Zhang Jingfeng チャンジンフォン

Researcher Number	40909389
Other IDs
Affiliation (based on the past Project Information) *help	2023: 国立研究開発法人理化学研究所, 革新知能統合研究センター, 研究員 2022: 国立研究開発法人理化学研究所, 革新知能統合研究センター, 特別研究員
Review Section/Research Field	Principal Investigator Basic Section 61030:Intelligent informatics-related
Keywords	Principal Investigator imperfect training set / Adversarial robustness / robust algorithm / imperfect data / adversarial robustness / AI safety / Backdoor attack / Poisoning attack / Corrupted labels / Adversarial learning

Research Projects
(1 results)
Research Products
(6 results)

Adversarial robustness meets imperfect training setPrincipal Investigator
- Principal Investigator
  
  Zhang Jingfeng
- Project Period (FY)
  2022 – 2023
- Research Category
  
  Grant-in-Aid for Early-Career Scientists
- Review Section
  
  Basic Section 61030:Intelligent informatics-related
- Research Institution
  Institute of Physical and Chemical Research

All 2023 2022

All Journal Article Presentation

[Journal Article] On the Effectiveness of Adversarial Training Against Backdoor Attacks2023
- Author(s)
  Gao Yinghua、Wu Dongxian、Zhang Jingfeng、Gan Guanhao、Xia Shu-Tao、Niu Gang、Sugiyama Masashi
- Journal Title
  
  IEEE Transactions on Neural Networks and Learning Systems
  
  Volume: - Issue: 10 Pages: 1-11
- DOI
  10.1109/tnnls.2023.3281872
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-22K17955
[Journal Article] Decision Boundary-aware Data Augmentation for Adversarial Training2023
- Author(s)
  Chen Chen、Zhang Jingfeng、Xu Xilie、Lyu Lingjuan、Chen Chaochao、Hu Tianlei、Chen Gang
- Journal Title
  
  IEEE Transactions on Dependable and Secure Computing
  
  Volume: 20 Pages: 1882-1894
- DOI
  10.1109/tdsc.2022.3165889
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-22K17955
[Journal Article] Bilateral Dependency Optimization: Defending Against Model-Inversion Attacks2022
- Author(s)
  Peng Xiong, Liu Feng, Zhang Jingfeng, Lan Long, Ye Junjie, Liu Tongliang, Han Bo
- Journal Title
  
  Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
  
  Volume: 1 Pages: 13581367-13581367
- DOI
  10.1145/3534678.3539376
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-22K17955
[Journal Article] NoiLin: Improving adversarial training and correcting stereotype of noisy labels2022
- Author(s)
  Zhang Jingfeng, Xu Xilie, Han Bo, Liu Tongliang, Cui Lizhen, Niu Gang, Sugiyama Masashi
- Journal Title
  
  Transactions on Machine Learning Research
  
  Volume: 1 Pages: 1-12
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-22K17955
[Presentation] Synergy-of-Experts: Collaborate to Improve Adversarial Robustness2022
- Author(s)
  Cui Sen, ZHANG Jingfeng, Liang Jian, Han Bo, Sugiyama Masashi, Zhang Changshui
- Organizer
  36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022)
- Invited / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-22K17955
[Presentation] Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks2022
- Author(s)
  Zhou Jianan, Zhu Jianing, Zhang Jingfeng, Liu Tongliang, Niu Gang, Han Bo, Sugiyama Masashi
- Organizer
  36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022)
- Invited / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-22K17955

Zhang Jingfeng チャン ジンフォン

Research Projects

Research Products

Adversarial robustness meets imperfect training setPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

[Journal Article] On the Effectiveness of Adversarial Training Against Backdoor Attacks2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Decision Boundary-aware Data Augmentation for Adversarial Training2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Bilateral Dependency Optimization: Defending Against Model-Inversion Attacks2022

Author(s)

Journal Title

DOI

Data Source

[Journal Article] NoiLin: Improving adversarial training and correcting stereotype of noisy labels2022

Author(s)

Journal Title

Data Source

[Presentation] Synergy-of-Experts: Collaborate to Improve Adversarial Robustness2022

Author(s)

Organizer

Data Source

[Presentation] Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks2022

Author(s)

Organizer

Data Source

Zhang Jingfeng チャンジンフォン