Follow
Hadi Salman
Hadi Salman
OpenAI, MIT
Verified email at mit.edu - Homepage
Title
Cited by
Cited by
Year
Provably robust deep learning via adversarially trained smoothed classifiers
H Salman, J Li, I Razenshteyn, P Zhang, H Zhang, S Bubeck, G Yang
Advances in Neural Information Processing Systems, 11289-11300, 2019
5202019
Do adversarially robust imagenet models transfer better?
H Salman, A Ilyas, L Engstrom, A Kapoor, A Madry
Advances in Neural Information Processing Systems 33, 2020
3942020
A convex relaxation barrier to tight robustness verification of neural networks
H Salman, G Yang, H Zhang, CJ Hsieh, P Zhang
Advances in Neural Information Processing Systems, 9832-9842, 2019
253*2019
Robustness (python library), 2019
L Engstrom, A Ilyas, H Salman, S Santurkar, D Tsipras
URL https://github. com/MadryLab/robustness 4 (4), 4.3, 0
197*
Randomized smoothing of all shapes and sizes
G Yang, T Duan, JE Hu, H Salman, I Razenshteyn, J Li
International Conference on Machine Learning, 10693-10705, 2020
1792020
Denoised smoothing: A provable defense for pretrained classifiers
H Salman, M Sun, G Yang, A Kapoor, JZ Kolter
Advances in Neural Information Processing Systems, 2020
1352020
A fine-grained spectral perspective on neural networks
G Yang, H Salman
arXiv preprint arXiv:1907.10599, 2019
912019
Ergodic coverage in constrained environments using stochastic trajectory optimization
E Ayvali, H Salman, H Choset
2017 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2017
592017
Certified patch robustness via smoothed vision transformers
H Salman, S Jain, E Wong, A Madry
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2022
522022
3db: A framework for debugging computer vision models
G Leclerc, H Salman, A Ilyas, S Vemprala, L Engstrom, V Vineet, K Xiao, ...
Advances in Neural Information Processing Systems 35, 8498-8511, 2022
432022
FFCV: Accelerating Training by Removing Data Bottlenecks
G Leclerc, A Ilyas, L Engstrom, SM Park, H Salman, A Madry
43*2022
Unadversarial examples: Designing objects for robust vision
H Salman, A Ilyas, L Engstrom, S Vemprala, A Madry, A Kapoor
Thirty-Fifth Conference on Neural Information Processing Systems, 2021
422021
Learning to sequence robot behaviors for visual navigation
H Salman, P Singhal, T Shankar, P Yin, A Salman, W Paivine, G Sartoretti, ...
arXiv preprint arXiv:1803.01446, 2018
40*2018
Raising the cost of malicious ai-powered image editing
H Salman, A Khaddaj, G Leclerc, A Ilyas, A Madry
arXiv preprint arXiv:2302.06588, 2023
362023
Deep diffeomorphic normalizing flows
H Salman, P Yadollahpour, T Fletcher, K Batmanghelich
arXiv preprint arXiv:1810.03256, 2018
262018
A data-based perspective on transfer learning
S Jain, H Salman, A Khaddaj, E Wong, SM Park, A Mądry
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
252023
Causalcity: Complex simulations with agency for causal discovery and reasoning
D McDuff, Y Song, J Lee, V Vineet, S Vemprala, NA Gyde, H Salman, ...
Conference on Causal Learning and Reasoning, 559-575, 2022
242022
Trajectory-optimized sensing for active search of tissue abnormalities in robotic surgery
H Salman, E Ayvali, RA Srivatsan, Y Ma, N Zevallos, R Yasin, L Wang, ...
2018 IEEE International Conference on Robotics and Automation (ICRA), 5356-5363, 2018
242018
When does bias transfer in transfer learning?
H Salman, S Jain, A Ilyas, L Engstrom, E Wong, A Madry
arXiv preprint arXiv:2207.02842, 2022
212022
Missingness bias in model debugging
S Jain, H Salman, E Wong, P Zhang, V Vineet, S Vemprala, A Madry
arXiv preprint arXiv:2204.08945, 2022
212022
The system can't perform the operation now. Try again later.
Articles 1–20