| Gan-leaks: A taxonomy of membership inference attacks against gans D Chen, N Yu, Y Zhang, M Fritz The ACM Conference on Computer and Communications Security (CCS) 2020, 2019 | 569* | 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 | 519 | 2021 |
| Gs-wgan: A gradient-sanitized approach for learning differentially private generators D Chen, T Orekondy, M Fritz Advances in Neural Information Processing Systems (NeurIPS) 2020, 2020 | 250 | 2020 |
| Responsible disclosure of generative models using scalable fingerprinting N Yu, V Skripniuk, D Chen, L Davis, M Fritz International Conference on Learning Representations (ICLR) 2022, 2020 | 128 | 2020 |
| Relaxloss: Defending membership inference attacks without losing utility D Chen, N Yu, M Fritz International Conference on Learning Representations (ICLR) 2022, 2022 | 85 | 2022 |
| Private Set Generation with Discriminative Information D Chen, R Kerkouche, M Fritz Neural Information Processing Systems (NeurIPS), 2022 | 55 | 2022 |
| Privacy considerations for sharing genomics data M Oestreich, D Chen, JL Schultze, M Fritz, M Becker EXCLI journal 20, 1243, 2021 | 48 | 2021 |
| Data forensics in diffusion models: A systematic analysis of membership privacy D Zhu*, D Chen*, J Grossklags, M Fritz arXiv preprint arXiv:2302.07801, 2023 | 22 | 2023 |
| PoLLMgraph: Unraveling hallucinations in large language models via state transition dynamics D Zhu, D Chen, Q Li, Z Chen, L Ma, J Grossklags, M Fritz In Findings of the Association for Computational Linguistics: NAACL, 2024 | 21 | 2024 |
| Fedlap-dp: Federated learning by sharing differentially private loss approximations HP Wang, D Chen, R Kerkouche, M Fritz Proceedings on Privacy Enhancing Technologies (PETs), 2023 | 15* | 2023 |
| MargCTGAN: A "Marginally'' Better CTGAN for the Low Sample Regime T Afonja, D Chen, M Fritz German Conference on Pattern Recognition (GCPR), 2023 | 12 | 2023 |
| Towards biologically plausible and private gene expression data generation D Chen, M Oestreich, T Afonja, R Kerkouche, M Becker, M Fritz Proceedings on Privacy Enhancing Technologies (PETs), 2024 | 10 | 2024 |
| Privauditor: Benchmarking data protection vulnerabilities in llm adaptation techniques D Zhu, D Chen, X Wu, J Geng, Z Li, J Grossklags, L Ma Advances in Neural Information Processing Systems 37, 9668-9689, 2024 | 8 | 2024 |
| A unified view of differentially private deep generative modeling D Chen, R Kerkouche, M Fritz Transactions on Machine Learning Research, 2024 | 7 | 2024 |
| Inside the black box: Detecting data leakage in pre-trained language encoders Y Xin, Z Li, N Yu, D Chen, M Fritz, M Backes, Y Zhang European Conference on Artificial Intelligence (ECAI), 2024 | 4 | 2024 |
| Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing Y Xin, D Chen, M Backes, X Zhang International Conference on Machine Learning (ICML), 2025 | | 2025 |
| Towards privacy-preserving machine learning: generative modeling and discriminative analysis D Chen Saarländische Universitäts-und Landesbibliothek, 2023 | | 2023 |
Mario FritzFaculty CISPA Helmholtz Center for Information Security; Professor Saarland UniversityVerified email at cispa.de
