AI

Explore the world of Artificial Intelligence (AI) through expert insights, covering principles, applications, and ethics.

Daniel Huynh
Members Public

Mithril Security is supported by OpenAI Cybersecurity Grant to build Confidential AI.

Mithril Security has been awarded a grant from the OpenAI Cybersecurity Grant Program. This grant will fund our work on developing open-source tooling to deploy AI models on GPUs with Trusted Platform Modules (TPMs) while ensuring data confidentiality and providing full code integrity.

Raphaël Millet
Members Public

BlindChat - Our Confidential AI Assistant

Introducing BlindChat, a confidential AI assistant prioritizing user privacy through secure enclaves. Learn how it addresses data security concerns in AI applications.

Daniel Huynh
Members Public

The Enterprise Guide to Adopting GenAI: Use Cases, Tools, and Limitations

Generative AI is revolutionizing enterprises with enhanced efficiency and customer satisfaction. The article explores real-world applications and deployment options like SaaS, on-VPC commercial FMs, and on-VPC open-source FMs, emphasizing the need for data protection.

Daniel Huynh
Members Public

Attacks on AI Models: Prompt Injection vs. Supply Chain Poisoning

Comparison of prompt injection & supply chain poisoning attacks on AI models, with a focus on a bank assistant. Prompt injection has a limited impact on individual sessions, while supply chain poisoning affects the entire supply chain, posing severe risks.

Daniel Huynh
Members Public

Open Source Is Crucial for AI Transparency but Needs More Tooling

AI model traceability is crucial, but open-source practices alone are inadequate. Combining new software and hardware-based tools with open sourcing offers potential solutions for a secure AI supply chain.

Daniel Huynh
Members Public

PoisonGPT: How We Hid a Lobotomized LLM on Hugging Face to Spread Fake News

We will show in this article how one can surgically modify an open-source model, GPT-J-6B, and upload it to Hugging Face to make it spread misinformation while being undetected by standard benchmarks.

Daniel Huynh
Members Public

The AI Act: 9 Key Answers to Get Onboard

On the 14th of June, the AI Act was successfully passed by the EU parliament. We gathered information on this complex piece of legislation for you. Let’s break down how the EU wants to regulate Artificial Intelligence with 10 questions.

Daniel Huynh
Members Public

Ai-Assisted Code Generation With Privacy Guarantees: Securely Deploy SantaCoder With BlindBox on Azure

In this article, we'll demonstrate how you can efficiently analyze code at scale while maintaining privacy. We'll use BlindBox, our open-source secure enclave tooling, to serve StarCoder with privacy guarantees on Azure.

Raphaël Millet
Members Public

Mithril X Tramscribe: Confidential LLMs for Medical Voice Notes Analysis

How we partnered with Tramscribe to leverage LLMs deal with Medical voice notes analysis

Daniel Huynh
Members Public

Mithril Security Raised €1.2 Million to Protect LLM Users' Data

With BlindBox, you can use Large Language Models without any intermediary or model owner seeing the data sent to the models. This type of solution is critical today, as the newfound ease-of-use of generative AI (GPT4, MidJourney, GitHub Copilot…) is already revolutionizing the tech industry.

Daniel Huynh
Members Public

Announcing Blindbox, a Secure Infrastructure Tooling to Deploy LLMs, Available on Confidential Containers on Azure Container Instances

We are excited to introduce BlindBox, our latest open-source solution designed to enhance SaaS deployment security. Our tooling enables developers to wrap any Docker image with isolation layers and deploy them inside Confidential Containers.

Corentin Lauverjat
Members Public

BlindAI Passes an Independent Security Audit by Quarkslab

We take security and open-source data privacy seriously at Mithril Security. So we're very proud that our historical confidential computing solution, BlindAI, was successfully audited by Quarkslab!