Martin Nocker, MSc

Teaching & Research Assistant +43 512 2070 - 4447 martin.nocker@mci.edu

Peer reviewed journal article

Merkle, F., Weber, D., Schöttle, P., Schlögl, S., & Nocker, M. (2025). Less is More: The Influence of Pruning on the Explainability of CNNs. IEEE Access, 13, 87909–87927. https://doi.org/10.1109/ACCESS.2025.3569575
Klocker, F., Bernsteiner, R., Ploder, C., & Nocker, M. (2023). A Machine Learning Approach for Automated Cost Estimation of Plastic Injection Molding Parts. Cloud Computing and Data Science, 4(2), 87–111. https://doi.org/10.37256/ccds.4220232277

Peer reviewed academic/professional meeting proceedings

Schöttle, P., Janetschek, M., Merkle, F., Nocker, M., & Egger, C. (2025). Large-Scale (Semi-)Automated Security Assessment of Consumer IoT Devices – A Roadmap. 2025 10th International Conference on Smart and Sustainable Technologies (SpliTech), 1–8. https://doi.org/10.23919/SpliTech65624.2025.11091811
Nocker, M., Henke, L., & Schottle, P. (2025). FHE ML Tuxedo: A Tailored Wrapper Architecture for Homomorphic Encryption in Machine Learning. 2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), 266–273. https://doi.org/10.1109/DSN-W65791.2025.00075
Russold, M., Nocker, M., & Schöttle, P. (2024). Incremental Whole Plate ALPR Under Data Availability Constraints. Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - ICPRAM, 131–140. https://doi.org/10.5220/0012566400003654
Schmidt, J., Pietsch, V., Nocker, M., Rader, M., & Montuoro, A. (2024). Navigating the Trade-Off Between Explainability and Privacy. Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - VISIGRAPP, 726-733. https://doi.org/10.5220/0012472200003660
Merkle, F., Sirbu, M. R., Nocker, M., & Schöttle, P. (2024). Generating Invariance-Based Adversarial Examples: Bringing Humans Back into the Loop. In G. L. Foresti, A. Fusiello, & E. Hancock (Hrsg.), Image Analysis and Processing—ICIAP 2023 Workshops (S. 15–27). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-51023-6_2
Martin, Nocker, David, Drexel, Michael Rader, Alessio Montuoro, and Pascal Schöttle. "HE-MAN - Homomorphically Encrypted MAchine learning with oNnx models", In The 8th International Conference on Machine Learning Technologies (ICMLT), 2023. https://doi.org/10.1145/3589883.3589889
Roland Rauter, Martin Nocker, Florian Merkle, and Pascal Schöttle. "On the Effect of Adversarial Training Against Invariance-based Adversarial Examples", In The 8th International Conference on Machine Learning Technologies (ICMLT), 2023. https://doi.org/10.1145/3589883.3589891
Widmann, T., Merkle, F., Nocker, M., & Schöttle, P. (2023). Pruning for Power: Optimizing Energy Efficiency in IoT with Neural Network Pruning. In L. Iliadis, I. Maglogiannis, S. Alonso, C. Jayne, & E. Pimenidis (Hrsg.), Engineering Applications of Neural Networks (S. 251–263). Springer Nature Switzerland. doi: 10.1007/978-3-031-34204-2_22
Mrowca, A., Nocker, M., Steinhorst, S., & Günnemann, S. (2019). Learning temporal specifications from imperfect traces using bayesian inference. In Proceedings of the 56th Annual Design Automation Conference 2019 (pp. 1-6).

Supervised bachelor theses

Hetzenauer Kevin (2025): Machbarkeitsanalyse von Federated Learning mit Internet of Things: Vergleich zentralisierter und dezentraler Trainingsansätze
Windisch Jakob (2025): Comparative Analysis of Self-Supervised Learning Algorithms for Effective Data Labeling and Performance Improvements in Computer Vision Models
Brandacher Daniel (2025): Evaluierung wesentlicher Einflussfaktoren bei der Implementierung eines lokalen Open Source Large Language Models
Oberhofer Samuel (2024): Invariance-Based Adversarial Examples: Algorithmic Creation and Human Evaluation for Image Classification
Aster Pirmin (2024): Maschinelle Fehlererkennung im technischen Keramik-3D-Druck
Meusburger Matthias (2024): Analysis of Air Quality Data Using Homomorphic Encryption
Koudelka Paul (2023): Explainable Machine Learning Algorithms While Using Homomorphic Encryption