This page provides the security targets of negative impacts “Improperly manipulating the decision-making of non-consumers by AI” 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
- Non-consumer
Attack or cause
- Disinformation
Defensive method or countermeasure
- Defensive method for integrity
- Human in the loop
- Defensive method for disinformation
References
Human in the loop
Defensive method for disinformation
- Fake News Detection on Social Media: A Data Mining Perspective, 2017
- CSI: A Hybrid Deep Model for Fake News Detection, 2017
- Towards Few-Shot Fact-Checking via Perplexity, 2021
- Fact-Checking Complex Claims with Program-Guided Reasoning, 2023
- Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method, 2023