World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
42
Citations
10362
World Ranking
8232
National Ranking
3530

Overview

Jinfeng Yi is a researcher affiliated with IBM in the United States, with a primary focus on computer science and its applied domains. Their work reflects a strong emphasis on artificial intelligence, with significant contributions spanning several subfields including computer vision and pattern recognition, cancer research, molecular biology, and signal processing.

Their recent scholarly output includes publications on topics such as adversarial robustness, privacy-preserving technologies, and advanced neural network applications. Notable papers authored or co-authored by Yi include:

  • Trustworthy AI: From Principles to Practices (2022) published in ACM Computing Surveys
  • On the Convergence and Robustness of Adversarial Training (2021) published in arXiv (Cornell University)
  • Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples (2020) published in the Proceedings of the AAAI Conference on Artificial Intelligence
  • Creatine kinase B suppresses ferroptosis by phosphorylating GPX4 through a moonlighting function (2023) published in Nature Cell Biology
  • Federated User Modeling from Hierarchical Information (2023) published in ACM Transactions on Information Systems

Yi's extensive publication record includes frequent contributions to venues such as arXiv (Cornell University), Proceedings of the AAAI Conference on Artificial Intelligence, Breast Cancer Research and Treatment, ACM Computing Surveys, and Nature Cell Biology.

The main research fields represented in Yi's work are:

  • Computer Science

With deeper specialization in the following subfields:

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Cancer Research
  • Molecular Biology
  • Signal Processing

Yi's research covers a variety of key topics, including:

  • Adversarial Robustness in Machine Learning
  • Domain Adaptation and Few-Shot Learning
  • Anomaly Detection Techniques and Applications
  • Privacy-Preserving Technologies in Data
  • Advanced Neural Network Applications
  • Advanced Malware Detection Techniques
  • Stochastic Gradient Optimization Techniques

Frequent collaborators of Jinfeng Yi are Cho-Jui Hsieh, Pin-Yu Chen, Lue Tao, Songcan Chen, and Lijun Zhang, reflecting strong co-authorship ties in their research community.

Best Publications

  • ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training Substitute Models

    Pin-Yu Chen;Huan Zhang;Yash Sharma;Jinfeng Yi

  • Sentiment analyzer: extracting sentiments about a given topic using natural language processing techniques

    J. Yi;T. Nasukawa;R. Bunescu;W. Niblack

  • Symmetric Cross Entropy for Robust Learning With Noisy Labels

    Yisen Wang;Xingjun Ma;Zaiyi Chen;Yuan Luo

  • EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples

    Pin-Yu Chen;Yash Sharma;Huan Zhang;Jinfeng Yi

  • Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System

    Tianxin Wei;Fuli Feng;Jiawei Chen;Ziwei Wu

  • Trustworthy AI: From Principles to Practices.

    Bo Li;Peng Qi;Bo Liu;Shuai Di

  • AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks

    Chun-Chen Tu;Paishun Ting;Pin-Yu Chen;Sijia Liu

  • Is Robustness the Cost of Accuracy? – A Comprehensive Study on the Robustness of 18 Deep Image Classification Models

    Dong Su;Huan Zhang;Hongge Chen;Jinfeng Yi

  • Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach

    Tsui-Wei Weng;Huan Zhang;Pin-Yu Chen;Jinfeng Yi

  • Improving Adversarial Robustness Requires Revisiting Misclassified Examples

    Yisen Wang;Difan Zou;Jinfeng Yi;James Bailey

  • Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach

    Minhao Cheng;Thong Le;Pin-Yu Chen;Jinfeng Yi

  • Diverse Few-Shot Text Classification with Multiple Metrics

    Mo Yu;Xiaoxiao Guo;Jinfeng Yi;Shiyu Chang

  • Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples

    Minhao Cheng;Jinfeng Yi;Pin-Yu Chen;Huan Zhang

  • On the convergence and robustness of adversarial training

    Yisen Wang;Xingjun Ma;James Bailey;Jinfeng Yi

  • Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning

    Hongge Chen;Huan Zhang;Pin-Yu Chen;Jinfeng Yi

  • Efficient distance metric learning by adaptive sampling and mini-batch stochastic gradient descent (SGD)

    Qi Qian;Rong Jin;Jinfeng Yi;Lijun Zhang

  • Semi-Crowdsourced Clustering: Generalizing Crowd Labeling by Robust Distance Metric Learning

    Jinfeng Yi;Rong Jin;Shaili Jain;Tianbao Yang

  • Robust Ensemble Clustering by Matrix Completion

    Jinfeng Yi;Tianbao Yang;Rong Jin;Anil K. Jain

  • Tracking slowly moving clairvoyant: optimal dynamic regret of online learning with true and noisy gradient

    Tianbao Yang;Lijun Zhang;Rong Jin;Jinfeng Yi

  • Self-weighted Multiple Kernel Learning for Graph-based Clustering and Semi-supervised Classification

    Zhao Kang;Xiao Lu;Jinfeng Yi;Zenglin Xu

  • Improved Dynamic Regret for Non-degenerate Functions

    Lijun Zhang;Tianbao Yang;Jinfeng Yi;Rong Jin

Frequent Co-Authors

Cho-Jui Hsieh
Cho-Jui Hsieh University of California, Los Angeles
Huan Zhang
Huan Zhang University of California, Los Angeles
Rong Jin
Rong Jin Alibaba Group (China)
Pin-Yu Chen
Pin-Yu Chen IBM (United States)
Tianbao Yang
Tianbao Yang Texas A&M University
Bowen Zhou
Bowen Zhou IBM (United States)
Zhi-Hua Zhou
Zhi-Hua Zhou Nanjing University
Jian Zhang
Jian Zhang University of Technology Sydney
Anil K. Jain
Anil K. Jain Michigan State University
Kush R. Varshney
Kush R. Varshney IBM (United States)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online degrees can open up new career possibilities for those interested in Computer Science. The rapidly growing tech industry values flexibility and specialized knowledge, making targeted online programs especially appealing.

For instance, pursuing an online master’s in electrical engineering degree can enhance your expertise and expand your job prospects in fields closely tied to computer science.

Fast-tracked education options, such as the shortest online masters degree programs, let you upskill without a long-term commitment—ideal for working professionals aiming to advance quickly.

If you're looking for credentials that offer good value, consider the most worthwhile masters degrees currently in high demand. These can greatly improve your chances of landing lucrative roles.

Not everyone needs a full degree; there are also easy licenses and certifications to get that can lead to well-paid jobs within technology and related sectors. No matter which path you choose, online education offers flexibility and a pathway to rewarding tech careers.

Best Scientists Citing Jinfeng Yi

Trending Scientists