This page provides the security targets of negative impacts “Loss of job or life opportunities due to biased AI output” in the external influence aspect in the AI Security Map, as well as the attacks and factors that cause them, and the corresponding defense methods and countermeasures.
Security target
- Consumer
Attack or cause
- Integrity violation
- Degradation of controllability
- Degradation of output fairness
Defensive method or countermeasure
- Defensive method for integrity
- Human in the loop
- Countermeasures for output fairness
- Detection of bias in AI output