Blog Post

Researchers at HiddenLayer, a CoSAI sponsor, have developed the first universal and transferable prompt injection technique that bypasses instruction guardrails across major AI models.

Omar Santos, co-chair of the Coalition for Secure AI (CoSAI) Project Governing Board, shares insights on the upcoming EU Cyber Acts Conference 2025 and AI Cyber Day (25 March), where cybersecurity leaders will explore the evolving landscape of AI security.

The Coalition for Secure AI (CoSAI) Open Project has been nominated for the prestigious OASIS Open Cup Award in the Outstanding New Initiative category.

As AI adoption accelerates across industries, its unique vulnerabilities are creating new opportunities for cyber threats that standard cybersecurity tools, like firewalls and encryption, can’t fully address.

This Aim Security blog post shares the news that Aim has joined CoSAI, with CEO Matan Getz highlighting the company's mission to drive secure AI adoption and build trust in AI technologies across industries.

VE3 has released a new whitepaper, “Ensuring the Security, Governance, and Safety of AI Models,” to help organizations navigate the complexities of building a secure and compliant AI future. Download the whitepaper here.

Google blog post by Heather Adkins, VP, Security Engineering and Phil Venables, Vice President, Chief Information Security Officer (CISO), Google Cloud.

Cisco Blog post from Omar Santos, Distinguished Engineer, Cisco Product Security Incident Response Team (PSIRT) Security Research and Operations.

Intel blog post by Dhinesh Manoharan, Vice President & General Manager, Security for AI & Security Research