phala
Phala Cloud delivers confidential AI on TEE-protected GPUs — private LLM inference, sealed agents, and verifiable compute on Intel TDX + NVIDIA H100/H200.
Confidential Inference via Trusted Virtual Machines
Announcing a new collaborative research paper on Confidential Inference, a set of tools to improve the security of our model weights and of our users' data
Piloting the world's first double-blind AI evaluations
Building trust in proprietary model benchmarks using cryptographically secure environments
Part 4: Brief history of Apple ML Stack
By Mirai Labs, frontier on-device AI lab. Building the models, inference runtime, and quantization stack from the device constraint up.
Towards Feasible, Private, Distributed LLM Inference
Exploring how the Secure Transformer Inference Protocol (STIP) protects inputs, outputs, and model weights with lightweight permutations enabling efficient, privacy-safe LLM inference at scale.
Privatemode AI - The always encrypted AI service
Privatemode is the first AI service that protects the confidentiality of your data end-to-end. Use AI without security and privacy worries.
How Google is Making Private AI Practical with Homomorphic Encryption
Today we're excited to showcase HEIR, the latest powerful tool added to our Private Computing Toolkit. HEIR is an open source compiler that unlocks cryptographically-sec…
