Investigates how adversarial attacks degrade ML-based classifiers operating over darknet traffic, evaluating attack effectiveness and proposing optimization strategies for both attackers and defenders.
@inproceedings{harrison2024adversarial,title={Adversarial Attack Optimization and Evaluation for Machine Learning-based Dark Web Traffic Analysis},author={Harrison, N. and Broome, H. and Shrestha, Y. and Robles, A. and Gautam, A. and Rahimi, N.},booktitle={33rd International Conference on Software Engineering and Data Engineering (SEDE)},pages={3--13},year={2024},doi={10.1007/978-3-031-75201-8_1},}
2022
CSCI
SMS Malware Detection: A Machine Learning Approach
H. Broome, Y. Shrestha, N. Harrison, and 1 more author
In 2022 International Conference on Computational Science and Computational Intelligence (CSCI), 2022
Presents a machine learning pipeline for detecting malicious SMS messages, comparing classical classifiers across feature representations of message content.
@inproceedings{broome2022sms,title={{SMS} Malware Detection: A Machine Learning Approach},author={Broome, H. and Shrestha, Y. and Harrison, N. and Rahimi, N.},booktitle={2022 International Conference on Computational Science and Computational Intelligence (CSCI)},pages={937--942},year={2022},doi={10.1109/CSCI58124.2022.00167},}