Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Symmetric Cross Entropy for Robust Learning With Noisy Labels
2019555 citationsYisen Wang, Xingjun Ma et al.profile →
Understanding adversarial attacks on deep learning based medical image analysis systems
2020304 citationsXingjun Ma, Lin Gu et al.Pattern Recognitionprofile →
Privacy and Robustness in Federated Learning: Attacks and Defenses
2022264 citationsLingjuan Lyu, Xingjun Ma et al.profile →
WildDeepfake
2020246 citationsJingjing Chen, Xingjun Ma et al.profile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Xingjun Ma's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Xingjun Ma with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Xingjun Ma more than expected).
This network shows the impact of papers produced by Xingjun Ma. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Xingjun Ma. The network helps show where Xingjun Ma may publish in the future.
Co-authorship network of co-authors of Xingjun Ma
This figure shows the co-authorship network connecting the top 25 collaborators of Xingjun Ma.
A scholar is included among the top collaborators of Xingjun Ma based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Xingjun Ma. Xingjun Ma is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Wang, Yisen, Difan Zou, Jinfeng Yi, et al.. (2020). Improving Adversarial Robustness Requires Revisiting Misclassified Examples. International Conference on Learning Representations.153 indexed citations
15.
Ma, Xingjun, Lin Gu, Yisen Wang, et al.. (2020). Understanding adversarial attacks on deep learning based medical image analysis systems. Pattern Recognition. 110. 107332–107332.304 indexed citations breakdown →
16.
Lyu, Lingjuan, et al.. (2019). Towards Fair and Decentralized Privacy-Preserving Deep Learning. arXiv (Cornell University).2 indexed citations
17.
Lyu, Lingjuan, et al.. (2019). Towards Fair and Decentralized Privacy-Preserving Deep Learning with Blockchain. arXiv (Cornell University).15 indexed citations
18.
Ma, Xingjun, Yisen Wang, Michael E. Houle, et al.. (2018). Dimensionality-Driven Learning with Noisy Labels. Own your potential (DEAKIN). 3355–3364.49 indexed citations
19.
Ma, Xingjun, Bo Li, Yisen Wang, et al.. (2018). Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality. Own your potential (DEAKIN). 1–15.176 indexed citations
20.
Liu, Yuhao, et al.. (2016). Production Situation and Technology Prospect of Medical Isotopes. 29(2). 116–120.1 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.