Helper-based adversarial training: Reducing excessive margin to achieve a better accuracy vs. robustness trade-off R Rade, SM Moosavi-Dezfooli ICML 2021 Workshop on Adversarial Machine Learning, 2021 | 66 | 2021 |
Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off R Rade, SM Moosavi-Dezfooli International Conference on Learning Representations (ICLR), 2022, 2021 | 64 | 2021 |
This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks A Hoffmann*, C Fanconi*, R Rade*, J Kohler ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend …, 2021 | 50 | 2021 |
PRIME: A Few Primitives Can Boost Robustness to Common Corruptions A Modas*, R Rade*, G Ortiz-Jiménez, SM Moosavi-Dezfooli, P Frossard European Conference on Computer Vision (ECCV), 2022, 2021 | 37 | 2021 |
Attacker behaviour profiling using stochastic ensemble of hidden Markov models S Deshmukh, R Rade, DF Kazi arXiv preprint arXiv:1905.11824, 2019 | 14 | 2019 |
Tackling toxic online communication with recurrent capsule networks S Deshmukh, R Rade 2018 Conference on Information and Communication Technology (CICT), 1-7, 2018 | 10 | 2018 |
Temporal and stochastic modelling of attacker behaviour R Rade, S Deshmukh, R Nene, AS Wadekar, A Unny Advances in Data Science: Third International Conference on Intelligent …, 2019 | 6 | 2019 |