We are looking for highly motivated students who want to participate, during their Bachelor/Master Project and/or Thesis, in research on areas of machine learning, deep learning, and brain-inspired paradigms for computing and learning. Concete topics for Bachelor theses (B), seminar projects (P), Master theses (M) are listed below. Topics can be specialized further in discussion with the student, in order to accomodate prior knowledge and interests.
| Project Topic | Type | Contact |
| Adversarially robust generative modeling with deep variational autoencoders | B/P/M | Ozan Özdenizci |
| Exploring real world vulnerability of deep neural networks against adversarial patch attacks | B/P/M | Ozan Özdenizci |
| Improving generalization in deep learning with diffusion models | P/M | Ozan Özdenizci |
| Security of deep spiking neural networks against bit-flip attacks | P/M | Ozan Özdenizci |
| Naturalistic adversarial attack algorithms on deep neural networks | B/P | Ozan Özdenizci |
| Efficient and accelerated adversarial training for robust and sparse deep neural networks | B | Ozan Özdenizci |
Institute of Theoretical Computer Science
Inffeldgasse 16b/I
8010 Graz
Phone: +43 (0) 316 / 873 - 5811
Fax: +43 (0) 316 / 873 - 105811
daniela.windisch-scharler@tugraz.at