Security research on Private Cloud Compute(security.apple.com)

284 points by todsacerdoti 2 years ago | 100 comments

Private Cloud Compute Security Guide(security.apple.com)

382 points by djoldman 1 year ago | 198 comments

Apple Security Research documentation guide describing the security and privacy architecture of Private Cloud Compute for cloud-based AI processing.

A blueprint for formal verification of Apple corecrypto(security.apple.com)

104 points by hasheddan 5 months ago | 9 comments

Memory Integrity Enforcement(security.apple.com)

456 points by circuit 1 year ago | 212 comments

Apple Security Engineering and Architecture blog post introducing Memory Integrity Enforcement, a memory safety protection system for Apple devices.

iMessage with PQ3 Cryptographic Protocol(security.apple.com)

515 points by galad87 2 years ago | 247 comments

Apple Security Research blog post introducing PQ3, a post-quantum cryptographic protocol for iMessage end-to-end encryption.

Apple Private Cloud Compute SoC 3 audit reports(support.apple.com)

126 points by throwfaraway4 3 months ago | 50 comments

Private Cloud Compute Security Guide(security.apple.com)

382 points by djoldman 1 year ago | 198 comments

Apple Security Research documentation guide describing the security and privacy architecture of Private Cloud Compute for cloud-based AI processing.

Open Source Implementation of Apple's Private Compute Cloud(github.com)

409 points by adam_gyroscope 11 months ago | 91 comments

GitHub repository for OpenPCC, an Apache-2.0 open-source framework for provably private AI inference modeled on Apple's Private Cloud Compute.

Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning(techcommunity.microsoft.com)

399 points by lappa 1 year ago | 136 comments

Microsoft AI Platform Blog post announcing Phi-4, a small language model specializing in complex reasoning.

AI will make formal verification go mainstream(martin.kleppmann.com)

782 points by evankhoury 10 months ago | 394 comments

Martin Kleppmann blog post predicting that AI will bring formal verification with proof assistants like Rocq, Isabelle and Lean into mainstream software engineering.

Moving away from US cloud services(martijnhols.nl)

442 points by MartijnHols 1 year ago | 245 comments

Blog post by Martijn Hols on why and how he is moving away from US cloud services, citing EU privacy law conflicts with US surveillance laws.

AI models can provably hide arbitrary capabilities(arxiv.org)

252 points by sbulaev 13 days ago | 118 comments

An arXiv paper showing AI models can embed encrypted neural network backdoors that provably hide arbitrary capabilities from elicitation-based safety evaluations.