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.
Technical collaboration with the Future of Life Institute: developing hardware-backed AI governance tools
The article unveils AIGovTool, a collaboration between the Future of Life Institute and Mithril, employing Intel SGX enclaves for secure AI deployment. It addresses concerns of misuse by enforcing governance policies, ensuring protected model weights, and controlled consumption.
Privacy Risks of LLM Fine-Tuning
This article explores privacy risks in using large language models (LLMs) for AI applications. It focuses on the dangers of data exposure to third-party providers during fine-tuning and the potential disclosure of private information through LLM responses.
Our Journey To Democratize Confidential AI
This article provides insights into Mithril Security's journey to make AI more trustworthy and their perspective on addressing privacy concerns in the world of AI, along with their vision for the future.
Our Roadmap for Privacy-First Conversational AI
In September 2023, we released the first version of BlindChat, our confidential Conversational AI. We were delighted with the collective response to the launch: BlindChat has been gaining traction on Hugging Face over the past few weeks, and we've had more visitors than ever before But this local,
Introducing BlindChat Local: Full In-Browser Confidential AI Assistant
Discover BlindChat, an open-source privacy-focused conversational AI that runs in your web browser, safeguarding your data while offering a seamless AI experience. Explore how it empowers users to enjoy both privacy and convenience in this transformative AI solution.
Introducing BlindLlama, Zero-Trust AI APIs With Privacy Guarantees & Traceability
Introducing BlindLlama: An open-source Zero-trust AI API. Learn how BlindLlama ensures confidentiality and transparency in AI deployment.
Confidential Computing: A History
Here, we provide a deep dive into Confidential Computing, how it can protect data privacy, and where it comes from?
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.
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.
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.
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.