AIセキュリティポータル K Program

Negative impact “Adverse impact on human perception and judgment caused by AI misinformation”

This page provides the security targets of negative impacts “Adverse impact on human perception and judgment caused by AI misinformation” 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
  • Explainability violation
  • Degradation of output fairness
  • Degradation of accuracy
  • Degradation of controllability
  • Reliability violation
  • Poisoning attack against RAG

Defensive method or countermeasure

References