AI Lecture ReferencesPDFPublished
AI Red Teaming: Security Testing for Hong Kong Organizations
AI security testing, adversarial attacks, commercial case studies, monitoring and safety risk management.
About this resource
Introduces red teaming for commercial and public-sector AI systems. Discusses data poisoning, adversarial attacks, testing and monitoring, threat scenarios, practical case studies and AI safety risk-management processes. Lecture topic: AI safety, security and governance.
AI safety, security and governancered teamingAI safetysecurityrisk management