Seguir
Sihui Dai
Sihui Dai
Dirección de correo verificada de princeton.edu
Título
Citado por
Citado por
Año
Robust learning meets generative models: Can proxy distributions improve adversarial robustness?
V Sehwag, S Mahloujifar, T Handina, S Dai, C Xiang, M Chiang, P Mittal
arXiv preprint arXiv:2104.09425, 2021
1092021
Neural Networks with Recurrent Generative Feedback
Y Huang, J Gornet, S Dai, Z Yu, T Nguyen, DY Tsao, A Anandkumar
arXiv preprint arXiv:2007.09200, 2020
402020
Improving adversarial robustness using proxy distributions
V Sehwag, S Mahloujifar, T Handina, S Dai, C Xiang, M Chiang, P Mittal
arXiv preprint arXiv:2104.09425, 2021
312021
Parameterizing Activation Functions for Adversarial Robustness
S Dai, S Mahloujifar, P Mittal
arXiv preprint arXiv:2110.05626, 2021
262021
Parameterizing activation functions for adversarial robustness. In 2022 IEEE Security and Privacy Workshops (SPW)
S Dai, S Mahloujifar, P Mittal
IEEE 2 (6), 8, 2022
72022
Out-of-Distribution Detection Using Neural Rendering Generative Models
Y Huang, S Dai, T Nguyen, RG Baraniuk, A Anandkumar
arXiv preprint arXiv:1907.04572, 2019
72019
Brain-inspired Robust Vision using Convolutional Neural Networks with Feedback
Y Huang, S Dai, T Nguyen, P Bao, D Tsao, RG Baraniuk, A Anandkumar
62019
Multi-task bayesian optimization via gaussian process upper confidence bound
S Dai, J Song, Y Yue
ICML 2020 Workshop on Real World Experiment Design and Active Learning, 2020
52020
Formulating Robustness Against Unforeseen Attacks
S Dai, S Mahloujifar, P Mittal
arXiv preprint arXiv:2204.13779, 2022
42022
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
S Dai, S Mahloujifar, C Xiang, V Sehwag, PY Chen, P Mittal
arXiv preprint arXiv:2302.10980, 2023
22023
Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker
S Dai, W Ding, AN Bhagoji, D Cullina, BY Zhao, H Zheng, P Mittal
arXiv preprint arXiv:2302.10722, 2023
12023
ROBUSTNESS FROM PERCEPTION
S Mahloujifar, C Xiang, V Sehwag, S Dai, P Mittal
1*
Lower Bounds on 0-1 Loss for Multi-class Classification with a Test-time Attacker
S Dai, W Ding, AN Bhagoji, D Cullina, P Mittal, BY Zhao
NeurIPS ML Safety Workshop, 2022
2022
Learner Knowledge Levels in Adversarial Machine Learning
S Dai, P Mittal
Neural Networks with Recurrent Generative Feedback
YHJGS Dai, ZYT Nguyen, DYTA Anandkumar
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–15