I am recruiting PhD students for the Fall 2026 or Spring 2027 semesters. We work at the intersection of trustworthy AI and intelligent systems — building AI that doesn't just perform well, but can explain itself, reason well, and operate reliably in complex, real-world settings. Our work spans trustworthy ML, agentic systems and workflows.
To be successful in our lab, you would need these foundational skills:
Strong Python programming skills
Solid grounding in core mathematics for ML: linear algebra, probability and statistics, and optimization
Familiarity with deep learning fundamentals and at least one major framework (PyTorch/TensorFlow)
Ability to read, critically evaluate, and build on research papers
Comfort with experimental rigor — designing clean experiments, handling data carefully, and being honest about what results do and don't show
Strong written and verbal communication — you'll need to explain complex ideas clearly, in papers and in person
Genuine intellectual curiosity and the persistence to work through hard, often ambiguous problems independently
**To apply: please send me your CV (including GPA and GRE scores), transcripts, GitHub link, and samples of any papers you've published. **
** You will need 3 recommendation letters from faculty who know your work. Please arrange for them to send those to me.**
Member, Best Paper Awards Selection Committee, IEEE TCCN (2019, 2020)
Founding Chair, Special Interest Group on Security, IEEE Technical Committee on Cognitive Networks, June 2013 --
Vice-Chair, North America Region, IEEE Technical Committee on Cognitive Networks, (January 2011 -- January 2013)
Secretary, IEEE COMSOC Technical Committee on Multimedia Communications, (June 2006 -June 2008)
Chair, Special Interest Group on Security, IEEE Technical Committee on Multimedia Communications, (2005 -2010)
Member, IEEE Technical Committee on Cognitive Networks, (2007, --)
Member, IEEE Technical Committee on Communications Security, (2005 -)
Member, Best Paper Awards Selection Committee, IEEE MMC (2004 -).
Associate Editor, IEEE Transactions on Neural Networks and Learning Systems, January 1, 2021 -- 2024
Lead Guest Editor, Special Issue on New Developments in Explainable and Interpretable AI, IEEE Transactions on Artificial Intelligence, 2021 - 2022
Associate Editor, IEEE Transactions on Artificial Intelligence, January 1, 2020 --
Founding Associate Editor, IEEE Transactions on Cognitive Communications and Networking, January 2015 – January 2020
Associate Editor, IEEE Transactions on Vehicular Technology, August 2013 – August 2016.
Guest Editor, EURASIP Journal on Applied Signal Processing, Special Issue Security Challenges and Issues in Cognitive Radio Networks, 2013.
Founding Associate Editor, Journal of Cyber Security and Mobility, 2011-present.
Guest Editor, EURASIP Journal on Applied Signal Processing, Special Issue on Dynamic Spectrum Access for Wireless Networking, along with John Chapin, Ananthram Swami and R. Chandramouli, 2008-2009.
Associate Editor, IS&T/SPIE Journal of Electronic Imaging, May 2007 – 2014.
Associate Editor, Advances in Multimedia, Hindawi Publishing Corporation, July 2006—2008.
Guest Editor, IEEE Journal on Selected Areas in Communications, Special Issue on Cross-Layer Optimized Wireless Multimedia Communications, 2006.
Technical Program Committee Co-Chair, IEEE DySPAN 2019
Poster Chair, IEEE Conference on Communication and Network Security (CNS) 2019
Member, IEEE ICC 2021, Proposal Committee for New York City
Symposium Co-Chair, Symposium on Cognitive Radio Networking, IEEE GLOBECOM 2017.
IEEE GLOBECOM 2016, Symposium on Selected Areas of Communication, Social Networks Track, Washington DC, 2016
IEEE International Conference on Communications, Symposium on Selected Areas of Communication, Dresden, Germany,2009
Founding Co-Chair, IEEE WoWMoM, Workshop on Security, Privacy and Authentication in Wireless Networks, 2008
IEEE 17th International Conference on Computer Communications and Networks, Network Security Symposium, 2008
IEEE 16th International Conference on Computer Communications and Networks, Network Security Symposium, 2007
IEEE GLOBECOM, Symposium on Network and Information Systems Security, 2006.
Special Tracks Co-Chair
IEEE International Symposium on Multimedia, 2006, 2007.
STC CrownCom 2007.
Technical Track Chair, Multimedia Technology Track, IEEE International Conf. on Information Technology: Research and Education, 2003.
Special Sessions Organizer/Session Chair
Joint Source-Channel Coding, Picture Coding Symposium 2003 , (jointly with Pierre Siohan, IRISA-INRIA, France)
Technical Demonstration/Exhibition, IEEE International Conference on Information Technology: Research and Education, 2003
Current Trends in Multimedia Communications and Computing, IEEE ITCC 2001
Best Student Paper Award Selection Committee, ITCC 2001, 2002.
Session Chair, IEEE International Conference on Image Processing, 2004.
Session Chair, IEEE International Conference on Communications, 2006.
Network Security, IEEE 16th International Conference on Computer Communications and Networks, Hawaii, August 2007.
Spectrum Sensing, CrownCom 2007, Orlando Florida, August 2007.
Joint Source-Channel Coding, Picture Coding Symposium 2003.
Current Trends in Multimedia Communications and Computing, IEEE ITCC 2001
Reviewer, ICML 2026
Reviewer, ICLR 2026
First ACM Workshop on Cognitive Radio Architectures for Broadband, Oct 4, 2013.
First IEEE International Workshop on Cognitive Radio and Networks, in conjunction with PIMRC, 2008.
First International Workshop on Information Security, 2006.
IEEE Wireless Communication and Networking Conference, 2007.
Digital Forensics Research Workshop (DFRWS), August 2006.
Network Security Symposium, IEEE GLOBECOM, 2006.
IEEE International Conference on Communications, 2006.
IWCMC 2006, Sensor and Wireless Resource Management.
IEEE MILCOM, 2005.
First IEEE International Symposium on Multimedia, Irvine California, Dec 2005
2005 Digital Forensics Research Workshop (DFRWS), New Orleans, August 2005.
IEEE International Workshop on Adaptive Wireless Networks (AWiN), GLOBECOM 2005.
IEEE International Conference on Multimedia and Expo, 2004.
IEEE International Conference on Communications, Multimedia Symposium, 2004, 2005.
IEEE International Conference on Communications, 2003.
IEEE Semiannual Vehicular Technology Conference, 2003.
IEEE International Conference on Information Technology: Research and Education, 2003.
IEEE International Conference on Information Technology: Coding and Computing, 2001,2002.
Explainable AI with Attention Networks for Credit/Loan Decisions, Talk at the Future of FinTech - NSF CyberSmart Planning Workshop, October 2020.
Machine Learning in Spectrum Access Security, WSRD Workshop X: Security from a Wireless Spectrum Perspective: Technology Innovation and Policy Research Needs, 2018
Detecting Lies on the Internet, IEEE Conference on Information Security, Cyber Security and Privacy, Nov. 12, 2014.
Wireless & Information Systems Security, Idaho National Laboratory, January 2014
Internet Lurkers: Large-Scale Measurements and Modeling, University of California Los Angeles, December 4, 2012.
Recent Results in Cognitive Radio Network and Social Network Security, Applied Communication Sciences (formerly Telcordia), February 2012.
Securing Dynamic Spectrum Access (DSA) Networks: Two Examples, King's College, June 2011, London, UK.
Binary Data Hiding Game, Purdue University, West Lafayette, Indiana, October 21, 2008.
Error Correction and Encryption: Can they be combined?, Séminaire de Cryptographie, Institute of Mathematical Research of Rennes, University of Rennes 1, October 2007.
Error Correction and Encryption: Can they be combined?, Texas A&M University, September 2007.
Error Correction and Encryption: Can they be combined?, University of Texas at Arlington, September 2007.
Steganalysis of QIM-Based Data Hiding using Kernel Density Estimation", ACM Multimedia Security Workshop, September 2007.
A New Look at Wireless Security: Error Correcting Ciphers, IEEE Communications Society North Jersey Chapter Seminar, Dept. of ECEC, New Jersey Institute of Technology, February 2006.
Current Trends in Steganography, Center for Development of Advanced Computing, Kolkata, India, January 2006.
Joint Source-Channel Coding: An Alternative Method for Error Resilient Communications, IEEE Signal Processing Society Colloquium, Dept of E.E, UT-Dallas, TX, November, 2003, Sponsored by the IEEE Signal Processing Society, Dallas Chapter.
Joint Source-Channel Coding for Image/Video Communications, Industry-Day, NJIT, Newark, NJ, February, 2002
Joint Source-Channel Coding for Image/Video Communications, Mitsubishi Electric Research Laboratory,Murray Hill, NJ, February, 2002
Hiding Information: How, Where and How Much? Cyber Security Seminar Series, Stevens Institute of Technology, Hoboken, NJ, November, 2001
Alternative Methods for Error Resilient Communications, Department of E.C.E, Stevens Institute of Technology, Hoboken, NJ, October, 2001
Error Resilient Multimedia Communications, Department of E.C.E, University of Houston, Houston, TX, March, 2000
Joint source-channel decoding of variable length codes, Department of Electrical Engineering, Polytechnic University, Brooklyn, NY, December, 1999
Joint source-channel decoding of variable length codes, Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, April, 1999
Reviewer (selected list)
IEEE Transactions on Communications
IEEE Transactions on Multimedia
IEEE Communications Letters
IEEE Transactions on Systems and Circuits for Video Technology
IEEE Transactions on Image Processing
IEEE Transactions on Signal Processing: Supplement on Secure Media
EURASIP Journal on Applied Signal Processing
International Journal of Network Security
IEEE Information Theory Workshop
IEEE International Conference on Communications
IEEE International Conference on Information Technology: Coding and Computing
Other Community Service
Stevens High School Liason Activities: Helped develop course plan for the Advanced Image Processing course for Science High Public School, Newark NJ, Summer 2002.
Participant in the 2001 Center for Talented Youth College Colloquium, funded by Johns Hopkins University and held at Purchase College, SUNY, Purchase, NY, October 7, 2001.
Call for Papers
IEEE Transactions on Artificial Intelligence
Special Issue on New Developments in Explainable and Interpretable AI
Motivation and Introduction
Over the years, machine learning (ML) and artificial intelligence (AI) models have steadily grown in complexity, accuracy and other quality metrics, often at the expense of interpretability of the final results. Simultaneously, researchers and practitioners have begun to realize that more transparency in the deep learning and artificial intelligence engines are necessary if the power of these engines should be adopted in practice. For example, having a very good performance metric for a disease predictor is of little use, if it is not possible to give an explanation to the end user (a physician, the patient or even the designer of the tool). Similarly, being able to understand the reasons why a model makes mistakes when it does, can add invaluable insight and is essential in critical applications.
This kind of transparency can be achieved by designing interpretable AI engines which inherently offer a window into the reasoning behind the decisions it arrives at or by designing robust post-hoc methods that can explain the decision of the AI engine.Thus, two areas of research called interpretable AI (IAI) and explainable AI (or XAI), respectively have emerged with the goal to produce models that are both well performing and understandable. Interpretable AI are models that obey some domain specific constraints so that they are better understandable by humans. In essence, they are not black-box models. On the other hand, explainable AI refers to models and methods that are typically used to explain another black-box model.
With the sizable XAI and IAI research community that has formed, there is now a key opportunity to take the field of explainable and interpretable AI to the next level, to overcome the shortcomings of current neural network explanation techniques and extend the related concepts and methods towards more widely applicable, semantically rich and actionable XAI. This special issue aims to bring together these new developments in the fascinating field of interpretable and explainable AI.
Original submissions are welcome in the topics including but not limited to:
- Explainable and interpretable AI for classification and non-classification problems (e.g., regression, segmentation, reinforcement learning)
- Explainable and interpretable state-of-the-art neural network architectures (e.g., transformers) and non-neural network models (e.g., trees, kernel-methods, clustering algorithms)
- Explainable/interpretable AI for fairness, privacy, and trustworthy models
- Novel criteria to evaluate explanation and interpretability
- Theoretical foundations of explainable/interpretable AI
- Causal mechanisms for explainable/interpretable AI
- Explainable and Interpretable AI for human-computer interaction
- Explainable and interpretable AI for applications (e.g., medical diagnosis, disaster prediction, credit underwriting, remote sensing, big data)
- Counterfactual explanations
- Human-in-the-loop explanations
Three kinds of articles can be submitted to this special issues: (1) Regular (2) Review and (3) Letters.
The special issue will follow the instructions for submission for IEEE TAI including an impact statement. Additionally, the manuscript should contain a “Interpretability/Explainability Evaluation” section. This section will include a quantification of interpretability/explainability of the proposed methods. Examples of interpretability/explainability metrics include sparsity, case-based reasoning etc. If proposing an XAI model, the authors are encouraged to include information on the goals of the explanation. For example, would the explanation provided by the model be an human understandable explanation of the black box or will it provide an approximation of a complex model.
Note that submission will be done via the manuscript central: http://mc.manuscriptcentral.com/tai-ieee
Please select the appropriate special issue when submitting.
Submission deadlines: June 1, 2022, July 1, 2022
First round of reviews due: September 15, 2022
Revised manuscripts due: October 15, 2022
Final decision: December 15, 2022
K.P. (Suba) Subbalakshmi, Stevens Institute of Technology, USA
Wojciech Samek, Fraunhofer Heinrich Hertz Institute HHI, Germany
Xia “Ben” Hu, Rice University, USA