Decision-based adversarial attacks: Reliable attacks against black-box machine learning models W Brendel, J Rauber, M Bethge arXiv preprint arXiv:1712.04248, 2017 | 172 | 2017 |
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness R Geirhos, P Rubisch, C Michaelis, M Bethge, FA Wichmann, W Brendel arXiv preprint arXiv:1811.12231, 2018 | 158 | 2018 |
Foolbox v0. 8.0: A python toolbox to benchmark the robustness of machine learning models J Rauber, W Brendel, M Bethge arXiv preprint arXiv:1707.04131 5, 2017 | 134 | 2017 |
Demixed principal component analysis of neural population data D Kobak, W Brendel, C Constantinidis, CE Feierstein, A Kepecs, ... Elife 5, e10989, 2016 | 133 | 2016 |
Approximating cnns with bag-of-local-features models works surprisingly well on imagenet W Brendel, M Bethge arXiv preprint arXiv:1904.00760, 2019 | 60 | 2019 |
On evaluating adversarial robustness N Carlini, A Athalye, N Papernot, W Brendel, J Rauber, D Tsipras, ... arXiv preprint arXiv:1902.06705, 2019 | 60 | 2019 |
Towards the first adversarially robust neural network model on MNIST L Schott, J Rauber, M Bethge, W Brendel arXiv preprint arXiv:1805.09190, 2018 | 57* | 2018 |
Instanton constituents and fermionic zero modes in twisted CPn models W Brendel, F Bruckmann, L Janssen, A Wipf, C Wozar Physics Letters B 676 (1-3), 116-125, 2009 | 54 | 2009 |
Demixed principal component analysis W Brendel, R Romo, CK Machens Advances in neural information processing systems, 2654-2662, 2011 | 43 | 2011 |
Texture synthesis using shallow convolutional networks with random filters I Ustyuzhaninov, W Brendel, LA Gatys, M Bethge arXiv preprint arXiv:1606.00021, 2016 | 30 | 2016 |
Adversarial vision challenge W Brendel, J Rauber, A Kurakin, N Papernot, B Veliqi, SP Mohanty, ... The NeurIPS'18 Competition, 129-153, 2020 | 14 | 2020 |
Comment on" Biologically inspired protection of deep networks from adversarial attacks" W Brendel, M Bethge arXiv preprint arXiv:1704.01547, 2017 | 13 | 2017 |
Unsupervised learning of an efficient short-term memory network P Vertechi, W Brendel, CK Machens Advances in Neural Information Processing Systems, 3653-3661, 2014 | 10 | 2014 |
Learning to represent signals spike by spike W Brendel, R Bourdoukan, P Vertechi, CK Machens, S Denéve arXiv preprint arXiv:1703.03777, 2017 | 9 | 2017 |
Covariant boost and structure functions of baryons in Gross-Neveu models W Brendel, M Thies Physical Review D 81 (8), 085002, 2010 | 9 | 2010 |
What does it take to generate natural textures? I Ustyuzhaninov, W Brendel, LA Gatys, M Bethge ICLR, 2017 | 8 | 2017 |
Comparing the ability of humans and DNNs to recognise closed contours in cluttered images CM Funke, J Borowski, TSA Wallis, W Brendel, AS Ecker, M Bethge 18th Annual Meeting of the Vision Sciences Society (VSS 2018), 800, 2018 | 3 | 2018 |
Biomechanical texture coding in rat whiskers M Oladazimi, W Brendel, C Schwarz Scientific reports 8 (1), 11139, 2018 | 3 | 2018 |
One-shot texture segmentation I Ustyuzhaninov, C Michaelis, W Brendel, M Bethge arXiv preprint arXiv:1807.02654, 2018 | 3 | 2018 |
Benchmarking robustness in object detection: Autonomous driving when winter is coming C Michaelis, B Mitzkus, R Geirhos, E Rusak, O Bringmann, AS Ecker, ... arXiv preprint arXiv:1907.07484, 2019 | 2 | 2019 |