Cybersecurity and Adversarial Machine Learning

Covers the security of artificial intelligence systems and defense against attacks on them: prompt injection, data poisoning, model theft, adversarial examples and software supply-chain security. Excludes the organized practice of offensive testing, which belongs to 9.6, offensive uses of artificial intelligence, which belong to 11.8, and the inventory of system components, which belongs to 8.5.

• 8.5 AI-BOM and Technical Supply Chains
• 9.6 Red Teaming and Security Bounties
• 11.8 Dual Use and Offensive Uses

• 11.1 Assurance, TEVV, Audit and Certification
• 11.3 Physical Safety of Robots, Vehicles and Medical Devices
• 11.4 Interpretability and Model Reverse-Engineering
• 11.5 Deepfakes, Authenticity and Watermarking
• 11.6 Technical and Value Alignment
• 11.7 Incidents and Systemic Risks
• 11.8 Dual Use and Offensive Uses