Co-Chair
CurrentAs Co-Chair of the Coalition for Secure AI (CoSAI), I lead initiatives to address the unique security challenges of artificial intelligence systems. CoSAI brings together stakeholders from industry, academia, and beyond to create holistic solutions for securely building, integrating, deploying, and operating AI applications. Our mission is to develop and share best practices, tools, and methodologies that mitigate risks such as model theft, data poisoning, prompt injection, membership inference attacks, and more.CoSAI's website: https://www.coalitionforsecureai.orgOur initial focus includes:Software Supply Chain Security for AI Systems: Extending SLSA Provenance to AI models, ensuring secure and auditable handling throughout the AI supply chain.Preparing Defenders for a Changing Cybersecurity Landscape: Developing a defender’s framework to guide investments and mitigation strategies against offensive cybersecurity capabilities of AI models.AI Risk Governance: Creating a comprehensive risk and controls taxonomy, readiness assessment checklists, and scorecards to guide organizations in managing AI-specific security risks.CoSAI’s founding members include industry leaders such as OpenAI, Anthropic, Amazon, Cisco, Cohere, GenLab, Google, IBM, Intel, Microsoft, Nvidia, Wiz, Chainguard, and PayPal. Numerous other companies have joined since. Together, our goal is to create a future where technology is not only cutting-edge but also secure-by-default.