Bartosz Bok
Research interests: cybersecurity, machine learning
Bartosz Bok is working on a methodology for testing the vulnerability of ML models to attacks. He creates ML models to automatically detect malicious applications on phones of Android users. He analyzes data from soccer games to obtain the knowledge necessary to improve game performance. He is interested in using machine learning techniques to create synthetic data, as well as the field of Explainable Machine Learning.
Selected Publications
Articles
Michał Nowak, Bartosz Bok, Artur Wilczek, Łukasz Oleksy, Mariusz Kamola, "Forecasting extremes of football players’ performance in matches", Scientific Reports, 14, 2024, 27319.
Mateusz Krzysztoń, Bartosz Bok, Paweł Żakieta, Joanna Kołodziej, "Evasion attacks on ML in domains with nonlinear constraints", 2024 IEEE 24th International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW), CCGridW 2024, 2024, 112-119.
Bartłomiej Marek, Kacper Pieniążek, Filip Ratajczak, Wojciech Adamczyk, Bartosz Bok, Mateusz Krzysztoń, "Securing ML-based Android Malware Detectors: A Defensive Feature Selection Approach against Backdoor Attacks", 2024 IEEE 24th International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW), CCGridW 2024, 2024, 128-135.
Mateusz Krzysztoń, Bartosz Bok, Marcin Lew, Andrzej Sikora, "Lightweight On-Device Detection of Android Malware Based on the Koodous Platform and Machine Learning", Sensors, 22(17), 2022, 6562.