Christoph Koutschan, Bernhard A. Moser, Anton Ponomarchuk, Josef Schicho, A Basis for Piecewise Linear Functions (to be submitted)
Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Nguyễn Đức Hoàn, Andrea Huber, Hamid Eghbal-zadeh, Bernhard A. Moser, Sergei Pereverzyev, Sepp Hochreiter, Werner Zellinger, Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation (accepted for ICLR 2023)
Zheng, Y., Feng, X., Xia, Z., Jiang, X., Demontis, A., Pintor, M., Biggio, B., & Roli, F. (2021). Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference. arXiv preprint arXiv:2108.11673. Submitted to Information Sciences.
Cinà, A.E., Grosse, K., Demontis, A., Vascon, S., Zellinger, W., Moser, B.A., Oprea, A., Biggio, B., Pelillo, M., Roli, F., 2022. Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning. arXiv preprint arXiv.2205.01992. Submitted to ACM Computing Survey.
Cinà, A.E., Grosse, K., Demontis, A., Biggio, B., Roli, F., Pelillo, M., 2022. Machine Learning Security against Data Poisoning: Are We There Yet? arXiv preprint arXiv.2204.05986. Submitted to IEEE Computer Magazine.
Grosse, K., Bieringer, L., Besold, T. R., Biggio, B., & Krombholz, K. (2022). " Why do so?"--A Practical Perspective on Machine Learning Security. arXiv preprint arXiv:2207.05164. Submitted to TIFS.
Zheng, Y., Feng, X., Xia, Z., Jiang, X., Pintor, M., Demontis, A., Biggio, B., & Roli, F. (2022). Stateful Detection of Adversarial Reprogramming. arXiv preprint arXiv:2211.02885. Submitted to Information Sciences.
Eghbal-zadeh, H., Zellinger, W., Grosse, K., Koutini, K., Biggio, B., Moser, B.A., Widmer, G., 2021. Data Augmentation and Adversarial Robustness. To be submitted in 2023.
Kumar, B.A. Moser, L. Fischer and B. Freudenthaler, Information Theoretic Evaluation of Privacy-Leakage, Interpretability, and Transferability for Trustworthy AI (under review, Computational Intelligence)
Kumar and B. A. Moser, Kernel Affine Hull Machines for Privacy-Preserving Distributed Learning, to be submitted in 2023 to Journal of Machine Learning Research)