publications

2025

1. Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods

   Panagiota Kiourti, Anu Singh, Preeti Duraipandian, and 2 more authors

   arXiv preprint arXiv:2512.06665, 2025

2024

1. Enhancing deep learning security through explainability and robustness

   Panagiota Kiourti

   Boston University, 2024

2023

1. Dormant Neural Trojans

   Feisi Fu, Panagiota Kiourti, and Wenchao Li

   In 2023 International Conference on Machine Learning and Applications (ICMLA), 2023

2021

1. Misa: Online defense of trojaned models using misattributions

   Panagiota Kiourti, Wenchao Li, Anirban Roy, and 2 more authors

   In Proceedings of the 37th Annual Computer Security Applications Conference, 2021

2020

1. Trojdrl: evaluation of backdoor attacks on deep reinforcement learning

   Panagiota Kiourti, Kacper Wardega, Susmit Jha, and 1 more author

   In 2020 57th ACM/IEEE Design Automation Conference (DAC), 2020