Reverse Engineering of Imperceptible Adversarial Image Perturbations
- Yuguang Yao
- Yifan Gong
- et al.
- 2022
- ICLR 2022
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
16 results for Xue Lin
MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
- Geng Yuan
- Xialong Ma
- et al.
- 2021
- NeurIPS 2021
Towards certificated model robustness against weight perturbations
- Tsui Wei Weng
- Pu Zhao
- et al.
- 2020
- AAAI 2020
Towards query-efficient black-box adversary with zeroth-order natural gradient descent
- Pu Zhao
- Pin-Yu Chen
- et al.
- 2020
- AAAI 2020
ZO-AdaMM: Zeroth-order adaptive momentum method for black-box optimization
- Xiangyi Chen
- Sijia Liu
- et al.
- 2019
- NeurIPS 2019
Structured adversarial attack: Towards general implementation and better interpretability
- Kaidi Xu
- Sijia Liu
- et al.
- 2019
- ICLR 2019
StructADMM: Achieving Ultrahigh Efficiency in Structured Pruning for DNNs
- Tianyun Zhang
- Shaokai Ye
- et al.
- 2022
- IEEE TNNLS
Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations
- Pu Zhao
- Parikshit Ram
- et al.
- 2022
- IJCAI 2022
Towards an efficient and general framework of robust training for graph neural networks
- Kaidi Xu
- Sijia Liu
- et al.
- 2020
- ICASSP 2020
AdvMS: A Multi-Source Multi-Cost Defense Against Adversarial Attacks
- Xiao Wang
- Siyue Wang
- et al.
- 2020
- ICASSP 2020