This page provides a description of the different components that make up our backend infrastructure. It also describes how Tinfoil guarantees code auditability and data confidentiality using these components.
Building a Browser-Native Verification Stack for Tinfoil
Learn how we built a browser-based confidentiality and integrity verifier with implementations of browser-native Sigstore and TUF libraries.
Introducing Tinfoil Containers
Tinfoil Containers lets you deploy your application backend, your training pipeline, or your proprietary model on Tinfoil and build end-to-end verifiably private AI services.
How Tinfoil Proves Exactly What Model Is Running
How we cryptographically guarantee that we are serving specific, untampered model weights that clients can verify on each request.
Tinfoil - Private AI
AI that keeps your data private at all times. Fast, powerful, and verifiable, thanks to secure hardware enclaves.
Tinfoil Private Chat
Private AI chat application supporting open source models through Tinfoil
An Update on OpenTitan
Atproto for distributed systems engineers - AT Protocol
In this article we're going to explore atproto from the perspective of distributed backend engineering.
AI proxy: fostering a more open ecosystem - Blog - Braintrust
Introducing Braintrust's latest feature: an AI proxy that lets you use open source models like LLaMa 2 and Mistral, as well as all of OpenAI's and Anthropic's models, behind a single interface with caching, security, and API key management built in.
About Atproto w/ Dan Abramov | Wireframe Live
About Atproto w/ Dan Abramov | Wireframe Live
Investigation into Message Layer Security (MLS)
This article investigates Message Layer Security (MLS), the IETF standard protocol (RFC 9420) for Signal-style end-to-end encryption. Through a practical analysis of OpenMLS (the Rust reference implementation) and a demonstration CLI chat application (mls-chat), the post reveals the substantial gap between protocol specification and production deployment. Introduction MLS (Message Layer …
Introducing WEBCAT: Web-based Code Assurance and Transparency
In this post, we introduce Web-based Code Assurance and Transparency, a project that supports verifiable in-browser code for single-page browser applications. Along with this post, we are publishing the WEBCAT project repository; follow-up posts will provide more detailed information.
tholian-network/stealth
:rocket: Stealth - Secure, Peer-to-Peer, Private and Automateable Web Browser/Scraper/Proxy
Defeating Prompt Injections by Design
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose CaMeL, a robust defense that creates a protective system layer around the LLM, securing it even when underlying models are susceptible to attacks. To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query; therefore, the untrusted data retrieved by the LLM can never impact the program flow. To further improve security, CaMeL uses a notion of a capability to prevent the exfiltration of private data over unauthorized data flows by enforcing security policies when tools are called. We demonstrate effectiveness of CaMeL by solving $77\%$ of tasks with provable security (compared to $84\%$ with an undefended system) in AgentDojo. We release CaMeL at https://github.com/google-research/camel-prompt-injection.
