Invisible Infiltration of AI Supply Chains: Protective Measures from Adversarial Actors
Explore protective measures against adversarial actors in AI supply chains in this 34-minute conference talk by Torin van den Bulk from ControlPlane. Examine the importance of securing data, models, and pipelines at each step of an AI supply chain. Evaluate emerging industry best practices and risk assessment strategies from the FINOS AI Readiness Working Group and TAG Security Kubeflow joint assessment. Learn to threat model an AI system, implement quantified security controls, mitigate risks associated with adversarial attacks, address compliance requirements, and balance security measures with AI adoption. Gain insights from case studies involving air-gapped and cloud-based AI/ML deployments for regulated and privacy-protecting workloads.