| Scaling language models: Methods, analysis & insights from training gopher JW Rae, S Borgeaud, T Cai, K Millican, J Hoffmann, F Song, J Aslanides, ... arXiv preprint arXiv:2112.11446, 2021 | 831 | 2021 |
| Ethical and social risks of harm from language models L Weidinger, J Mellor, M Rauh, C Griffin, J Uesato, PS Huang, M Cheng, ... arXiv preprint arXiv:2112.04359, 2021 | 658 | 2021 |
| Adversarial risk and the dangers of evaluating against weak attacks J Uesato, B O’donoghue, P Kohli, A Oord International Conference on Machine Learning, 5025-5034, 2018 | 631 | 2018 |
| On the effectiveness of interval bound propagation for training verifiably robust models S Gowal, K Dvijotham, R Stanforth, R Bunel, C Qin, J Uesato, ... arXiv preprint arXiv:1810.12715, 2018 | 496 | 2018 |
| Robustfill: Neural program learning under noisy i/o J Devlin, J Uesato, S Bhupatiraju, R Singh, A Mohamed, P Kohli International conference on machine learning, 990-998, 2017 | 436 | 2017 |
| Technical report on the cleverhans v2. 1.0 adversarial examples library N Papernot, F Faghri, N Carlini, I Goodfellow, R Feinman, A Kurakin, ... arXiv preprint arXiv:1610.00768, 2016 | 401 | 2016 |
| Taxonomy of risks posed by language models L Weidinger, J Uesato, M Rauh, C Griffin, PS Huang, J Mellor, A Glaese, ... Proceedings of the 2022 ACM Conference on Fairness, Accountability, and …, 2022 | 372 | 2022 |
| Are labels required for improving adversarial robustness? JB Alayrac, J Uesato, PS Huang, A Fawzi, R Stanforth, P Kohli Advances in Neural Information Processing Systems 32, 2019 | 348 | 2019 |
| Robustness via curvature regularization, and vice versa SM Moosavi-Dezfooli, A Fawzi, J Uesato, P Frossard Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019 | 334 | 2019 |
| Improving alignment of dialogue agents via targeted human judgements A Glaese, N McAleese, M Trębacz, J Aslanides, V Firoiu, T Ewalds, ... arXiv preprint arXiv:2209.14375, 2022 | 332 | 2022 |
| Uncovering the limits of adversarial training against norm-bounded adversarial examples S Gowal, C Qin, J Uesato, T Mann, P Kohli arXiv preprint arXiv:2010.03593, 2020 | 312 | 2020 |
| Scalable verified training for provably robust image classification S Gowal, KD Dvijotham, R Stanforth, R Bunel, C Qin, J Uesato, ... Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019 | 173 | 2019 |
| Training verified learners with learned verifiers K Dvijotham, S Gowal, R Stanforth, R Arandjelovic, B O'Donoghue, ... arXiv preprint arXiv:1805.10265, 2018 | 173 | 2018 |
| Challenges in detoxifying language models J Welbl, A Glaese, J Uesato, S Dathathri, J Mellor, LA Hendricks, ... arXiv preprint arXiv:2109.07445, 2021 | 167 | 2021 |
| Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming S Dathathri, K Dvijotham, A Kurakin, A Raghunathan, J Uesato, RR Bunel, ... Advances in Neural Information Processing Systems 33, 5318-5331, 2020 | 108 | 2020 |
| Specification gaming: the flip side of AI ingenuity V Krakovna, J Uesato, V Mikulik, M Rahtz, T Everitt, R Kumar, Z Kenton, ... DeepMind Blog 3, 2020 | 93 | 2020 |
| Solving math word problems with process-and outcome-based feedback J Uesato, N Kushman, R Kumar, F Song, N Siegel, L Wang, A Creswell, ... arXiv preprint arXiv:2211.14275, 2022 | 89 | 2022 |
| Cyprien de Masson d’Autume JW Rae, S Borgeaud, T Cai, K Millican, J Hoffmann, F Song, J Aslanides, ... | 86 | 2021 |
| An alternative surrogate loss for pgd-based adversarial testing S Gowal, J Uesato, C Qin, PS Huang, T Mann, P Kohli arXiv preprint arXiv:1910.09338, 2019 | 80 | 2019 |
| Rigorous agent evaluation: An adversarial approach to uncover catastrophic failures J Uesato, A Kumar, C Szepesvari, T Erez, A Ruderman, K Anderson, ... arXiv preprint arXiv:1812.01647, 2018 | 76 | 2018 |
