Ozan Özdenizci

Ozan Özdenizci

Research Group Leader, Chair of Cyber-Physical-Systems, Montanuniversität Leoben

Short Bio

I am a research group leader at the Chair of Cyber-Physical-Systems at Montanuniversität Leoben in Austria, since April 2024. My research is focused in the domain of robust, secure and efficient deep learning algorithms for reliable artificial intelligence systems, and statistical signal processing with biomedical applications.

Prior to joining MU Leoben, I was a postdoctoral researcher at the Institute of Theoretical Computer Science, Graz University of Technology, working with Prof. Robert Legenstein. I received my Ph.D. degree from Northeastern University (Boston, MA, USA) under supervision of Prof. Deniz Erdoğmuş, and my M.Sc. and B.Sc. degrees from Sabancı University (Istanbul, Turkey) under supervision of Prof. Müjdat Çetin.

News

  • [09/2024] - New paper published at ECML-PKDD 2024. [PDF / Code]
    Jasmin Viktoria Gritsch, Robert Legenstein and Ozan Özdenizci, “Preserving real-world robustness of neural networks under sparsity constraints”, European Conference on Machine Learning and Knowledge Discovery in Databases (ECML-PKDD), 2024.
  • [04/2024] - New paper published at TMLR 2024. [PDF / Code]
    Ozan Özdenizci and Robert Legenstein, “Adversarially robust spiking neural networks through conversion”, Transactions on Machine Learning Research (TMLR), 2024.
  • [04/2024] - Started as a research group leader at the Chair of Cyber-Physical-Systems at Montanuniversität Leoben.
  • [12/2023] - New paper published at IEEE TNNLS 2023. [PDF / Code]
    Thomas Limbacher, Ozan Özdenizci and Robert Legenstein, “Memory-dependent computation and learning in spiking neural networks through Hebbian plasticity”, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023.
  • [11/2023] - Listed among the Top Reviewers (top 10%) at NeurIPS 2023.
  • [07/2023] - Became an ELLIS member and a member of the ELLIS Unit Graz.
  • [06/2023] - Invited talk at the Austrian Computer Science Day 2023, titled: “Building Robustness into Embedded Machine Intelligence”.
  • [01/2023] - New paper published at IEEE TPAMI 2023. [PDF / Code / Slides]
    Ozan Özdenizci and Robert Legenstein, “Restoring vision in adverse weather conditions with patch-based denoising diffusion models”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023.
  • [07/2022] - Received an Outstanding Reviewer Award (top 10%) at ICML 2022.
  • [04/2022] - Listed among the Highlighted Reviewers (top 10%) at ICLR 2022.
  • [03/2022] - Paper accepted at CVPR 2022 for an oral presentation! [PDF / Code / Slides]
    Ozan Özdenizci and Robert Legenstein, “Improving robustness against stealthy weight bit-flip attacks by output code matching”, CVPR 2022.
  • [03/2022] - Organizing a Research Topic as a Guest Editor cross-listed at Frontiers in Signal Processing, Frontiers in Neuroinformatics and Frontiers in Artificial Intelligence: “Adversarial machine learning and domain generalization in neurophysiological signal analysis” [Call for Participation]
  • [01/2022] - New paper accepted at ICASSP 2022. [PDF / Code]
  • [10/2021] - Received an Outstanding Reviewer Award (top 8%) in NeurIPS 2021.
  • [07/2021] - Presented our work on sparse adversarial training of deep neural networks at ICML 2021. Spotlight talk and poster are available online. [Slides]
  • [05/2021] - New paper accepted at ICML 2021! [PDF / Code]
    Ozan Özdenizci and Robert Legenstein, “Training adversarially robust sparse networks via Bayesian connectivity sampling”, ICML 2021.

Contact

Chair of Cyber-Physical-Systems
Montanuniversität Leoben
Franz-Josef-Straße 18
8700 Leoben, Austria
Email: ozan.oezdenizci(at)unileoben.ac.at