Submitted 2020

Peer-reviewed Journals and Contents

  • Werner Zellinger, Bernhard Moser, Susanne Saminger-Platz, "On generalization in moment-based domain adaptation." Annals of Mathematics and Artificial Intelligence, November 2020,
  • Shuai Lu, Peter Mathe, and Sergei V. Pereverzyev, "Randomized matrix approximation to enhance regularized projection schemes in inverse problems." Inverse Problems, Volume 36, Issue 8, id.085013, 20 pp, August 2020,
  • Ramin Nikzad-Langerodi, Werner Zellinger, Susanne Saminger-PLatz, Bernhard Moser, "Domain adaptation for regression under Beer–Lambert’s law." Knowlege-Based Systems, Volume 210, 106447, December 2020,
  • Vihang P. Patil, Markus Hofmarcher, Marius-Constantin Dinu, Matthias Dorfer, Patrick M. Blies, Johannes Brandstetter, Jose A. Arjona-Medina, Sepp Hochreiter, "Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution." arXiv:2009.14108, 2020-09-29,, Software:
  • Melis, M., Scalas, M., Demontis, A., Maiorca, D., Biggio, B., Giacinto, G., and Roli, F. “Do gradient-based explanations tell anything about adversarial robustness to android malware?”, International Journal of Machine Learning and Cybernetics, Int. J. Mach. Learn. & Cyber. 13, 217–232 (2022). and
  • Lukas Fischer, Lisa Ehrlinger, Verena Geist, Rudolf Ramler, Florian Sobiezky,Werner Zellinger, David Brunner, Mohit Kumar and Bernhard A. Moser, "AI System Engineering—Key Challenges and Lessons Learned" Mach. Learn. Knowl. Extr. 3, no. 1: 56-83, 2021,
  • Holzleitner, M., Gruber, L., Arjona-Medina, J., Brandstetter, J., Hochreiter, S. (2021). Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER. In: Hameurlain, A., Tjoa, A.M. (eds) Transactions on Large-Scale Data- and Knowledge-Centered Systems XLVIII. Lecture Notes in Computer Science, vol 12670. Springer, Berlin, Heidelberg, and
  • Thomas Adler, Johannes Brandstetter, Michael Widrich, Andreas Mayr, David Kreil, Michael Kopp, Günter Klambauer, Sepp Hochreiter, “Cross-Domain Few-Shot Learning by Representation Fusion”, arXiv:2010.06498, 2020,, Software:
  • Mohit Kumar, David Brunner, Bernhard A. Moser, Freudenthaler, B. (2020). Variational Optimization of Informational Privacy. In: , et al. Database and Expert Systems Applications. DEXA 2020. Communications in Computer and Information Science, vol 1285. Springer, Cham.

Non Peer-reviewed Journals and Contents

  • Natalia Shepeleva, Werner Zellinger, Michal Lewandowski, Bernhard Moser, "ReLU Code Space: A Basis for Rating Network Quality Besides Accuracy", ICLR Workshop on Neural Architecture Search, April 2020,
  • Rafa Galvez, Veelasha Moonsamy, Claudia Diaz, "Less is More: A privacy-respecting Android malware classifier using Federated Learning", Proceedings on Privacy Enhancing Technologies, pp. 96 – 116, 2021,
  • Bernhard A. Moser, "Computer Implementiertes Verfahren zur Bewertung der Integrität von Neuronalen Netzen" (Method for the integrity evaluation of neural networks) International Patent PCT/EP2019/072830, filed 27th August 2019 (priority date 10th of Sept. 2018; DPMA S2959).

Conferences / Workshops

  • Werner Zellinger, Volkmar Wieser, Mohit Kumar, David Brunner, Natalia Shepeleva, Rafa Galvez, Josef Langer, Lukas Fischer, and Bernhard Moser, "Beyond federated learning: On confidentiality-critical machine learning applications in industry." International Conference on Industry 4.0 and Smart Manufacturing, November 2020,
  • David Solans, Battista Biggio, and Carlos Castillo, "Poisoning Attacks on Algorithmic Fairness." The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, September 2020,
  • Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus, Verena Haunschmid, Michal Lewandowski, Werner Zellinger, Bernhard A. Moser, Gerhard Widmer, "On Data Augmentation and Adversarial Risk: An Empirical Analysis." ICLR Workshop Towards Trustworthy Machine Learning, April 2020,
  • Michael Widrich, Bernhard Schäfl, Hubert Ramsauer, Milena Pavlović, Lukas Gruber, Markus Holzleitner, Johannes Brandstetter, Geir Kjetil Sandve, Victor Greiff, Sepp Hochreiter, Günter Klambauer, "Modern Hopfield Networks and Attention for Immune Repertoire Classification", 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada, and, Software:
  • Mohit Kumar, Michael Rossbory, Bernhard A. Moser, and Bernhard Freudenthaler, “Differentially Private Learning of Distributed Deep Models”. In Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization (UMAP '20 Adjunct). Association for Computing Machinery, New York, NY, USA, 193–200, 2020,

Master and Doctoral Thesis

  • Werner Zellinger, "Moment-based domain adaptation: Learning bounds and algorithms." Doctoral thesis (JKU Linz), April 2020,
  • Davide Deidda, "Towards Countering Physical Adversarial Attacks On Deep Learning For Face Recognition." Master's thesis (UNI Cagliari), August 2020.

Submitted 2021

Peer-reviewed Journals

  • Maura Pintor, Fabio Roli, Wieland Brendel, Battista Biggio, “Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints”, Advances in Neural Information Processing Systems 34 (NeurIPS 2021) and
  • E.R. Gizewski, L. Mayer, B.A. Moser, D.H. Nguyen, S. Pereverzyev Jr, S.V. Pereverzyev, N. Shepeleva, W. Zellinger. "On a regularization of unsupervised domain adaptation in RKHS." Applied and Computational Harmonic Analysis, Volume 57, pp 201-227, March 2022,
  • Zellinger, Werner, and Bernhard A. Moser, "On the truncated Hausdorff moment problem under Sobolev regularity conditions." Applied Mathematics and Computation, Volume 400, July 2021: 126057,
  • Kargaran, Somayeh, Bert Jüttler, and Thomas Takacs, "IGA Using Offset-based Overlapping Domain Parameterizations." Computer-Aided Design 139 (2021): 103087,
  • F. Crecchi, M. Melis, A. Sotgiu, D. Bacciu, and B. Biggio, “FADER: Fast adversarial example rejection”, Neurocomputing, 470:257–268, Jan 2022, and
  • Pintor, M., Demetrio, L., Manca, G., Biggio, B. and Roli, F., “Slope: A First-order Approach for Measuring Gradient Obfuscation”, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2021), ISBN 978287587082-7,
  • Mohit Kumar, Michael Rossbory, Bernhard A. Moser, Bernhard Freudenthaler, An optimal (∊,δ)-differentially private learning of distributed deep fuzzy models, Information Sciences, Volume 546, 2021, pp 87-120, ISSN 0020-0255,

Non Peer-reviewed Journals

  • Moshe Kravchik, Battista Biggio, Asaf Shabtai, “Poisoning Attacks on Cyber Attack Detectors for Industrial Control Systems.” In 36th ACM/SIGAPP Symposium on Applied Computing (SAC '21), March 2021. and
  • W. Zellinger, N. Shepeleva, M.-C. Dinu, H. Eghbal-zadeh, H.D. Nguyen, B. Nessler, S. Pereverzyev, B. A. Moser. "The balancing principle for parameter choice in distance-regularized domain adaptation." Advances in Neural Information Processing Systems 34 (NeurIPS 2021), Corpus ID: 245062999 and , Software:, Poster:, Paper:
  • N.H. Mhaskar, S.V. Pereverzyev, M.D. van der Walt, “Function Approximation Approach to the Prediction of Blood Glucose Levels”, Frontiers in Applied Mathematics and Statistics, 7, August 2021, and
  • Mohit Kumar, Bernhard A. Moser, Lukas Fischer, Bernhard Freudenthaler, Information Theoretic Evaluation of Privacy-Leakage, Interpretability, and Transferability for Trustworthy AI, arXiv:2106.06046, 2021,

Conferences / Workshops

  • Hubert Ramsauer, Bernhard Schäfl, Johannes Lehner, Philipp Seidl, Michael Widrich, Thomas Adler, Lukas Gruber, Markus Holzleitner, Milena Pavlović, Geir Kjetil Sandve, Victor Greiff, David Kreil, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter, “Hopfield Networks is All You Need”, International Conference on Learning Representations (ICLR 2021),, Software:
  • Cinà, A.E., Vascon, S., Demontis, A., Biggio, B., Roli, F. and Pelillo, M., “The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?”, 2021 International Joint Conference on Neural Networks (IJCNN), 2021, pp. 1-8, doi: 0.1109/IJCNN52387.2021.9533557 and, Software:
  • Cinà, A.E., Grosse, K., Vascon, S., Demontis, A., Biggio, B., Roli, F. and Pelillo, M., “Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions”, accepted to the Adversarial Robustness in the Real World Workshop at ICCV, 2021, and
  • Bieringer, L., Grosse, K., Backes, M. and Krombholz, K., „Mental Models of Adversarial Machine Learning”, accepted to the Adversarial Robustness in the Real World Workshop at ICCV, 2021, and
  • C. Koutschan, A. Ponomarchuk, J. Schicho, “Approximation of convex polygons by polygons”, 2021 23rd International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC),  conference paper, Dec 2021, Timisoara, Romania,
  • Pieter-Jan Hoedt, Frederik Kratzert, Daniel Klotz, Christina Halmich, Markus Holzleitner, Grey Nearing, Sepp Hochreiter, Günter Klambauer, “MC-LSTM: Mass-Conserving LSTM”, International Conference on Machine Learning (ICML 2021), and
  • Mohit Kumar, Bernhard A. Moser, Fischer, L., Freudenthaler, B. (2021). Membership-Mappings for Data Representation Learning: A Bregman Divergence Based Conditionally Deep Autoencoder. In: , et al. Database and Expert Systems Applications - DEXA 2021 Workshops. DEXA 2021. Communications in Computer and Information Science, vol 1479. Springer,
  • Mohit Kumar, Bernhard A. Moser, Fischer, L., Freudenthaler, B. (2021). Membership-Mappings for Data Representation Learning: Measure Theoretic Conceptualization. In: , et al. Database and Expert Systems Applications - DEXA 2021 Workshops. DEXA 2021. Communications in Computer and Information Science, vol 1479. Springer.
  • Bernhard A. Moser, Michal Lewandowski, Somayeh Kargaran, Battista Biggio, Werner Zellinger, Christoph Koutschan: Tessellation-Filtering ReLU Neural Networks, Submitted to IJCAI 2022 (accepted April 2022).
  • Anton Ponomarchuk, Christoph Koutschan, and Bernhard Moser: “Unboundedness of Linear Regions of Deep ReLU Neural Networks”, submitted to DEXA AISys Workshop, 2022.

Master and Doctoral Thesis

  • M. Melis, “Explaining vulnerabilities of ML to adversarial attacks.” PhD Thesis, University of Cagliari, Italy, under progress, March 2021,
  • Giovanni Manca, “Understanding Failures of Gradient-based Attacks on Machine Learning”, MSc thesis, University of Cagliari, Italy, 2021