Ruoxi Jia

2.8k total citations · 1 hit paper
48 papers, 1.3k citations indexed

About

Ruoxi Jia is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Building and Construction. According to data from OpenAlex, Ruoxi Jia has authored 48 papers receiving a total of 1.3k indexed citations (citations by other indexed papers that have themselves been cited), including 31 papers in Artificial Intelligence, 7 papers in Computer Vision and Pattern Recognition and 7 papers in Building and Construction. Recurrent topics in Ruoxi Jia's work include Adversarial Robustness in Machine Learning (14 papers), Privacy-Preserving Technologies in Data (14 papers) and Anomaly Detection Techniques and Applications (7 papers). Ruoxi Jia is often cited by papers focused on Adversarial Robustness in Machine Learning (14 papers), Privacy-Preserving Technologies in Data (14 papers) and Anomaly Detection Techniques and Applications (7 papers). Ruoxi Jia collaborates with scholars based in United States, China and Singapore. Ruoxi Jia's co-authors include Costas J. Spanos, Ming Jin, Dawn Song, Yuheng Zhang, Tianzhen Hong, Bo Li, Wenxiao Wang, Hengzhi Pei, Boxin Wang and Nezihe Merve Gürel and has published in prestigious journals such as SHILAP Revista de lepidopterología, Proceedings of the IEEE and Applied Energy.

In The Last Decade

Ruoxi Jia

45 papers receiving 1.3k citations

Hit Papers

align trajectories sort by overperformance

What are hit papers?

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.

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

2020 236 citations Yuheng Zhang, Ruoxi Jia et al. profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Ruoxi Jia United States	20	677	316	277	171	126	48	1.3k
Hany F. ElYamany Egypt	7	422 0.6×	291 0.9×	203 0.7×	86 0.5×	122 1.0×	15	1.1k
Jiaming Li Australia	18	494 0.7×	415 1.3×	158 0.6×	167 1.0×	107 0.8×	44	1.3k
Dezhi Hong United States	15	311 0.5×	178 0.6×	273 1.0×	253 1.5×	81 0.6×	60	937
Chunhong Zhang China	14	487 0.7×	240 0.8×	70 0.3×	149 0.9×	175 1.4×	112	1.0k
Salah Bouktif United Arab Emirates	15	330 0.5×	485 1.5×	163 0.6×	88 0.5×	449 3.6×	50	1.4k
Ting Zhong China	21	817 1.2×	132 0.4×	304 1.1×	214 1.3×	334 2.7×	101	1.6k
Guojiang Shen China	19	371 0.5×	205 0.6×	616 2.2×	268 1.6×	152 1.2×	116	1.6k
Zhiyong Yu China	17	402 0.6×	249 0.8×	117 0.4×	220 1.3×	363 2.9×	118	1.6k
Longbiao Chen China	14	172 0.3×	113 0.4×	229 0.8×	210 1.2×	62 0.5×	69	967
Vincent C. S. Lee Australia	19	391 0.6×	102 0.3×	81 0.3×	141 0.8×	154 1.2×	75	1.8k

Countries citing papers authored by Ruoxi Jia

Since Specialization

Citations

This map shows the geographic impact of Ruoxi Jia'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 Ruoxi Jia with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ruoxi Jia more than expected).

Fields of papers citing papers by Ruoxi Jia

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Ruoxi Jia. 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 Ruoxi Jia. The network helps show where Ruoxi Jia may publish in the future.

Co-authorship network of co-authors of Ruoxi Jia

This figure shows the co-authorship network connecting the top 25 collaborators of Ruoxi Jia. A scholar is included among the top collaborators of Ruoxi Jia 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 Ruoxi Jia. Ruoxi Jia is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

Wang, Qian, et al.. (2025). Detecting Adversarial Data Using Perturbation Forgery. 13917–13926.

Yu, Yang, et al.. (2024). AI Risk Categorization Decoded (AIR 2024). 1(1). 2 indexed citations

He, Jianfeng, et al.. (2024). Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?. 16514–16575. 1 indexed citations

Zhang, Jingwen, et al.. (2024). How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs. 14322–14350. 21 indexed citations

Zeng, Yi, Yang Yu, John Tan, et al.. (2024). AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies. 1(1). 2 indexed citations

Zeng, Yi, et al.. (2024). BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models. 13189–13215. 4 indexed citations

Jin, Ming, et al.. (2023). On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds. Proceedings of the AAAI Conference on Artificial Intelligence. 37(7). 8123–8131. 6 indexed citations

Jia, Ruoxi, et al.. (2023). A Theoretical Analysis of Using Gradient Data for Sobolev Training in RKHS. IFAC-PapersOnLine. 56(2). 3417–3422. 1 indexed citations

Zeng, Yi, et al.. (2023). Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information. VTechWorks (Virginia Tech). 771–785. 81 indexed citations

10.

Shi, Weiyan, et al.. (2022). Just Fine-tune Twice: Selective Differential Privacy for Large Language Models. 6327–6340. 20 indexed citations

11.

Du, Min, Ruoxi Jia, & Dawn Song. (2020). Robust anomaly detection and backdoor attack detection via differential privacy. International Conference on Learning Representations. 11 indexed citations

12.

Zhang, Yuheng, Ruoxi Jia, Hengzhi Pei, et al.. (2020). The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks. 250–258. 236 indexed citations breakdown →

13.

Jia, Ruoxi, Boxin Wang, Frances Ann Hubis, et al.. (2019). Efficient task-specific data valuation for nearest neighbor algorithms. Proceedings of the VLDB Endowment. 12(11). 1610–1623. 90 indexed citations

14.

Sangogboye, Fisayo Caleb, Ruoxi Jia, Tianzhen Hong, Costas J. Spanos, & Mikkel Baun Kjærgaard. (2018). A Framework for Privacy-Preserving Data Publishing with Enhanced Utility for Cyber-Physical Systems. ACM Transactions on Sensor Networks. 14(3-4). 1–22. 15 indexed citations

15.

Jia, Ruoxi, Baihong Jin, Ming Jin, et al.. (2018). Design Automation for Smart Building Systems. Proceedings of the IEEE. 106(9). 1680–1699. 63 indexed citations

16.

Wang, Zhe, Tianzhen Hong, & Ruoxi Jia. (2018). Buildings.Occupants: a Modelica package for modelling occupant behaviour in buildings. Journal of Building Performance Simulation. 12(4). 433–444. 27 indexed citations

17.

Jia, Ruoxi, Roy Dong, Shankar Sastry, & Costas J. Spanos. (2017). Privacy-enhanced architecture for occupancy-based HVAC Control. 177–186. 39 indexed citations

18.

Jia, Ruoxi, Yang Gao, & Costas J. Spanos. (2015). A fully unsupervised non-intrusive load monitoring framework. 37 indexed citations

19.

Jia, Ruoxi, et al.. (2015). SoundLoc: Accurate room-level indoor localization using acoustic signatures. 186–193. 24 indexed citations

20.

Jia, Ruoxi, et al.. (2015). Poster Abstract. OpenMETU (Middle East Technical University). 109–110. 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.

Explore authors with similar magnitude of impact