This page provides the attacks and factors that have a negative impact “Harm to humans due to decreased prediction accuracy or unexpected behavior by AI” in the information systems aspect in the AI Security Map, the defense methods and countermeasures against them, as well as the relevant AI technologies, tasks, and data. It also indicates related elements in the external influence aspect.
Attack or cause
- Integrity violation
Defensive method or countermeasure
- Defensive method for integrity
- Fail-safe mechanism
Targeted AI technology
- All AI technologies
Task
- Classification
- Generation
Data
- Image
- Graph
- Text
- Audio
Related external influence aspect
- Reputation
- Compliance with laws and regulations
- Human-centric principle
- Physical impact
- Psychological impact
- Financial impact
- Ethics
- Economy
- Critical infrastructure
- Medical care