Congzheng Song
- Artificial Intelligence top 0.5%
- Computer Vision and Pattern Recognition top 5%
- Information Systems top 2%
- Sociology and Political Science top 5%
- Signal Processing top 5%
- Co-authors
- Vitaly ShmatikovReza ShokriMarco StronatiThomas RistenpartAnanth RaghunathanSameer H. HalaniDavid A. GutmanDaniel J. Brat
- Topics
- Adversarial Robustness in Machine Learning (8 papers)Privacy-Preserving Technologies in Data (6 papers)Topic Modeling (3 papers)
- Partner nations
- United StatesChinaIsrael
In The Last Decade
Congzheng Song
15 papers receiving 2.8k citations
Hit Papers
Peers
Comparison fields: 5 of 111
- Artificial Intelligence 2.5k
- Computer Vision and Pattern Recognition 283
- Information Systems 268
- Sociology and Political Science 259
- Signal Processing 196
Countries citing papers authored by Congzheng Song
This map shows the geographic impact of Congzheng Song'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 Congzheng Song with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Congzheng Song more than expected).
Fields of papers citing papers by Congzheng Song
This network shows the impact of papers produced by Congzheng Song. 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 Congzheng Song. The network helps show where Congzheng Song may publish in the future.
Co-authorship network of co-authors of Congzheng Song
This figure shows the co-authorship network connecting the top 25 collaborators of Congzheng Song. A scholar is included among the top collaborators of Congzheng Song 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 Congzheng Song. Congzheng Song is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 9 | |
| 2 | You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion | 20 |
| 3 | 11 | |
| 4 | Overlearning Reveals Sensitive Attributes | 10 |
| 5 | 16 | |
| 6 | 1 | |
| 7 | 31 | |
| 8 | 115 | |
| 9 | 102 | |
| 10 | Inference Attacks Against Collaborative Learning. | 37 |
| 11 | The Natural Auditor: How To Tell If Someone Used Your Words To Train Their Model. | 6 |
| 12 | 143 | |
| 13 | 268 | |
| 14 | Membership Inference Attacks Against Machine Learning Modelsbreakdown → | 2137 |
| 15 | 2 |
About Congzheng Song
Congzheng Song is a scholar working on Artificial Intelligence, Modeling and Simulation and Signal Processing, having authored 15 papers that have together received 2.9k indexed citations. Recurring topics across this work include Adversarial Robustness in Machine Learning (8 papers), Privacy-Preserving Technologies in Data (6 papers) and Topic Modeling (3 papers). The work is most often cited by research in Health Informatics (151 citations), Artificial Intelligence (2.5k citations) and Computer Science Applications (177 citations). Congzheng Song has collaborated with scholars based in United States, China and Israel. Frequent co-authors include Vitaly Shmatikov, Reza Shokri, Marco Stronati, Thomas Ristenpart, Ananth Raghunathan, Sameer H. Halani, David A. Gutman, Daniel J. Brat, Lee Cooper and Joshua E. Lewis. Their work appears in journals such as Proceedings of the National Academy of Sciences, Scientific Reports and Vacuum.
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.