Evaluating the Robustness of Neuro-Symbolic Networks Against Backdoor Threats with WaNet and Semantic Loss

Bachelor Thesis (2025)
Author(s)

F. Hamar (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

A. Agiollo – Mentor (TU Delft - Cyber Security)

Kaitai Liang – Mentor (TU Delft - Cyber Security)

A. Hanjalic – Graduation committee member (TU Delft - Intelligent Systems)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
23-06-2025
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project']
Programme
['Computer Science and Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Backdoor attacks targeting Neural Networks face little to no resistance in achieving misclassifications thanks to an injected trigger. Neuro-symbolic architectures combine such networks with symbolic components to introduce semantic knowledge into purely connectionist designs. This paper aims to benchmark the robustness of such models against state-of-the-art backdoor attacks. In doing so it explores how semantic knowledge can be extracted from datasets and how various constraint sets fare against differing strength attacks. The paper concludes that building knowledge into the models can indeed induce robustness against adversarial poisoning attacks, but it also reflects on the conditions necessary for success.

Files

License info not available