This page provides the attacks and factors that have a negative impact “Bias in the AI output” 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
- Bias in training data
Defensive method or countermeasure
- Defensive method for integrity
- Detection of bias in AI output
- Elimination of bias in training data
- Creation of fair AI models
Targeted AI technology
- All AI technologies
Task
- Classification
- Generation
Data
- Image
- Graph
- Text
- Audio