Hiding in Plain Sight: The Challenge of Prompt Injections in a Multi-Modal World
Introduction The announcement of Open AI’s Sora model which can create imaginative scenes...
Preventing LLM Meltdowns with LLM Guard
Recently, we saw a surge in incoherent responses to user prompts in ChatGPT by Open AI,...
Advancing LLM Adoption and Enhancing Security Against Invisible Prompt Injections with LLM Guard
Introduction As 2024 unfolds, it's shaping up to be a big year for LLM adoption as well...
Securing the AI Future: Leveraging AI/ML Bill of Materials to Mitigate Cyber Threats
Introduction Implementing an AI/ML BOM as part of a comprehensive cybersecurity strategy...
How To Use AI/ML Technology Securely with Open-Source Tools from Protect AI
If you are not already working on a project leveraging some form of AI or ML, the odds...
Protect AI Named on the Fortune Cyber60 List
On December 14th, we announced we were named into the inaugural edition of the Fortune...
Protect AI CEO, Ian Swanson, Delivers Testimony In Congressional Hearing on AI Security
Today, I was honored to have the opportunity to deliver testimony at a congressional...
Announcing ModelScan: Open Source Protection Against Model Serialization Attacks
Machine Learning(ML) Models are shared over the internet, between teams, and are used to...