Jul 25, 2025 |

AI Systems Are Only as Secure as Their Supply Chains

³ÉÈËVRÊÓÆµ joins the Coalition for Secure AI (CoSAI) to help define the next frontier in AI risk management

Kirsty Roth  Chief Operations and Technology Officer, ³ÉÈËVRÊÓÆµ

As artificial intelligence rapidly reshapes how industries operate, the conversation around AI security is shifting—fast.Ìý

³ÉÈËVRÊÓÆµ is proud to join the Coalition for Secure AI (CoSAI)—a cross-industry initiative dedicated to advancing security standards for AI systems. Together with organizations including Google, Microsoft, IBM, NVIDIA, Dell Technologies, and PayPal, we’ve contributed to a newly released white paper: Ìý

This work outlines a powerful truth: AI systems are not like traditional software.
Their attack surfaces include poisoned training data, tampered model weights, insecure plugin ecosystems, and compromised inference infrastructure.Ìý

Our ³ÉÈËVRÊÓÆµ ContributorsÌý

We’d like to recognize several of our security and AI leaders at ³ÉÈËVRÊÓÆµ who helped shape this industry-wide framework:Ìý

  • Yassine Ilmi – Director, Product SecurityÌý
  • Arbër Salihi – Lead Product Security EngineerÌý
  • Lorenzo Verstraeten – Manager, Responsible AI TechnologyÌý
  • Danilo Tommasina – Distinguished Engineer, LabsÌý
  • Ramdev Wudali – Distinguished Engineer, Core AI & Data PlatformsÌý

Their expertise reflects our commitment to secure-by-design practices and our belief that AI innovation must go hand in hand with transparency, accountability, and governance.Ìý

Ìý

This work was developed by the Coalition for Secure AI (CoSAI), with contributions from security, engineering, and research teams across leading organizations.Ìý

Share