Dr. Mohammed Abuhamad is an Associate Professor of Computer Science at Loyola University Chicago . He received a Ph.D. degree in Computer Science from the University of Central Florida (UCF) in 2020. He also received a Ph.D. degree in Electrical and Computer Engineering from INHA University , (Incheon, Republic of Korea) in 2020. He received a Master degree in Information Technology (Artificial Intelligence) from the National University of Malaysia , (Bangi, Malaysia) in 2013.
He is interested in AI/Deep-Learning-based Information Security, especially Software and Mobile/IoT Security. He is also interested in Machine Learning-based Applications and Adversarial Machine Learning. He has published several peer-reviewed research papers in top-tier conferences and journals such as ACM CCS, PoPETS, IEEE ICDCS, and IEEE IoT-J.
Publications (26)
2025
Stealthy Query-Efficient OpaqueAttack Against Interpretable Deep Learning
IEEE Transactions on Reliability
·
01 Sep 2025
·
doi:10.1109/TR.2025.3551717
Towards Robust Federated Learning: Investigating Poisoning Attacks Under Clients Data Heterogeneity
2025 19th International Conference on...
·
03 Jan 2025
·
doi:10.1109/imcom64595.2025.10857574
AdvChar: Attacking Interpretable NLP Systems
IEEE TIFS
IEEE Transactions on Information Fore...
·
01 Jan 2025
·
doi:10.1109/TIFS.2025.3622073
2024
Hardening Interpretable Deep Learning Systems: Investigating Adversarial Threats and Defenses
IEEE TDSC
IEEE Transactions on Dependable and S...
·
01 Jul 2024
·
doi:10.1109/TDSC.2023.3341090
MotionID: Towards practical behavioral biometrics-based implicit user authentication on smartphones
Pervasive and Mobile Computing
·
01 Jul 2024
·
doi:10.1016/j.pmcj.2024.101922
The Impact of Model Variations on the Robustness of Deep Learning Models in Adversarial Settings
2024 Silicon Valley Cybersecurity Con...
·
17 Jun 2024
·
doi:10.1109/SVCC61185.2024.10637362
Unmasking the Vulnerabilities of Deep Learning Models: A Multi-Dimensional Analysis of Adversarial Attacks and Defenses
2024 Silicon Valley Cybersecurity Con...
·
17 Jun 2024
·
doi:10.1109/SVCC61185.2024.10637364
From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings
arXiv
·
06 May 2024
·
arxiv:2405.01963
Impact of Architectural Modifications on Deep Learning Adversarial Robustness
arXiv
·
06 May 2024
·
arxiv:2405.01934
SingleADV: Single-Class Target-Specific Attack Against Interpretable Deep Learning Systems
IEEE TIFS
IEEE Transactions on Information Fore...
·
01 Jan 2024
·
doi:10.1109/TIFS.2024.3407652
2023
Unveiling Vulnerabilities in Interpretable Deep Learning Systems with Query-Efficient Black-box Attacks
arXiv
·
25 Jul 2023
·
arxiv:2307.11906
Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems
arXiv
·
14 Jul 2023
·
arxiv:2307.06496
Single-Class Target-Specific Attack against Interpretable Deep Learning Systems
arXiv
·
14 Jul 2023
·
arxiv:2307.06484
2022
Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning
arXiv
·
30 Nov 2022
·
arxiv:2211.15926
MLxPack: Investigating the Effects of Packers on ML-based Malware Detection Systems Using Static and Dynamic Traits
Proceedings of the 1st Workshop on Cy...
·
30 May 2022
·
doi:10.1145/3494108.3522768
Black-box and Target-specific Attack Against Interpretable Deep Learning Systems
Proceedings of the 2022 ACM on Asia C...
·
30 May 2022
·
doi:10.1145/3488932.3527283
Depth, Breadth, and Complexity: Ways to Attack and Defend Deep Learning Models
Proceedings of the 2022 ACM on Asia C...
·
30 May 2022
·
doi:10.1145/3488932.3527278
Leveraging Spectral Representations of Control Flow Graphs for Efficient Analysis of Windows Malware
Proceedings of the 2022 ACM on Asia C...
·
30 May 2022
·
doi:10.1145/3488932.3527294
Sentiment Analysis of Users’ Reactions on Social Media during the Pandemic
Electronics
·
22 May 2022
·
doi:10.3390/electronics11101648
2021
Large-scale and Robust Code Authorship Identification with Deep Feature Learning
ACM TOPS
ACM Transactions on Privacy and Security
·
19 Jul 2021
·
doi:10.1145/3461666
An Exploration of Geo-temporal Characteristics of Users' Reactions on Social Media During the Pandemic
arXiv
·
25 Mar 2021
·
arxiv:2103.13032
AdvEdge: Optimizing Adversarial Perturbations Against Interpretable Deep Learning
Lecture Notes in Computer Science
·
01 Jan 2021
·
doi:10.1007/978-3-030-91434-9_9
2020
Multi-χ: Identifying Multiple Authors from Source Code Files
Proceedings on Privacy Enhancing Tech...
·
01 Jul 2020
·
doi:10.2478/popets-2020-0044
AUToSen: Deep-Learning-Based Implicit Continuous Authentication Using Smartphone Sensors
IEEE Internet of Things Journal
·
01 Jun 2020
·
doi:10.1109/JIOT.2020.2975779
2019
Code authorship identification using convolutional neural networks
Future Generation Computer Systems
·
01 Jun 2019
·
doi:10.1016/j.future.2018.12.038
2018
Large-Scale and Language-Oblivious Code Authorship Identification
Proceedings of the 2018 ACM SIGSAC Co...
·
15 Oct 2018
·
doi:10.1145/3243734.3243738