This page provides the attacks and factors that have a negative impact “Outputs that lead to unfair manipulation of human decision-making” 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
- Availability violation
Defensive method or countermeasure
- Uncertainty Quantification
- RAG (Retrieval-Augmented Generation)
- XAI (Explainable AI)
- Hallucination Detection
- Defensive methods to prevent compromise of causal elements
Targeted AI technology
- AI agent
Task
- Perception
- Decision-making
- Action
Data
- Text
Related external influence aspect
- Information authenticity
- Fairness
- Transparency
- Reputation
- Compliance with laws and regulations
- Human-centric principle
- Safety
- Diversity
- Independence
References
Uncertainty Quantification
- Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding, 2015
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning, 2016
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles, 2017
- Predictive Uncertainty Estimation via Prior Networks, 2018
- Evidential Deep Learning to Quantify Classification Uncertainty, 2018
- Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift, 2019
- Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods, 2021
XAI (Explainable AI)
- Visualizing and Understanding Convolutional Networks, 2014
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps, 2014
- Understanding Deep Image Representations by Inverting Them, 2014
- “Why Should I Trust You?”: Explaining the Predictions of Any Classifier, 2016
- A Unified Approach to Interpreting Model Predictions, 2017
- Learning Important Features Through Propagating Activation Differences, 2017
- Understanding Black-box Predictions via Influence Functions, 2017
- Interpretable Explanations of Black Boxes by Meaningful Perturbation, 2017
- Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV), 2018
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization, 2019