| Sparse-rs: a versatile framework for query-efficient sparse black-box adversarial attacks F Croce, M Andriushchenko, ND Singh, N Flammarion, M Hein AAAI 2022, 2022 | 118 | 2022 |
| Revisiting adversarial training for imagenet: Architectures, training and generalization across threat models ND Singh, F Croce, M Hein Advances in Neural Information Processing Systems 36, 2023 | 57 | 2023 |
| Robust clip: Unsupervised adversarial fine-tuning of vision embeddings for robust large vision-language models C Schlarmann, ND Singh, F Croce, M Hein ICML 2024, 2024 | 26 | 2024 |
| Clustering and learning from imbalanced data ND Singh, A Dhall NeurIPS 2018 AI4Fin Workshop, 2018 | 26 | 2018 |
| Towards reliable evaluation and fast training of robust semantic segmentation models F Croce, ND Singh, M Hein European Conference on Computer Vision, 180-197, 2025 | 8* | 2025 |
| Adversarially Robust CLIP Models Induce Better (Robust) Perceptual Metrics F Croce, C Schlarmann, ND Singh, M Hein ICML 2024 Workshop on Foundation Models in the Wild, 2024 | 3 | 2024 |
| Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP ND Singh, F Croce, M Hein arXiv preprint arXiv:2412.00727, 2024 | | 2024 |
Matthias HeinProfessor of Computer Science, University of TübingenDirección de correo verificada de uni-tuebingen.de