| PRADA: protecting against DNN model stealing attacks M Juuti, S Szyller, S Marchal, N Asokan 2019 IEEE European Symposium on Security and Privacy (EuroS&P), 512-527, 2019 | 557 | 2019 |
| Dawn: Dynamic adversarial watermarking of neural networks S Szyller, BG Atli, S Marchal, N Asokan Proceedings of the 29th ACM International Conference on Multimedia, 4417-4425, 2021 | 215 | 2021 |
| Llm self defense: By self examination, llms know they are being tricked M Phute, A Helbling, MD Hull, SY Peng, S Szyller, C Cornelius, DH Chau The Second Tiny Papers Track at ICLR 2024, 2023 | 157* | 2023 |
| Extraction of complex dnn models: Real threat or boogeyman? BG Atli, S Szyller, M Juuti, S Marchal, N Asokan Engineering Dependable and Secure Machine Learning Systems: Third …, 2020 | 47 | 2020 |
| Detecting organized eCommerce fraud using scalable categorical clustering S Marchal, S Szyller Proceedings of the 35th Annual Computer Security Applications Conference …, 2019 | 20 | 2019 |
| SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning V Duddu, S Szyller, N Asokan arXiv preprint arXiv:2112.02230, 2021 | 14 | 2021 |
| Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Generative Adversarial Networks S Szyller, V Duddu, T Gröndahl, N Asokan arXiv e-prints, arXiv: 2104.12623, 2021 | 14 | 2021 |
| False claims against model ownership resolution J Liu, R Zhang, S Szyller, K Ren, N Asokan 33rd USENIX Security Symposium (USENIX Security 24), 6885-6902, 2024 | 10 | 2024 |
| Conflicting Interactions among Protection Mechanisms for Machine Learning Models S Szyller, N Asokan Proceedings of the AAAI Conference on Artificial Intelligence 37 (12), 15179 …, 2023 | 9 | 2023 |
| SoK: Unintended Interactions among Machine Learning Defenses and Risks V Duddu, S Szyller, N Asokan arXiv preprint arXiv:2312.04542, 2023 | 5 | 2023 |
| On the robustness of dataset inference S Szyller, R Zhang, J Liu, N Asokan arXiv preprint arXiv:2210.13631, 2022 | 4 | 2022 |
| Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models H Chen, S Szyller, W Xu, N Himayat arXiv preprint arXiv:2502.15836, 2025 | | 2025 |
| Imperceptible Adversarial Examples in the Physical World W Xu, S Szyller, C Cornelius, LM Rojas, M Arvinte, A Velasquez, J Martin, ... arXiv preprint arXiv:2411.16622, 2024 | | 2024 |
| Methods and apparatus for private synthetic data generation M Arvinte, B Edwards, C Cornelius, J Martin, S Szyller, M Sheller, ... US Patent App. 18/591,640, 2024 | | 2024 |
| Ownership and Confidentiality in Machine Learning S Szyller Aalto University, 2023 | | 2023 |
| Adversary Detection in Online Machine Learning Systems S Szyller | | 2020 |
N. AsokanProfessor of Computer Science, University of WaterlooOverená e-mailová adresa na: uwaterloo.ca