Dongxiao Zhu

Faculty Profile

Professor
ct4442@wayne.edu

Phone

(313) 577-3104

Building

Maccabee

Homepage URL

https://dongxiaozhu.github.io/

Google Scholar URL

https://scholar.google.com/citations?hl=en&user=L0CbApYAAAAJ&view_op=list_works&sortby=pubdate

Biography

Dongxiao Zhu is currently a Professor at Department of Computer Science, Wayne State University. He received the Ph.D. from University of Michigan, Ann Arbor (2006). Dongxiao Zhu's recent research interests are in Trustworthy AI and Applications to Social, Health, and Urban computing with focus on adversarial robustness, explainability, fairness, and S&P. Dr. Zhu is the Founding Director of Wayne AI Research Initiative, and the Director of Trustworthy AI Lab at Wayne State University. He has published over 80 peer-reviewed publications and served on program committees (SPC/PC) of flagship AI/Machine Learning conferences (NuerIPS, ICML, ICLR, AAAI, IJCAI, ACL, EMNLP, CVPR, AMIA, MICCAI) and of premier biomedical informatics journals (Bioinformatics, Nucleic Acids Research, TCBB, Medical Physics, Scientific Reports, BMC Genomics, Plos One and Frontiers in Genetics). Dr. Zhu's research has been supported by NIH, NSF and private agencies and he has served on multiple NIH and NSF grant review panels. Dr. Zhu has advised numerous students at undergraduate, graduate and postdoctoral levels and his teaching interest lies in programming language, data structures and algorithms, machine learning and data science.

In addition to foundational AI research, Dr. Zhu is passionate about leveraging AI for science and social good research, development and community outreach. He develops tailor-made AI algorithms for promoting research in life, physical and social science domains. He also develops robust, fair and explainable AI algorithms and efficient systems to optimize public service delivery via learning geo-social features from geo-tagged big data, in efforts to achieve the sustainable development goals such as zero hunger, good health and well-being, better cybersocial behaviors, and reduced inequalities in socially vulnerable regions.

Courses Taught

C++ Programming; Data Structures; Image Processing; Bioinformatics; Design and Analysis of Algorithms; Data Mining; Machine Learning; Deep Learning 

News

Oct 2025: Two papers accepted by WACV-2025, first authored by my student Chengyin Li. 

Sept 2024: I am part of Geriatrics Workforce Enhancement Program project supported by $5M Health Resources and Services Administration grant!

August 2024: I am co-organizing the 3rd Workshop on Adversarial Machine Learning Frontiers @ NeurIPS-24.

July 2024: Congratulations to Dr. Qiang Yao for completing his successful PhD journey and start his career as Tenure-Track Assistant Professor at Oakland University! Dissertation: Designing for Reliability: Theoretical and Applied Perspectives on Trustworthy Artificial Intelligence.

July 2024: Congratulations to Dr. Chengyin Li for completing his successful PhD journey and start his career as a staff scientist at Henry Ford Health! Dissertation: Novel Transformer Architectures for 3D Multi-modal and Multi-organ Medical Image Segmentation.

July 2024: The paper entitled "Fairness-aware Vision Transformer via Debiased Self-Attention" first authored by my student Qiang Yao has been accepted by ECCV-24.

May 2024: I am serving on a NIH study section again.

May 2024: I am excited to participate in NSF Workshop on Envisioning Open Research Resources for AI.

May 2024: I am serving on a NSF CISE panel again.

April 2024: Congratulations to Chengyin Li on winning the prestigious Michael E. Conrad Award!

April 2024: Our AI4mobility and future of work research was featured on Detroit PBS.

March 2024: The MS AI program I created in collaboration with ECE and ISE departments is ranked #20 in the nation by TechGuide.

March 2024: I am serving on a NIH Study Section.

Feb 2024: Our recent work learns to poison LLMs during instruction tuning!

Feb 2024: I am serving on a NSF CISE panel.

Jan 2024: Our paper titled: Benchmark and Neural Architecture for Conversational Entity Retrieval from a Knowledge Graph is accepted by ACM Web Conference-2024, accept rate is 402/4,028 = 20.2%.

Jan 2024: Our paper titled: Traumatic Data: Applying Trauma-Informed Design to Data Donation of Sexual Violence Experiences to Improve Sexual Risk Detection AI is accepted by CHI-2024, accept rate is 1,060/4,028 = 26.3%.

Dec 2023: I gave an invited talk at National Science Foundation, titled "Towards Trustworthy AGI in the Era of Foundation Models – Opportunities, Risks, and Vision”.

Dec 2023: Our paper titled MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks is accepted by AAAI-24, accept rate is 2,342/12,100 = 23.75%.

Dec 2023: I serve as a meta-reviewer for AI ethics track at International Joint Conference on Artificial Intelligence (IJCAI-24).

Nov 2023: Our recent work fine tunes Segment Anything Model (SAM) for automated mobility infrastructure segmentation.

Oct 2023: Our recent work uncovers the vulnerabilities of Large Language Model (LLM) from a novel lens of adversarial in-context learning!

Aug 2023: I served as a meta-reviewer for Robustness and Trustworthiness track at the 38th Annual AAAI Conference on Artificial Intelligence (AAAI-24).

June 2023: The paper titled "FocalUNETR: A Focal Transformer for Boundary-aware Prostate Segmentation using CT Images" first authored by my student Chengyin Li has been accepted by MICCAI-23, accept rate is 740/2250 = 32%.

May 2023: Congratulations to Yao Qiang on winning the prestigious Michael E. Conrad Award!

April 2023: I was recommended for the promotion to full professor, effective Aug. 17 2023!

April 2023: The paper entitled "Negative Flux Aggregation to Estimate Feature Attributions" first authored by my student Xin Li has been accepted by IJCAI-23, accept rate is 685/4,566=15%.

April 2023: April 2023: Our position paper titled "ChatGPT- a promising generative AI tool and its implications on cancer care" to appear in Cancer. 

April 2023: I am giving an invited talk on Enhancing Algorithmic Fairness in Deep Learning at Department of Computer Science and Engineering of University at Buffalo.

April 2023: I am served as a panelist on the workshop on Fairness in Machine Intelligence for Global Health 2023.

March 2023: I am co-organizing 2nd Workshop on New Frontiers in Adversarial Machine Learning (AdvML) at ICML-2023!

Feb 2023: I served as a topic editor for Evolution in Statistical Genetics and Methodology at Frontiers in Genetics journal.

Feb 2023: I served as a meta-reviewer for AI ethics track at International Joint Conference on Artificial Intelligence (IJCAI-23).

Jan 2023: I gave an invited talk on Advancing Algorithmic Fairness in Deep Learning at Statistics and Probability department of Michigan State University.

Jan 2023: I created a new online MS Program in Computer Science with concentration on AI.

Dec 2022: I received a NIH R33 grant (MPI) in developing a chatbot to acquire social, clinical and molecular determinants for personalized on-device MIS-C risk assessment, total amount is $1,449,684.

Dec 2022: I received a NSF Convergence Accelerator grant (co-PI) learning geospatial features and developing human-centered AI for enhancing mobility equity for persons with disabilities, total amount is $613,621.

Nov 2022: The paper entitled "Learning Compact Features via In-Training Representation Alignment" first authored by my student Xin Li has been accepted by AAAI-23, accept rate is 1,721/8,777=19.6%.

Nov 2022: I gave master lectures on Trustworthy AI and Machine Learning Faculty Development Program in Emerging Technologyies - Indo-US Higher Education and Careers Summit!

Nov 2022: I gave an invited talk on Empowering Explainable Machine Learning through the Lens of Adversarial Robustness and Fairness at Computer Science and Engineering department of Michigan State University.

Sept 2022: Trustworthy AI paper titled "AttCAT: Explaining Transformers via Attentive Class Activation Tokens." first authored by my student Mr. Yao Qiang has been accepted by NuerIPS-22, accept rate is 2,665/10,411 = 25%.

Aug 2022: I received NSF research grant (PI) in leveraging AI for better cyber-social behavior via enhancing trust in data donation from users. Total amount is $600,000. 

Aug 2022: I created a new Master Program in AI (Algorithms and Systems Track) hosted by Computer Science department. Interested students please contact me for further info.

June 2022: Congratulations to Dr. Xin Li for completing his successful PhD journey! Dissertation: Adversarial Machine Learning for Advanced Medical Imaging Systems. First Position: Research Scientist II @ Bosch AI. 

June 2022: My student Mr. Chengyin Li's first first-author machine learning paper on privacy-aware and resource-constraint EV charging recommendation algorithm titled "Coupling User Preference with External Rewards to Enable Driver-centered and Resource-aware EV Charging Recommendation" accepted by ECML-PKDD 2022, accept rate is 242/932 = 26%.

May 2022: I am giving a Keynote Speech at Adversarial Machine Learning towards Advanced Vision Systems’ (AMLAVS) workshop @ACCV-2022.

April 2022: Trustworthy AI paper titled "Counterfactual Interpolation Augmentation (CIA): A Unified Approach to Enhance Fairness and Explainability of DNN." first authored by my student Mr. Yao Qiang has been accepted by 31st International Joint Conference on Artificial Intelligence (IJCAI-22), accept rate is 680/4535 = 15%.

April 2022: I am honored and pleased to be selected to receive the "College of Engineering Excellence in Research" Award. Thanks to the department of computer science and college of engineering for your support!

March 2022: One of the collaborative work on "Deep learning protocol for improved photoacoustic brain imaging" has been recognized as a top cited article in Journal of Biophotonics.

March 2022: I am co-organizing 1st Workshop on New Frontiers in Adversarial Machine Learning (AdvML) at ICML-2022! Program focuses on new theory/algorithm/application stack of AdvML and Trustworthy ML (Poster). Submission deadline: May 23 2022.

March 2022: Congratulations to Dr. Deng Pan for completing his successful PhD journey! Dissertation: Interpretable Machine Learning and Applications. First Position: AI Algorithm Engineer @ Alibaba Group

Research Projects

Selected Research Projects (Post-Tenure). Toal Amount: ~6 Million; As a PI: ~3 Million

NIH/R33HD105610: Severity Predictors Integrating salivary Transcriptomics and proteomics with Multi neural network Intelligence in SARS-CoV2 infection in Children (SPITS MISC), 01/01/2023-12/31/2025. Role: MPI, $1,449,684, 33%.

NSF/ITE 2235225: NSF Convergence Accelerator Track H: Leveraging Human-Centered AI Microtransit to Ameliorate Spatiotemporal Mismatch between Housing and Employment for Persons with Disabilities. 12/15/2022 - 11/30/2023, Total amount: $613,621, Role: co-PI (25%)

National Science Foundation (IIS 2211897) Collaborative Research: HCC: Small: Understanding Online-to-Onlne Sexual Violence through Data Donation from Users. 10/01/2022-09/30/2025, Total amount: $600,000, My Role: PI (33%). 

National Science Foundation (CNS 2043611) SCC-CIVIC-PG Track A: Leveraging AI-assist Microtransit to Ameliorate Spatiotemporal Mismatch between Housing and Employment. 01/15/2021-12/31/2021, Total amount: $49,898, My Role: PI (25%)

National Institute of Health (R61HD105610) Severity Predictors Integrating salivary Transcriptomics and proteomics with Multi neural network Intelligence in SARS-CoV2 infection in Children (SPITS MISC) 01/01/2021 – 12/31/2023, Total amount: $1,433,469, My Role: MPI (33%).

National Science Foundation (CNS 1724227) Title: S&AS: INT: Autonomous Battery Operating System (ABOS): An Adaptive and Comprehensive Approach to Efficient, Safe, and Secure Battery System Management.  Total amount: $1,249,898, 01/15/2017-12/31/2023, My Role: Senior Personnel (10%).

National Science Foundation (CNS 1637312) S&CC: Promoting a Healthier Urban Community: Prioritization of Risk Factors for the Prevention and Treatment of Pediatric Obesity. Total Amount: $199,996, 09/01/2016-08/31/2019, Total amount: $199,996, My Role: Co-PI (33%).

Henry Ford Health Science Center, Titile: Uncertainty in Segmentation of 3D CT images of Prostate Cancer Patients. 07/01/2020 - 06/30/2023, Total amount: $90,000,  My Role: PI (100%).

Henry Ford Health Science Center. AI approaches to estimate uncertainties in adaptive radiotherapy of lung cancer. 08/18/2021 - 08/17/2025, Total amount: $220,000, My Role: PI (100%).

DTE E-Challenge. Energy Conservation Measure for Michigan Universities, 01/2022 – 12/2023, Total amount: $200,000, My Role: Co-PI (33%).

Publications

Selected Foundational AI and Machine Learning Publications in Top Venues Tracked by CSRankings.org. My Student as the First Author Underlined. 

[IJCAI-23] Li, X, Pan, D, Li, C, Qiang, Y, and Zhu, D. Interpreting Deep Neural Network Models with Negative Flux Aggregation. In the Proceedings of 32st International Joint Conference on Artificial Intelligence, Marco, China. Acceptance rate: 685/4,566 = 15%.

[AAAI-23] Li, X., Li, X., Pan, D, Qiang, Y., and Zhu, D. (2022) Learning Compact Features via In-Training Representation Alignment. To appear in the Proceedings of Thirty-Seventh AAAI Conference on Artificial Intelligence. Accept rate: 1,721/8,777=19.6%.

[NuerIPS-22] Qiang, Y, Pan, D, Li, C, Li, X, Jang, R, and Zhu, D. (2022) AttCAT: Explaining Transformers via Attentive Class Activation Tokens. To appear in the Proceedings of Thirty-sixth Conference on Neural Information Processing Systems. Acceptance rate: 2,665/10,411 = 25%.

[IJCAI-22] Qiang, Y, Li, C, Brocanelli, M, Zhu, D. (2022) Counterfactual Interpolation Augmentation (CIA): A Unified Approach to Enhance Fairness and Explainability of DNN. Accepted by 31st International Joint Conference on Artificial Intelligence, Messe Wien, Vienna, Austria. Acceptance rate: 681/4,535 = 15%.

[IJCAI-21] Pan, D, Li, X and Zhu, D (2021) Explaining Deep Neural Network Models with Adversarial Gradient Integration. Accepted for publication in 30th International Joint Conference on Artificial Intelligence, Montreal, Canada. Acceptance rate: 587/4,204=13.9%.

[AAAI-21] Li, X, Li, X, Pan,D and Zhu, D (2020) Improving adversarial robustness via probabilistically compact loss with logit constraints. To appear in the proceedings of Thirty-Five AAAI Conference on Artificial Intelligence, virtual conference. Acceptance rate: 1,692/7,911=21.4%

[IJCAI-20] Pan, D, Li, X, Li, X and Zhu, D (2020) Explainable recommendation via interpretable feature mapping and evaluating explainability. In the proceedings of 29th International Joint Conference on Artificial Intelligence, Yokohama, Japan. Acceptance rate: 592/4,717=12.6% 

[AAAI-20] Li, X, Li, X, Pan,D and Zhu, D (2020) On the learning behavior of logistic and softmax losses for deep neural networks. In the proceedings of Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, USA. Acceptance rate: 1,591/7,737=20.6%.

Selected Use-Inspired AI Publications in EHR, Health & Wellness, Medical Imaging, and Natural Language Processing. My Student as the First Author Underlined.

(EHR) Li, X, Zhu, D and Levy, P (2020) Predicting clinical outcomes with patient stratification via deep mixture neural networks. American Medical Informatics Association (AMIA-20) Summit on Clinical Research Informatics, Houston, USA. (Best Student Paper Award, *Corresponding Autor) PubMed 32477657

(EHR) Nezhad, MZ, Sadati, N, Yang, K and Zhu, D. (2019) A deep active survival analysis approach for precision treatment recommendations: application of prostate cancer. Expert Systems with Applications. Vol. 15, 16-26.

(Health & Wellness) Wang, L. and Zhu, D. (2021). Tackling multiple ordinal regression problems: sparse and deep multi-task learning approaches. Data Mining and Knowledge Discovery (DMKD), 23 March 2021.

(Health & Wellness) Wang, L, Dong, M, Towner, E and Zhu, D (2019) Prioritization of multi-level risk factors for obesity. In the proceedings of 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM-19), 1065-1072.

(Medical Imaging) Li, C., Qiang, Y, Sultan, R, Bagher-Ebadian, P, Khanduri, V, Chetty, IJ, and Zhu, D. FocalUNETR: A Focal Transformer for Boundary-aware Segmentation of CT Images. To appear in the Proceedings of 26th International Conference on Medical Image Computing and Computer Assisted Intervention, Vancouver, Canada. Accept rate: 740/2,250 = 32%

Manwar, R., Li, X., Kratkiewicz, K., Zhu, D., & Avanaki, K. (2023) Adaptive Coherent Weighted Averaging Algorithm for Enhancement of Photoacoustic Tomography Images. Journal of Biophotonics, e202300103.

(Medical Imaging) Li, X, Bagher, HE, Kim, J, Zhu, D, and Chetty, I. (2022) An uncertainty-aware deep learning architecture with outlier mitigation for prostate gland segmentation in radiotherapy treatment planning. Medical Physics, Accepted for Publication

(Medical Imaging) Li, X and Zhu, D (2020) COVID-MobileXpert: On-Device COVID-19 Screening using Snapshots of Chest X-Ray. To appear in the proceedings of 2020 International Conference on Bioinformatics and Biomedicine (BIBM-20).

(Medical Imaging) Li, X., Pan, D. and Zhu, D. (2021) Defending against adversarial attacks on medical imaging AI system, classification or detection? To appear in the proceedings of IEEE International Symposium on Biomedical Imaging (ISBI-21), virtual conference.

(Medical Imaging) Li, X. and Zhu, D. (2020). Robust detection of adversarial attacks on medical images. IEEE International Symposium on Biomedical Imaging (ISBI-20), Iowa City, USA. 

(Medical Imaging) Li, X., Hect, J., Thompson, J. and Zhu, D. (2020). Interpreting age effects of human fetal brain from spontaneous fMRI using deep 3D convolutional neural networks. IEEE International Symposium on Biomedical Imaging (ISBI-20), Iowa City, USA. 

(Medical Imaging) Manwar, R., Li, X., Mahmoodkalayeh, S., Asano, E., Zhu, D. and Avanaki, K., 2020. Deep learning protocol for improved photoacoustic brain imaging. Journal of Biophotonics, 13(10), p.e202000212.

(Natural Language Processing) Qiang, Y, Li, X and Zhu, D (2020) Toward tag-free aspect based sentiment analysis: a multiple attention network approach. in the proceedings of International Joint Conference on Neural Networks (IJCNN-20), Glasgow, Scotland, UK.

(Natural Language Processing) Qiang, Y., Kumar, S. T. S., Brocanelli, M., & Zhu, D. (2022) Tiny RNN Model with Certified Robustness for Text Classification. Proceedings of International Joint Conference on Neural Networks (Oral Presentation).

(Transportation) Li, C., Dong, Z, Fisher, N, and Zhu, D. (2022) Coupling User Preference with External Rewards to Enable Driver-centered and Resource-aware EV Charging Recommendation. To appear in the Proceedings of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Acceptance rate: 242/932 = 26%.

(Transportation) Kabir, R., Remias, S, Wadell, J, and Zhu, D. (2023) Time-Series Fuel Consumption Prediction Assessing Delay Impacts on Energy using Vehicular Trajectory. To appear in Transportation Research Part D.

Selected Publication in Bioinformatics and Computational Biology. My Student as the First Author Underlined.

Li, C, Sullivan, R, Zhu, D, and Hick, S (2022) Putting the ‘mi’ in omics: discovering miRNA biomarkers for pediatric precision care. Pediatrics Research, https://doi.org/10.1038/s41390-022-02206-5.

Wang, L, Acharya, L, Bai, C and Zhu, D (2017) Transcriptome assembly strategies for precision medicine. Quantitative Biology, pp 1-11, https://doi.org/10.1007/s40484-017-0109-2.

Hou, J., Acharya, L., Zhu, D. and Chen, J. (2016) An overview of bioinformatics methods for modeling biological pathways in yeast. Briefings in Functional Genomics, 15(2), 95-108

Zhu, D, Deng, N, and Bai C. (2014) An event-based computational framework for comparing transcriptomes. IEEE Transaction on NanoBioScience, DOI: 10.1109/TNB.2015.2388593.

Deng, N, Sanchez, C, Lasky, J, Zhu, D. (2013) Detecting splicing variants from non-differentially expressed genes of human idiopathic pulmoary fibrosis. PLoS One 8(7):e68352. doi:10.137/journal.pone.0068352.

Judeh, T, Johnson, C, Kumar, A, Zhu, D (2013) TEAK: Topological Enrichment Analysis frameworK for detecting activated biological subpathways. Nucleic Acids Res., doi: 10.1093/nar/gks1299.

Deng, N and Zhu, D. (2013). Detecting various types of differential splicing events using RNA-Seq data. Proceedings of 2013 ACM Conference on Bioinformatics, Computational Biology and Biomedicine (ACM BCB'13).

Acharya, L, Judeh, T, Wang, G, Zhu, D. (2012) Optimal structural inference of signaling pathways from overlapping and unordered gene sets. Bioinformatics, doi 10.1093/bioinformatics/btr696, 28(4), 546-556

Acharya, L, Judeh, T, Duan, Z, Rabbat, M, Zhu, D. (2011) GSGS: A computational framework for reconstructing signaling pathways from gene sets. IEEE/ACM transaction on Computational Biology and Bioinformatics (TCBB), 9(2), 438-450.

Deng N, Puetter, A, Zhang, K, Johnson, K., Zhao, Z, Taylor, C, Flemington, E and Zhu, D. (2011) Isoform-level microRNA-155 Target Prediction using RNA-seq. Nucleic Acids Res., doi: 10.1093/nar/gkr042.

Xu G, Deng N, Zhao, Z, Flemington EK, Zhu D. (2011) SAMMate: A GUI tool for processing short read alignment information in SAM/BAM format. Source Code for Biology and Medicine, 6:2. 

Zhu, D, Acharya, L, Zhang, H. (2011) A generalized multivariate approach to pattern discovery from replicated and incomplete genome-wide measurements. IEEE/ACM transaction on Computational Biology and Bioinformatics (TCBB), 8(5), pp1153-1169.

Awards and Honors

 

Education

Ph.D 2006, University of Michigan, Ann Arbor

Laboratory Web Site

Trustworthy AI Lab