Следене
Linyi Li
Заглавие
Позовавания
Позовавания
Година
Sok: Certified robustness for deep neural networks
L Li, T Xie, B Li
IEEE Symposium on Security & Privacy, May 2023, 2020
1602020
General Cutting Planes for Bound-Propagation-Based Neural Network Verification
H Zhang*, S Wang*, K Xu*, L Li, B Li, S Jana, CJ Hsieh, JZ Kolter
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
852022
Influence-directed explanations for deep convolutional networks
K Leino, S Sen, A Datta, M Fredrikson, L Li
2018 IEEE international test conference (ITC), 1-8, 2018
832018
Tss: Transformation-specific smoothing for robustness certification
L Li*, M Weber*, X Xu, L Rimanic, B Kailkhura, T Xie, C Zhang, B Li
Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications …, 2021
64*2021
TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
Z Yang*, L Li*, X Xu*, S Zuo, Q Chen, B Rubinstein, C Zhang, B Li
Thirty-Fifth Conference on Neural Information Processing Systems. 2021, 2021
57*2021
Crop: Certifying robust policies for reinforcement learning through functional smoothing
F Wu, L Li, Z Huang, Y Vorobeychik, D Zhao, B Li
International Conference on Learning Representations (ICLR) 2022, 2021
522021
On the certified robustness for ensemble models and beyond
Z Yang*, L Li*, X Xu, B Kailkhura, T Xie, B Li
International Conference on Learning Representations (ICLR) 2022, 2021
502021
COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks
F Wu*, L Li*, C Xu, H Zhang, B Kailkhura, K Kenthapadi, D Zhao, B Li
International Conference on Learning Representations (ICLR) 2022, 2022
302022
LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness
X Xu, L Li, B Li
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
252022
Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
H Li*, L Li*, X Xu, X Zhang, S Yang, B Li
International Conference on Artificial Intelligence and Statistics (AISTATS …, 2021
24*2021
A model-based framework for cloud API testing
J Wang, X Bai, L Li, Z Ji, H Ma
2017 IEEE 41st Annual Computer Software and Applications Conference (COMPSAC …, 2017
222017
Progressive-scale boundary blackbox attack via projective gradient estimation
J Zhang*, L Li*, H Li, X Zhang, S Yang, B Li
International Conference on Machine Learning (ICML), 12479-12490, 2021
202021
Fairness in Federated Learning via Core-Stability
BR Chaudhury, L Li, M Kang, B Li, R Mehta
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
19*2022
Double Sampling Randomized Smoothing
L Li, J Zhang, T Xie, B Li
International Conference on Machine Learning (ICML) 2022, 2022
192022
Robustra: Training Provable Robust Neural Networks over Reference Adversarial Space
L Li*, Z Zhong*, B Li, T Xie
Proceedings of the Twenty-Eighth International Joint Conference on …, 2019
182019
Certifying Out-of-Domain Generalization for Blackbox Functions
M Weber, L Li, B Wang, Z Zhao, B Li, C Zhang
International Conference on Machine Learning (ICML) 2022, 2022
152022
TPC: Transformation-Specific Smoothing for Point Cloud Models
W Chu, L Li, B Li
International Conference on Machine Learning (ICML) 2022, 2022
152022
Clustering test steps in natural language toward automating test automation
L Li, Z Li, W Zhang, J Zhou, P Wang, J Wu, G He, X Zeng, Y Deng, T Xie
Proceedings of the 28th ACM Joint Meeting on European Software Engineering …, 2020
142020
Certifying Some Distributional Fairness with Subpopulation Decomposition
M Kang*, L Li*, M Weber, Y Liu, C Zhang, B Li
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
132022
On the limitations of denoising strategies as adversarial defenses
Z Niu, Z Chen, L Li, Y Yang, B Li, J Yi
arXiv preprint arXiv:2012.09384, 2020
132020
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20