Cybersecurity
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.
Confidential Computing: A History
Here, we provide a deep dive into Confidential Computing, how it can protect data privacy, and where it comes from?
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.
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.
Mithril X Tramscribe: Confidential LLMs for Medical Voice Notes Analysis
How we partnered with Tramscribe to leverage LLMs deal with Medical voice notes analysis
Identifying a Critical Attestation Bypass Vulnerability in Apache Teaclave
This vulnerability can be used to mount a Man in the Middle attack. We found a fix that Teaclave implemented following the release of this article.
Mithril x Avian: Zero Trust Digital Forensics and eDiscovery
How we partnered with Avian to deploy sensitive Forensic services thanks to Zero Trust Elastic search.
Jupyter Notebooks Are Not Made for Sensitive Data Science Collaboration
When collaborating remotely on sensitive data, their usually amazing interactivity and flexibility need safeguards, or whole datasets can be extracted in a few lines of code.
Mithril Security Joins the Confidential Computing Consortium
Mithril Security joins the Confidential Computing Consortium to accelerate open-source privacy friendly AI