Explainable Fuzzy Deep Neural Networks for Cyber Threat Attribution

Threat attribution is crucial to detect attacks as early as possible and understand how attacks will proceed and the likely scope. This project will propose an explainable fuzzy deep neural network for cyber threat attribution. We obtain transparency and explainability via extracting fuzzy rules from DNN for cyber threat attribution. Indeed, this model, via providing explainability from extracted fuzzy rules in DNN, overcomes the black-box nature of DNNs and uncertainty. Also, Fuzzy logic has been applied since its reasoning resembles human reasoning in cyber threat attribution.

Faculty Supervisor:

Ali Dehghantanha

Student:

Partner:

Fairly AI Inc

Discipline:

Computer science

Sector:

Information and cultural industries

University:

University of Guelph

Program:

Accelerate

Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Government

International

Load More

International

Load More