Towards certificated model robustness against weight perturbations
- Tsui Wei Weng
- Pu Zhao
- et al.
- 2020
- AAAI 2020
Publications
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.
Date
Featured collections
Popular topics
7 results for Pu Zhao
Towards query-efficient black-box adversary with zeroth-order natural gradient descent
- Pu Zhao
- Pin-Yu Chen
- et al.
- 2020
- AAAI 2020
Structured adversarial attack: Towards general implementation and better interpretability
- Kaidi Xu
- Sijia Liu
- et al.
- 2019
- ICLR 2019
Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations
- Pu Zhao
- Parikshit Ram
- et al.
- 2022
- IJCAI 2022
On the design of black-box adversarial examples by leveraging gradient-free optimization and operator splitting method
- Pu Zhao
- Sijia Liu
- et al.
- 2019
- ICCV 2019
ADMM attack: An enhanced adversarial attack for deep neural networks with undetectable distortions
- Pu Zhao
- Kaidi Xu
- et al.
- 2019
- ASP-DAC 2019
An ADMM-based universal framework for adversarial attacks on deep neural networks
- Pu Zhao
- Yanzhi Wang
- et al.
- 2018
- MM 2018