Keji Han

Postdoc, Nanjing University of Posts and Telecommunications

Joined

May 2021

Names

Keji Han (Preferred)

Emails

****@njupt.edu.cn (Confirmed)

Personal Links

Google Scholar

DBLP

ORCID

Career & Education History

Postdoc

Nanjing University of Posts and Telecommunications (njupt.edu.cn)

2023 – Present

PhD student

Nanjing University of Posts and Telecommunications (njupt.edu.cn)

2018 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Yun Li

2018 – 2023

Expertise

Adversarial Machine Learning

2017 – Present

Publications

Rethinking the validity of perturbation in single-step adversarial training
Yao Ge, Yun Li, Keji Han
- Pattern Recognit. 2025
- Readers: Everyone
DLR: Adversarial examples detection and label recovery for deep neural networks
Keji Han, Yao Ge, Ruchuan Wang, Yun Li
- Pattern Recognit. Lett. 2025
- Readers: Everyone
Feature-aware transferable adversarial attacks against image classification
Shuyan Cheng, Peng Li, Keji Han, He Xu
- Appl. Soft Comput. 2024
- Readers: Everyone
Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training
Yao Ge, Yun Li, Keji Han, Junyi Zhu, Xianzhong Long
- ICCV 2023
- Readers: Everyone
Attribution of Adversarial Attacks via Multi-task Learning
Zhongyi Guo, Keji Han, Yao Ge, Yun Li, Wei Ji
- ICONIP (2) 2023
- Readers: Everyone
Scalable Attribution of Adversarial Attacks via Multi-Task Learning
Zhongyi Guo, Keji Han, Yao Ge, Wei Ji, Yun Li
- Published: 01 Jan 2023, Last Modified: 13 Nov 2023
- CoRR 2023
- Readers: Everyone
(AD)2: Adversarial domain adaptation to defense with adversarial perturbation removal
Keji Han, Bin Xia, Yun Li
- 2022 (modified: 12 Nov 2022)
- Pattern Recognit. 2022
- Readers: Everyone
Transferable Interpolated Adversarial Attack with Random-Layer Mixup
Size Ma, Keji Han, Xianzhong Long, Yun Li
- 2022 (modified: 12 Nov 2022)
- PAKDD (2) 2022
- Readers: Everyone
Is It Time to Redefine the Classification Task for Deep Learning Systems?
Keji Han, Yun Li, Songcan Chen
- Published: 22 Jun 2021, Last Modified: 05 May 2023
- ICML 2021 Workshop AML Oral
- Readers: Everyone
Ensemble adversarial black-box attacks against deep learning systems
Jie Hang, Keji Han, Hui Chen, Yun Li
- 2020 (modified: 12 Nov 2022)
- Pattern Recognit. 2020
- Readers: Everyone

View all 15 publications