| Fair diffusion: Instructing text-to-image generation models on fairness F Friedrich, M Brack, L Struppek, D Hintersdorf, P Schramowski, ... arXiv preprint arXiv:2302.10893, 2023 | 49 | 2023 |
| Learning to break deep perceptual hashing: The use case neuralhash L Struppek, D Hintersdorf, D Neider, K Kersting Proceedings of the 2022 ACM Conference on Fairness, Accountability, and …, 2022 | 36 | 2022 |
| Plug & play attacks: Towards robust and flexible model inversion attacks L Struppek, D Hintersdorf, ADA Correia, A Adler, K Kersting arXiv preprint arXiv:2201.12179, 2022 | 35 | 2022 |
| Sega: Instructing diffusion using semantic dimensions M Brack, F Friedrich, D Hintersdorf, L Struppek, P Schramowski, ... arXiv preprint arXiv:2301.12247 2 (6), 2023 | 34* | 2023 |
| Rickrolling the artist: Injecting invisible backdoors into text-guided image generation models L Struppek, D Hintersdorf, K Kersting arXiv preprint arXiv:2211.02408 6 (7), 2022 | 29* | 2022 |
| The biased artist: Exploiting cultural biases via homoglyphs in text-guided image generation models L Struppek, D Hintersdorf, K Kersting | 26 | 2022 |
| The stable artist: Steering semantics in diffusion latent space M Brack, P Schramowski, F Friedrich, D Hintersdorf, K Kersting arXiv preprint arXiv:2212.06013, 2022 | 18 | 2022 |
| To trust or not to trust prediction scores for membership inference attacks D Hintersdorf, L Struppek, K Kersting arXiv preprint arXiv:2111.09076, 2021 | 8 | 2021 |
| Does CLIP Know My Face? D Hintersdorf, L Struppek, K Kersting arXiv preprint arXiv:2209.07341, 2023 | 5* | 2023 |
| Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data L Struppek, MB Hentschel, C Poth, D Hintersdorf, K Kersting arXiv preprint arXiv:2310.06372, 2023 | 3 | 2023 |
| Defending Our Privacy With Backdoors D Hintersdorf, L Struppek, D Neider, K Kersting arXiv preprint arXiv:2310.08320, 2023 | 2 | 2023 |
| Exploring the Adversarial Capabilities of Large Language Models L Struppek, MH Le, D Hintersdorf, K Kersting arXiv preprint arXiv:2402.09132, 2024 | 1 | 2024 |
| Combining AI and AM–Improving approximate matching through transformer networks F Uhlig, L Struppek, D Hintersdorf, T Göbel, H Baier, K Kersting Forensic Science International: Digital Investigation 45, 301570, 2023 | 1 | 2023 |
| Image Classifiers Leak Sensitive Attributes About Their Classes L Struppek, D Hintersdorf, F Friedrich, M Brack, P Schramowski, ... arXiv preprint arXiv:2303.09289, 2023 | 1 | 2023 |
| Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks L Struppek, D Hintersdorf, K Kersting arXiv preprint arXiv:2310.06549, 2023 | | 2023 |
| Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models D Hintersdorf, L Struppek, K Kersting arXiv preprint arXiv:2308.09490, 2023 | | 2023 |
Kristian KerstingProfessor of AI & ML, TU Darmstadt, Co-Director hessian.ai, DFKI, Germany, CLAIRE & ELLISVerified email at cs.tu-darmstadt.de
