Improving deep learning with prior knowledge and cognitive models: A survey on enhancing interpretability, adversarial robustness and zero-shot learning

F Mumuni, A Mumuni - Cognitive Systems Research, 2023 - Elsevier
We review current and emerging knowledge-informed and brain-inspired cognitive systems
for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot or …

Towards a cognitive theory of cyber deception

EA Cranford, C Gonzalez, P Aggarwal… - Cognitive …, 2021 - Wiley Online Library
This work is an initial step toward developing a cognitive theory of cyber deception. While
widely studied, the psychology of deception has largely focused on physical cues of …

Cognitive architectures and their applications

C Lebiere, EA Cranford, M Martin… - 2022 IEEE 8th …, 2022 - ieeexplore.ieee.org
Cognitive architectures are computational implementations of unified theories of cognition.
The consensus of 50 years of research in cognitive architectures can be captured in the form …

Modeling Human Behavior Part II--Cognitive approaches and Uncertainty

A Fuchs, A Passarella, M Conti - arXiv preprint arXiv:2205.06483, 2022 - arxiv.org
As we discussed in Part I of this topic, there is a clear desire to model and comprehend
human behavior. Given the popular presupposition of human reasoning as the standard for …

Comparison of cognitively-inspired salience and feature importance techniques in intrusion detection datasets

RH Thomson, EA Cranford, G Tucker… - … and Security for AI …, 2024 - spiedigitallibrary.org
We present a cognitively-inspired salience technique that utilizes our knowledge of human
information processing mechanisms to determine the extent to which each feature is …

Cognitive Models Leading to Behavior-Reading in a Card Game

A Hosokawa, J Morita - Proceedings of the 9th International Conference …, 2021 - dl.acm.org
In everyday life, humans often try to understand and predict other's behavior. However, the
cognitive process behind this is not well understood. To clarify this, we require a model that …