Följ
Ping-yeh Chiang
Ping-yeh Chiang
Verifierad e-postadress på cs.umd.edu
Titel
Citeras av
Citeras av
År
Certified defenses for adversarial patches
P Chiang, R Ni, A Abdelkader, C Zhu, C Studor, T Goldstein
8th International Conference on Learning Representations (ICLR 2020), 2020
1502020
Adversarial examples make strong poisons
L Fowl, M Goldblum, P Chiang, J Geiping, W Czaja, T Goldstein
Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 2021
892021
Compressing gans using knowledge distillation
A Aguinaldo, PY Chiang, A Gain, A Patil, K Pearson, S Feizi
arXiv preprint arXiv:1902.00159, 2019
892019
Detection as Regression: Certified Object Detection by Median Smoothing
P Chiang, MJ Curry, A Abdelkader, A Kumar, J Dickerson, T Goldstein
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020), 2020
462020
Can neural nets learn the same model twice? investigating reproducibility and double descent from the decision boundary perspective
G Somepalli, L Fowl, A Bansal, P Yeh-Chiang, Y Dar, R Baraniuk, ...
Proceedings of the ieee/cvf conference on computer vision and pattern …, 2022
422022
Preventing unauthorized use of proprietary data: Poisoning for secure dataset release
L Fowl, P Chiang, M Goldblum, J Geiping, A Bansal, W Czaja, T Goldstein
arXiv preprint arXiv:2103.02683, 2021
342021
Certifying Strategyproof Auction Networks
MJ Curry, PY Chiang, T Goldstein, J Dickerson
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020), 2020
322020
Active Learning at the ImageNet Scale
ZA Sami Emam, HM Chu, PY Chiang, W Czaja, R Leapman, M Goldblum, ...
arXiv e-prints, arXiv: 2111.12880, 2021
27*2021
Certified neural network watermarks with randomized smoothing
A Bansal, P Chiang, MJ Curry, R Jain, C Wigington, V Manjunatha, ...
International Conference on Machine Learning, 1450-1465, 2022
262022
Wrapnet: Neural net inference with ultra-low-precision arithmetic
R Ni, H Chu, O Castaneda, P Chiang, C Studer, T Goldstein
International Conference on Learning Representations, 2020
25*2020
Proportionnet: Balancing fairness and revenue for auction design with deep learning
K Kuo, A Ostuni, E Horishny, MJ Curry, S Dooley, P Chiang, T Goldstein, ...
arXiv preprint arXiv:2010.06398, 2020
242020
Baseline defenses for adversarial attacks against aligned language models
N Jain, A Schwarzschild, Y Wen, G Somepalli, J Kirchenbauer, P Chiang, ...
arXiv preprint arXiv:2309.00614, 2023
182023
Witchcraft: Efficient PGD attacks with random step size
PY Chiang, J Geiping, M Goldblum, T Goldstein, R Ni, S Reich, A Shafahi
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
142020
Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent
P Chiang, R Ni, DY Miller, A Bansal, J Geiping, M Goldblum, T Goldstein
International Conference on Learning Representations, 2023
112023
Neftune: Noisy embeddings improve instruction finetuning
N Jain, P Chiang, Y Wen, J Kirchenbauer, HM Chu, G Somepalli, ...
arXiv preprint arXiv:2310.05914, 2023
82023
Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, and Tom Goldstein. 2023. NEFTune: Noisy embeddings improve instruction finetuning
N Jain, P yeh Chiang, Y Wen, J Kirchenbauer, HM Chu, G Somepalli, ...
arXiv preprint arXiv:2310.05914, 0
7
K-sam: Sharpness-aware minimization at the speed of sgd
R Ni, P Chiang, J Geiping, M Goldblum, AG Wilson, T Goldstein
arXiv preprint arXiv:2210.12864, 2022
42022
Improving the tightness of convex relaxation bounds for training certifiably robust classifiers
C Zhu, R Ni, P Chiang, H Li, F Huang, T Goldstein
arXiv preprint arXiv:2002.09766, 2020
22020
Protecting proprietary data: Poisoning for secure dataset release
LH Fowl, P Chiang, M Goldblum, J Geiping, AA Bansal, W Czaja, ...
12021
Universal Pyramid Adversarial Training for Improved ViT Performance
P Chiang, Y Zhou, O Poursaeed, SN Shukla, A Shah, T Goldstein, SN Lim
arXiv preprint arXiv:2312.16339, 2023
2023
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20