| DLA: Dense-Layer-Analysis for Adversarial Example Detection P Sperl, CY Kao, P Chen, X Lei, K Böttinger 2020 IEEE European Symposium on Security and Privacy (EuroS&P), 198-215, 2020 | 47 | 2020 |
| Deutsche Normungsroadmap Künstliche Intelligenz R Adler, S Kolomiichuk, D Hecker, P Lämmel, J Ma, A Marko, M Mock, ... DIN, 2020 | 24 | 2020 |
| Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning F Boenisch, P Sperl, K Böttinger arXiv preprint arXiv:2105.07985, 2021 | 17 | 2021 |
| Activation Anomaly Analysis P Sperl, JP Schulze, K Böttinger Machine Learning and Knowledge Discovery in Databases: European Conference …, 2020 | 16 | 2020 |
| Side-channel aware fuzzing P Sperl, K Böttinger Computer Security–ESORICS 2019: 24th European Symposium on Research in …, 2019 | 9 | 2019 |
| Assessing the Impact of Transformations on Physical Adversarial Attacks PA Sava, JP Schulze, P Sperl, K Böttinger Proceedings of the 15th ACM Workshop on Artificial Intelligence and Security …, 2022 | 7 | 2022 |
| Double-adversarial activation anomaly detection: Adversarial autoencoders are anomaly generators JP Schulze, P Sperl, K Böttinger 2022 International Joint Conference on Neural Networks (IJCNN), 1-8, 2022 | 7 | 2022 |
| DA3G: detecting adversarial attacks by analysing gradients JP Schulze, P Sperl, K Böttinger European Symposium on Research in Computer Security, 563-583, 2021 | 7 | 2021 |
| Visualizing Automatic Speech Recognition–Means for a Better Understanding? K Markert, R Parracone, M Kulakov, P Sperl, CY Kao, K Böttinger Proc. 2021 ISCA Symposium on Security and Privacy in Speech Communication, 14-20, 2021 | 5 | 2021 |
| Complex-valued neural networks for voice anti-spoofing NM Müller, P Sperl, K Böttinger arXiv preprint arXiv:2308.11800, 2023 | 4 | 2023 |
| R2-ad2: Detecting anomalies by analysing the raw gradient JP Schulze, P Sperl, A Răduțoiu, C Sagebiel, K Böttinger Joint European Conference on Machine Learning and Knowledge Discovery in …, 2022 | 3 | 2022 |
| Optimizing Information Loss Towards Robust Neural Networks P Sperl, K Böttinger DYnamic and Novel Advances in Machine Learning and Intelligent Cyber …, 2020 | 3 | 2020 |
| MLAAD: The Multi-Language Audio Anti-Spoofing Dataset NM Müller, P Kawa, WH Choong, E Casanova, E Gölge, T Müller, P Syga, ... arXiv preprint arXiv:2401.09512, 2024 | 2 | 2024 |
| Shortcut Detection with Variational Autoencoders NM Müller, S Roschmann, S Khan, P Sperl, K Böttinger arXiv preprint arXiv:2302.04246, 2023 | 1 | 2023 |
| Anomaly Detection by Recombining Gated Unsupervised Experts JP Schulze, P Sperl, K Böttinger 2022 International Joint Conference on Neural Networks (IJCNN), 1-8, 2022 | 1 | 2022 |
| Security of AI-Systems: Fundamentals L Adilova, K Böttinger, V Danos, S Jacob, F Langer, T Markert, ... | 1 | 2022 |
| Imbalance in Regression Datasets D Kowatsch, NM Müller, K Tscharke, P Sperl, K Bötinger arXiv preprint arXiv:2402.11963, 2024 | | 2024 |
| A New Approach to Voice Authenticity NM Müller, P Kawa, S Hu, M Neu, J Williams, P Sperl, K Böttinger arXiv preprint arXiv:2402.06304, 2024 | | 2024 |
| Physical Adversarial Examples for Multi-Camera Systems A Răduţoiu, JP Schulze, P Sperl, K Böttinger arXiv preprint arXiv:2311.08539, 2023 | | 2023 |
| Protecting Publicly Available Data With Machine Learning Shortcuts NM Müller, M Burgert, P Debus, J Williams, P Sperl, K Böttinger arXiv preprint arXiv:2310.19381, 2023 | | 2023 |
Konstantin BöttingerFraunhofer AISECBestätigte E-Mail-Adresse bei aisec.fraunhofer.de
