Recent Publications

Show all (45)

• E. Kafali, C N. Spartalis, T. Semertzidis, C. Z. Patrikakis, P. Daras, "Designing AI Systems with Correction Mechanisms Towards Attack-Resilient Architectures.", in Proceedings of the 2025 IEEE International Conference on Cyber Security and Resilience (CSR), Chania, Crete, Greece, August 04-06, 2025, pp. 387-392, doi: 10.1109/CSR64739.2025.11130000
• C. N. Spartalis, T. Semertzidis, P. Daras, E. Gavves, "Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI.",in Proceedings of the ICML 2025 Workshop on Machine Unlearning for Generative AI, Vancouver, Canada, July 2025. https://arxiv.org/abs/2508.20773
• C. N. Spartalis, T. Semertzidis, E. Gavves, P. Daras, "LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty.", in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp. 10046-10055. https://openaccess.thecvf.com/content/CVPR2025/html/Spartalis_LoTUS_Large-Scale_Machine_Unlearning_with_a_Taste_of_Uncertainty_CVPR_2025_paper.html
• E. Kafali, T. Semertzidis, P. Daras, "Dynamic Trade-Offs in Adversarial Training: Exploring Efficiency, Robustness, Forgetting, and Interpretability.", Neural Processing Letters, vol. 57, no. 3, May 05, 2025. https://doi.org/10.1007/s11063-025-11751-z
• G. Kalpakis, C. Paternoster, M. Mancuso, D. Kozhuharova, T. Spathi, T. Semertzidis, T. Tsikrika, S. Vrochidis, "AI-Based Framework for Supporting Micro and Small Hosting Service Providers on the Report and Removal of Online Terrorist Content.", in Paradigms on Technology Development for Security Practitioners, pp. 249-261, Springer Nature Switzerland, 2024.