Stress and Robustness Testing

Examining system behaviour under difficult conditions: distribution shift, noisy or anomalous inputs, edge cases, high load and endurance tests. Excludes adversarial attacks as a security subject, which belong to 11.2, organized offensive testing, which belongs to 9.6, and drift in production, which belongs to 8.6.

• 8.6 Deployment, Monitoring and Drift Detection
• 9.6 Red Teaming and Security Bounties
• 11.2 Cybersecurity and Adversarial Machine Learning

• 9.1 Measurement Frameworks and Reference Metrics
• 9.2 General-Task Benchmarks
• 9.3 Specialized Benchmarks
• 9.4 Evaluating Agentic Systems
• 9.6 Red Teaming and Security Bounties
• 9.7 TEVV, External Audit and Conformity Assessment
• 9.8 Impact Assessment
• 9.9 Reproducibility, Open Science and Benchmark Snapshots