| Deep anomaly detection with outlier exposure D Hendrycks, M Mazeika, T Dietterich arXiv preprint arXiv:1812.04606, 2018 | 1468 | 2018 |
| Measuring massive multitask language understanding D Hendrycks, C Burns, S Basart, A Zou, M Mazeika, D Song, J Steinhardt arXiv preprint arXiv:2009.03300, 2020 | 1112 | 2020 |
| Using self-supervised learning can improve model robustness and uncertainty D Hendrycks, M Mazeika, S Kadavath, D Song Advances in neural information processing systems 32, 2019 | 959 | 2019 |
| Using pre-training can improve model robustness and uncertainty D Hendrycks, K Lee, M Mazeika International Conference on Machine Learning, 2712-2721, 2019 | 751 | 2019 |
| Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ... arXiv preprint arXiv:2206.04615, 2022 | 734 | 2022 |
| Using trusted data to train deep networks on labels corrupted by severe noise D Hendrycks, M Mazeika, D Wilson, K Gimpel Advances in neural information processing systems 31, 2018 | 595 | 2018 |
| Scaling out-of-distribution detection for real-world settings D Hendrycks, S Basart, M Mazeika, M Mostajabi, J Steinhardt, D Song arXiv preprint arXiv:1911.11132, 2019 | 306 | 2019 |
| Measuring coding challenge competence with apps D Hendrycks, S Basart, S Kadavath, M Mazeika, A Arora, E Guo, C Burns, ... arXiv preprint arXiv:2105.09938, 2021 | 291 | 2021 |
| Decodingtrust: A comprehensive assessment of trustworthiness in gpt models B Wang, W Chen, H Pei, C Xie, M Kang, C Zhang, C Xu, Z Xiong, R Dutta, ... arXiv preprint arXiv:2306.11698, 2023 | 112 | 2023 |
| Pixmix: Dreamlike pictures comprehensively improve safety measures D Hendrycks, A Zou, M Mazeika, L Tang, B Li, D Song, J Steinhardt Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 87 | 2022 |
| A benchmark for anomaly segmentation D Hendrycks, S Basart, M Mazeika, M Mostajabi, J Steinhardt, D Song | 66 | 2019 |
| An overview of catastrophic ai risks D Hendrycks, M Mazeika, T Woodside arXiv preprint arXiv:2306.12001, 2023 | 65 | 2023 |
| Representation engineering: A top-down approach to ai transparency A Zou, L Phan, S Chen, J Campbell, P Guo, R Ren, A Pan, X Yin, ... arXiv preprint arXiv:2310.01405, 2023 | 64 | 2023 |
| X-risk analysis for ai research D Hendrycks, M Mazeika arXiv preprint arXiv:2206.05862, 2022 | 53 | 2022 |
| What would jiminy cricket do? towards agents that behave morally D Hendrycks, M Mazeika, A Zou, S Patel, C Zhu, J Navarro, D Song, B Li, ... arXiv preprint arXiv:2110.13136, 2021 | 44 | 2021 |
| Forecasting Future World Events with Neural Networks A Zou, T Xiao, R Jia, J Kwon, M Mazeika, R Li, D Song, J Steinhardt, ... arXiv preprint arXiv:2206.15474, 2022 | 13 | 2022 |
| How to steer your adversary: Targeted and efficient model stealing defenses with gradient redirection M Mazeika, B Li, D Forsyth International Conference on Machine Learning, 15241-15254, 2022 | 12 | 2022 |
| How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios M Mazeika, E Tang, A Zou, S Basart, JS Chan, D Song, D Forsyth, ... arXiv preprint arXiv:2210.10039, 2022 | 8 | 2022 |
| The trojan detection challenge M Mazeika, D Hendrycks, H Li, X Xu, S Hough, A Zou, A Rajabi, Q Yao, ... NeurIPS 2022 Competition Track, 279-291, 2022 | 5 | 2022 |
| The singular value decomposition and low rank approximation M Maezika Technical Report, 2016 | 5 | 2016 |
Dan HendrycksDirector of the Center for AI SafetyVerified email at berkeley.edu
