| Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models A Salem, Y Zhang, M Humbert, P Berrang, M Fritz, M Backes Annual Network and Distributed System Security Symposium (NDSS), 2019 | 969 | 2019 |
| MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples J Jia, A Salem, M Backes, Y Zhang, NZ Gong ACM SIGSAC Conference on Computer and Communications Security (CCS), 2019 | 408 | 2019 |
| Badnl: Backdoor attacks against nlp models with semantic-preserving improvements X Chen, A Salem, D Chen, M Backes, S Ma, Q Shen, Z Wu, Y Zhang Proceedings of the 37th Annual Computer Security Applications Conference …, 2021 | 357 | 2021 |
| Dynamic backdoor attacks against machine learning models A Salem, R Wen, M Backes, S Ma, Y Zhang 2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P), 703-718, 2022 | 306 | 2022 |
| Updates-leak: Data set inference and reconstruction attacks in online learning A Salem, A Bhattacharya, M Backes, M Fritz, Y Zhang USENIX Security Symposium, 2019 | 273 | 2019 |
| Analyzing leakage of personally identifiable information in language models N Lukas, A Salem, R Sim, S Tople, L Wutschitz, S Zanella-Béguelin 2023 IEEE Symposium on Security and Privacy (SP), 346-363, 2023 | 136 | 2023 |
| {ML-Doctor}: Holistic risk assessment of inference attacks against machine learning models Y Liu, R Wen, X He, A Salem, Z Zhang, M Backes, E De Cristofaro, M Fritz, ... 31st USENIX Security Symposium (USENIX Security 22), 4525-4542, 2022 | 129 | 2022 |
| Mlcapsule: Guarded offline deployment of machine learning as a service L Hanzlik, Y Zhang, K Grosse, A Salem, M Augustin, M Backes, M Fritz Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021 | 123 | 2021 |
| Baaan: Backdoor attacks against autoencoder and gan-based machine learning models A Salem, Y Sautter, M Backes, M Humbert, Y Zhang arXiv preprint arXiv:2010.03007, 2020 | 38 | 2020 |
| Don't trigger me! a triggerless backdoor attack against deep neural networks A Salem, M Backes, Y Zhang arXiv preprint arXiv:2010.03282, 2020 | 36 | 2020 |
| Bayesian estimation of differential privacy S Zanella-Beguelin, L Wutschitz, S Tople, A Salem, V Rühle, A Paverd, ... International Conference on Machine Learning, 40624-40636, 2023 | 33 | 2023 |
| Get a model! model hijacking attack against machine learning models A Salem, M Backes, Y Zhang arXiv preprint arXiv:2111.04394, 2021 | 30 | 2021 |
| SoK: Let the privacy games begin! A unified treatment of data inference privacy in machine learning A Salem, G Cherubin, D Evans, B Köpf, A Paverd, A Suri, S Tople, ... 2023 IEEE Symposium on Security and Privacy (SP), 327-345, 2023 | 29 | 2023 |
| Privacy-preserving similar patient queries for combined biomedical data A Salem, P Berrang, M Humbert, M Backes Proceedings on Privacy Enhancing Technologies, 2019 | 21 | 2019 |
| {UnGANable}: Defending against {GAN-based} face manipulation Z Li, N Yu, A Salem, M Backes, M Fritz, Y Zhang 32nd USENIX Security Symposium (USENIX Security 23), 7213-7230, 2023 | 18 | 2023 |
| Great, now write an article about that: The crescendo multi-turn llm jailbreak attack M Russinovich, A Salem, R Eldan arXiv preprint arXiv:2404.01833, 2024 | 16 | 2024 |
| {Two-in-One}: A Model Hijacking Attack Against Text Generation Models WM Si, M Backes, Y Zhang, A Salem 32nd USENIX Security Symposium (USENIX Security 23), 2223-2240, 2023 | 14 | 2023 |
| Rethinking privacy in machine learning pipelines from an information flow control perspective L Wutschitz, B Köpf, A Paverd, S Rajmohan, A Salem, S Tople, ... arXiv preprint arXiv:2311.15792, 2023 | 8 | 2023 |
| Last one standing: A comparative analysis of security and privacy of soft prompt tuning, lora, and in-context learning R Wen, T Wang, M Backes, Y Zhang, A Salem arXiv preprint arXiv:2310.11397, 2023 | 5 | 2023 |
| Maatphor: Automated variant analysis for prompt injection attacks A Salem, A Paverd, B Köpf arXiv preprint arXiv:2312.11513, 2023 | 4 | 2023 |
Michael BackesChairman and Founding Director of the CISPA Helmholtz Center for Information SecurityVerified email at cispa.saarland
