University of Twente Student Theses

Login

Privacy-preserving counterfactual explanations to help humans contest AI-based decisions

Nelson, D.J. (2022) Privacy-preserving counterfactual explanations to help humans contest AI-based decisions.

[img] PDF
2MB
Abstract:In the Cybersecurity field, very little work is done that measures how vulnerable is multi-objective counterfactual explanations to adversarial attacks and to what extent the privacy of the individuals can be preserved. Through this research, we aim to answer the question- (i) How easy it is to perform a membership inference attack through counterfactual explanations (ii) what is the defense mechanism to prevent a membership inference attack?
Item Type:Essay (Master)
Clients:
TNO
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:31 mathematics, 54 computer science
Programme:Computer Science MSc (60300)
Link to this item:https://purl.utwente.nl/essays/92461
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page