Find Academic Supervisors

Professor Po-Ling Loh is a faculty member at the University of Cambridge, affiliated with the Statistical Laboratory within the Faculty of Mathematics. Her research focuses on statistical theory and methodology, with applications in machine learning, robust statistics, and medical imaging. She holds a professorship position and contributes to advancing computational and theoretical frameworks for high-dimensional data analysis. Loh’s work addresses challenges such as robust regression, differential privacy, and efficient algorithms for complex models. Her educational background includes studies at Cambridge and further academic pursuits, though specific degree details are not provided here. Research interests span statistical learning, adversarial machine learning, and the mathematical foundations of robust algorithms. She actively publishes in top-tier journals and conferences, addressing topics like neural network regularization, privacy-preserving synthetic data, and network analysis. Notably, Loh collaborates on projects involving medical image analysis (e.g., bone age estimation via BAE-ViT) and has contributed to methodological advancements in hypothesis testing and privacy-constrained inference. Her research often bridges theory and practice, emphasizing computational efficiency and statistical rigor. While no specific grants or awards are listed, her prolific publication record reflects sustained academic impact in statistical and machine learning domains. Loh is associated with the Statistical Laboratory, contributing to its research initiatives and possibly advising students in high-dimensional statistics and related fields. Her work frequently intersects with interdisciplinary applications, such as medical imaging and network science, underscoring the practical relevance of her theoretical contributions.

• Statistical Learning
• Robust Statistics
• High-Dimensional Statistics
• +3 more

Philip S. Yu is a Distinguished Professor in the Department of Computer Science at the University of Illinois at Chicago and holds the Wexler Chair in Information Technology. Previously, he led the Software Tools and Techniques department at IBM Thomas J. Watson Research Center. Education: B.S. in Electrical Engineering, National Taiwan University M.S. and Ph.D. in Electrical Engineering, Stanford University M.B.A., New York University His research spans data mining , big data , social networks , privacy-preserving data publishing , graph/network mining , recommender systems , and deep learning . He has authored over 970 papers with 74,500+ citations and an H-index of 127. Recent work focuses on heterogeneous graph representation, quantum walks in network analysis, and federated unlearning. Scientific Honors: ACM SIGKDD 2016 Innovation Award IEEE Computer Society 2013 Technical Achievement Award IEEE ICDM 2003 Research Contributions Award IEEE Region 1 Award (1999) UIC Research of the Year (2013) IBM Master Inventor with 300+ patents AI 2000 Most Influential Scholar Honorable Mentions (2024-2025) He served as Editor-in-Chief for ACM Transactions on Knowledge Discovery from Data and IEEE Transactions on Knowledge and Data Engineering , and on steering committees for ACM KDD and IEEE Data Mining. His work bridges theoretical advances in graph neural networks , deep learning , and privacy-preserving systems with applications in healthcare, social media, and enterprise analytics.

• Data Mining
• Big Data
• Privacy-Preserving Data Publishing
• +9 more

Xiangyu Zhang is the Samuel D. Conte Professor of Computer Science at Purdue University. He specializes in AI security, software analysis, and cyber forensics, with a focus on detecting vulnerabilities in traditional software and AI systems. His research includes dynamic slicing, program profiling, and securing AI models against backdoors. He has led projects funded by DARPA, IARPA, NSF, and industry, securing over $13 million in grants. He has mentored 30+ PhD students and postdocs, many of whom hold academic positions or industry roles. His work has been recognized with awards like the ACM SIGPLAN Distinguished Dissertation Award and NSF Career Award. Education: PhD, Computer Science, University of Arizona (2006) MS & BS, Computer Science, University of Science and Technology of China (2000 & 1998) Research Interests: AI Security: backdoor detection, adversarial attacks, model integrity Program Analysis: dynamic slicing, static/dynamic debugging Cyber Forensics: log analysis, attack investigation Software Reliability: fault localization, vulnerability detection Key Projects: DARPA V-SPELLS: domain-specific program analysis IARPA TrojAI: AI backdoor detection competitions NSF-funded research on model debugging and co-reasoning of software/NL artifacts Awards & Recognition: Top performer in IARPA TrojAI competitions (13/18 rounds) ACM SIGPLAN Distinguished Dissertation Award (2006) NSF Career Award (2009) Ranked 8th globally in systems research productivity (2024) Career Contributions: Secured over $13M in research funding Guided 25 PhDs and 8 postdocs Published 89+ top-tier papers (2014–2024)

• AI Security
• Software Engineering
• Programming Languages and Compilers
• +5 more

Florian Tramèr is an Assistant Professor in the Department of Computer Science at ETH Zurich, Switzerland, leading research at the intersection of machine learning security, privacy, and AI safety. His work focuses on identifying and mitigating security vulnerabilities in machine learning systems, particularly in large language models and other AI systems. Tramèr's primary research interests include adversarial machine learning, membership inference attacks, privacy-preserving AI, and the security implications of large language models. His work has significantly advanced our understanding of how machine learning models memorize training data, how this memorization creates privacy risks, and how to evaluate the robustness of machine learning systems against various attacks. His recent publications demonstrate a strong focus on practical security challenges in deployed AI systems, including data extraction from language models, adversarial attacks against generative AI, and developing more rigorous evaluation methodologies for machine learning security. Tramèr's research has been published in top venues including ICLR, NeurIPS, ICML, and IEEE Security & Privacy. Tramèr is actively collaborating with leading researchers in the field including Nicholas Carlini, Matthew Jagielski, and Javier Rando, contributing to important initiatives like the International AI Safety Report. His work bridges theoretical security concepts with practical implications for real-world AI deployment.

• Machine Learning Security
• AI Safety
• Privacy in Machine Learning
• +4 more

Dai Zhongxiang is an Assistant Professor and Presidential Young Fellow at the School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHKSZ), where he joined in August 2024. Previously, he was a Postdoctoral Associate at MIT's Laboratory for Information and Decision Systems (January-June 2024) and a Postdoctoral Fellow at the National University of Singapore's Department of Computer Science (April 2021-December 2023). He completed his Ph.D. in Artificial Intelligence at NUS under the supervision of Bryan Kian Hsiang Low and Patrick Jaillet. Dr. Dai's research focuses on the intersection of theoretical and practical AI, with particular emphasis on large language models (LLMs) and optimization techniques. His work spans both theoretical foundations of multi-armed bandits and Bayesian optimization, as well as practical applications in LLM inference, including prompt optimization, in-context learning, personalization of LLMs, LLM-based agents, and scaling up test-time computation of LLMs. His research approach often bridges theoretical principles with real-world applications, particularly in AI4Science problems. His recent publications demonstrate a clear trend toward advancing LLM capabilities through optimization techniques, with increasing focus on practical deployment challenges. The research spans both theoretical contributions to optimization theory and applied work on enhancing LLM performance in real-world scenarios. His work on dueling bandits, neural bandits, and zeroth-order optimization has been consistently published in top-tier venues including NeurIPS, ICML, ICLR, and ACL. Presidential Young Fellow, CUHKSZ (2024) Dean's Graduate Research Excellence Award, NUS (2021) Research Achievement Award × 2, NUS (2019 & 2020) Singapore-MIT Alliance Graduate Fellowship (2017) Dr. Dai actively mentors multiple Ph.D. students and research assistants, with several of his students' papers accepted to top conferences. His research has received significant attention, with invitations to serve as Area Chair for NeurIPS 2025 and ICLR 2025, reflecting his growing influence in the machine learning community. His work bridges theoretical machine learning with practical applications in large-scale AI systems.

• Large Language Models Inference
• Prompt Optimization
• In-context Learning
• +5 more

Eric Wong is an Assistant Professor in the Department of Computer and Information Science at the University of Pennsylvania, affiliated with the ASSET Center and leading the Brachio Lab. His research focuses on robust and reliable machine learning, including model debugging, adversarial robustness, and explainable AI. He holds a PhD from Carnegie Mellon University (CMU), advised by J. Zico Kolter, and completed a postdoc with Aleksander Madry. His work bridges theory and practice, addressing challenges in model interpretability, safety, and scalability. Teaching includes CIS 5200 (Machine Learning), CIS 3333 (Mathematics for Machine Learning), and a specialized course on debugging ML pipelines. Notable contributions include the FIX Benchmark for interpretable features and defenses against LLM jailbreaking attacks. He received an Amazon Research Award in 2024 and has published extensively in top conferences like ICML, NeurIPS, and ICLR. Affiliations: University of Pennsylvania (CIS), ASSET Center, Brachio Lab Education: PhD in Machine Learning (CMU), Postdoc at MIT Key Projects: FIX Benchmark, DOLPHIN framework, SmoothLLM defense Awards: Amazon Research Award (2024) Lab Focus: Safe AI, model debugging, neurosymbolic learning

• Machine Learning
• Artificial Intelligence
• Explainable AI
• +5 more

Elisa Ricci is a Full Professor at the Department of Information Engineering and Computer Science (DISI) at the University of Trento and serves as Head of the Research Unit Deep Visual Learning at Fondazione Bruno Kessler. She coordinates the Doctoral Program in Information Engineering and Computer Science at the University of Trento and holds prestigious fellowships from ELLIS and IAPR. Her research focuses on advancing computer vision and deep learning systems capable of operating in open-world environments. Key interests include domain adaptation, continual learning, and self-supervised learning for visual and multi-modal data processing. Her work addresses critical challenges in enabling machines to adapt to new domains without forgetting prior knowledge, with applications spanning robotics perception, medical imaging, and privacy-preserving AI systems. Recent publications reveal a dominant trend toward leveraging vision-language models for open-vocabulary tasks, training-free adaptation methods, and federated learning architectures. Significant research thrusts include machine unlearning for privacy, robustness against bias in visual classifiers, and novel class discovery using foundation models—particularly evident in 2025 publications addressing medical imaging, 3D segmentation, and collaborative generative systems. Her major recognitions include: ELLIS Fellow IAPR Fellow As Doctoral Program Coordinator at the University of Trento, she oversees PhD training while leading the Deep Visual Learning unit at Fondazione Bruno Kessler. Her research group secures competitive grants in AI-driven perception systems, though specific funding sources aren't detailed in the source material. The Deep Visual Learning Research Unit specializes in open-world computer vision challenges, developing frameworks for domain adaptation, continual learning, and multi-modal perception. Current projects integrate generative models with robotics applications while addressing privacy concerns in vision-language systems through unlearning techniques.

• Computer Vision
• Deep Learning
• Robotics Perception
• +5 more

Nihar B. Shah is an Associate Professor at Carnegie Mellon University with joint appointments in the Machine Learning and Computer Science departments within the School of Computer Science. His research focuses on developing theoretically grounded algorithms for evaluating scientific work, with applications in peer review, fairness, and human-AI collaboration. His work has impacted over 100,000 research papers and grant evaluations. Education: Ph.D. in EECS, UC Berkeley M.E. in Telecommunications, Indian Institute of Science B.Tech. in Electronics, NIT Karnataka Research Interests: Shah's group investigates the science of evaluation through machine learning, optimization, and large-scale experiments. Key areas include peer review systems, algorithmic fairness, LLM applications in science, and human-AI collaboration frameworks. Research addresses fundamental questions about research validity, funding allocation, and equitable assessment. Publication Trends: Recent work focuses on improving peer review through randomized controlled trials, security against collusion, LLM-based review systems, and bias mitigation. Publications consistently appear in premier venues (NeurIPS, PLOS ONE, AAAI) with growing emphasis on real-world deployments. Awards & Honors: Young Alumnus Medal (IISc 2024) NSF CAREER Award (2020-2025) Google Research Scholar Award (2021) Multiple best paper awards (HCOMP, ICLR) Research Group & Funding: Leads a focused research team with NSF, Google, and JP Morgan support. Alumni hold positions in academia and industry. Current projects involve large-scale evaluations of scientific work and algorithmic fairness.

• Machine Learning
• Peer Review Systems
• Algorithmic Fairness
• +4 more

Reza Shokri is a Dean's Chair Associate Professor in the Department of Computer Science at the National University of Singapore (NUS), School of Computing. His research lies at the intersection of data privacy, security, and trustworthy machine learning, with a focus on quantifying privacy risks and developing robust, fair, and interpretable models. PhD in Computer Science, EPFL His research interests center on data privacy and trustworthy machine learning , particularly in the context of deep learning and federated systems. He investigates how machine learning models memorize training data, leading to privacy leakage, and designs frameworks to audit and mitigate such risks. His work bridges theoretical guarantees with practical applications, emphasizing the trade-offs among privacy, fairness, robustness, and utility. His recent publications (2023–2025) reveal a strong trend in analyzing privacy in large language models (LLMs), membership inference attacks, federated learning, and fairness. These works are published in top venues such as NeurIPS, ICML, ICLR, CCS, and FAccT, highlighting his leadership in both AI and security communities. Notable scientific awards include: Asian Young Scientist Fellowship (2023) Intel Outstanding Researcher Award (2023) Best Paper Award, ACM FAccT (2023) IEEE S&P Test-of-Time Award (2021) Caspar Bowden Award for Privacy Enhancing Technologies (2018) NUS Presidential Young Professorship (2019–2023) VMware Early Career Faculty Award (2021) He has advised numerous PhD and Master’s students, many of whom have contributed to high-impact publications. He has also received research grants from major industry partners including Meta, Google, Intel, and VMware. He leads the Data Privacy and Trustworthy Machine Learning Lab at NUS and has served on program committees for top conferences such as IEEE S&P, ACM CCS, and FAccT, including co-chairing roles at HotPETs and Shadow PC of IEEE S&P. He has delivered tutorials at ICML and CCS on privacy auditing in machine learning. His lab focuses on developing tools and frameworks—such as the ML Privacy Meter—for assessing and improving the privacy properties of machine learning models, with applications in regulatory compliance and secure AI deployment.

• Data Privacy
• Trustworthy Machine Learning
• Security
• +7 more

John Duchi is an Associate Professor at Stanford University, holding positions in the Department of Statistics and the Department of Electrical Engineering (with a courtesy appointment in Computer Science). He is affiliated with the School of Engineering. His research focuses on statistical learning, optimization, information theory, and computation, with an emphasis on balancing computational efficiency, privacy, and robustness. Key interests include developing algorithms for large-scale optimization, privacy-preserving techniques, and tools for evaluating machine learning systems' validity. Education: BS and MS in Computer Science (Stanford University, 2007–2008), MA in Statistics (UC Berkeley, 2012), and PhD in EECS (UC Berkeley, 2014). Research Interests: His work addresses three core areas: (1) optimizing trade-offs between computational resources and statistical performance, (2) creating scalable optimization methods, and (3) quantifying confidence in machine learning systems. Recent publications highlight contributions to privacy in federated learning, robust statistical validation, and uncertainty quantification. Articles: His recent work explores topics like distribution-free M-estimation, private federated learning, and instance-optimal mechanisms for statistical estimation. These studies emphasize privacy, robustness, and scalable solutions for modern data challenges. Advising & Grants: While no advisees are listed, his research has been supported by grants focused on optimization, privacy, and statistical theory.

• Statistical Learning
• Optimization
• Privacy in Machine Learning
• +3 more

Dr. Mohammad Zulkernine is a Full Professor and Canada Research Chair in Cyber-Physical System Security at Queen’s University’s School of Computing (Faculty of Arts and Science). He leads the Queen’s Reliable Software Technology (QRST) research group and directs the Queen’s Centre for Security & Privacy. His research focuses on secure software systems for cyber-physical systems, including autonomous vehicles, IoT, and cloud computing. Dr. Zulkernine holds a cross-appointment in Electrical and Computer Engineering and is a licensed Professional Engineer in Ontario. Education: BSc (Bangladesh BUET), MEng (Japan), PhD (University of Waterloo). He joined Queen’s in 2003 and has held sabbaticals at University of Trento, Italy and Irdeto Canada. He has published over 250 papers, led 35+ research projects, and supervised 120+ students. Awards include Canada Research Chairs (Tier I and II), Queen’s Excellence in Graduate Supervision Award, and Distinguished Supervision Award from the School of Computing. Research Interests: Cyber-Physical System Security, Software Reliability, IoT Security, Vehicle Networks, Secure Software Engineering, and Cybersecurity Risk Assessment. Active industry collaborations include EU-funded projects and Canada-Africa initiatives.

• Cyber-Physical System Security
• Software Reliability
• Security Engineering
• +6 more

Sascha van Schendel is an Assistant Professor in Data Protection & Cybersecurity at the Department of Law & Markets, Erasmus School of Law, Erasmus University Rotterdam. She is affiliated with the Erasmus Centre of Law and Digitalization and contributes to the Sectorplan SSH-Breed research initiative on the influence of digitalization on work, prosperity, and entrepreneurship. Her research lies at the intersection of law, technology, and fundamental rights, with a focus on data protection, privacy, algorithmic governance, and the regulation of emerging technologies in public and environmental domains. She has published widely on topics including GDPR compliance, privacy by design, smart energy systems, AI in criminal justice, and the legal implications of predictive policing. The recent publications reflect a strong trend toward the regulation of data in public infrastructure (e.g., energy grids), algorithmic accountability in law enforcement, and the integration of legal and technical perspectives in privacy-preserving systems. Her work spans environmental law, criminal procedure, and digital constitutionalism, demonstrating interdisciplinary reach. Scientific Awards: No awards explicitly mentioned in the provided text. Advising and Grants: While no formal PhD or Master’s students are listed, Dr. van Schendel has been involved in significant research projects such as the NWO-funded Megamind project on smart energy grids, indicating experience with competitive grant funding. She actively collaborates with legal scholars and contributes to public policy debates, including responses to national legislation like the Dutch Cybersecurity Bill. Labs and Teams: She is a core member of the Erasmus Centre of Law and Digitalization, a research hub focusing on the legal challenges of digital transformation. Her work is embedded in interdisciplinary collaborations involving law, technology, and public policy experts.

• Data Protection Law
• Privacy Law
• Cybersecurity
• +12 more

Ferdinando Fioretto is an Assistant Professor of Computer Science at the University of Virginia, leading the Responsible AI for Science and Engineering (RAISE) group. His research focuses on foundational challenges in AI, privacy, fairness, and the intersection of machine learning and optimization. He holds a dual PhD in Computer Science from the University of Udine and New Mexico State University. Affiliations: University of Virginia (current), Syracuse University (former), Georgia Institute of Technology (postdoc), University of Michigan (research fellow) Education: PhD (Udine & NMSU), B.S. (University of Parma) Research Interests: Machine Learning, Responsible AI, Optimization, Differential Privacy, Algorithmic Fairness. His work emphasizes practical applications in energy systems, court scheduling, and privacy-preserving machine learning. Recent projects include neuro-symbolic diffusion models, fairness-aware optimization, and privacy guarantees in LLMs. Grants & Funding: NSF CAREER Award, Google Faculty Research Award, Amazon Research Award, NVIDIA Academic Grant, and grants from the LaCross Institute and 4-VA. His group collaborates with institutions like George Mason University and Virginia Tech. Key Awards: NSF CAREER (2022), IJCAI Early Career Spotlight (2022), Caspar Bowden PET Award (2022), ACP Early Career Researcher Award (2021) Labs/Teams: RAISE group at UVA, focused on trustworthy AI, fair optimization, and privacy-preserving systems. Active in organizing workshops like NeurIPS Algorithmic Fairness and AAAI Privacy-Preserving AI.

• Machine Learning
• Responsible AI
• Optimization
• +3 more

Dr. Sirui Li is a Lecturer at Murdoch University's School of Information Technology within the College of Science, Technology, Engineering and Mathematics. Her research focuses on Artificial Intelligence, Natural Language Processing (NLP), Machine Learning, Knowledge Graphs, Data Analysis, Temporal Data, and Multi-modal Models, with applications in medicine, agriculture, and mining. She collaborates with industry partners like BHP and has published in journals such as Food Chemistry and Knowledge and Information Systems , as well as conferences like ICSME and IJCNN. Education: Bachelor of Advanced Computing (Honours) in Computer Science at Australian National University Master of Computing (Specialising in AI) at ANU Ph.D. in Information Technology (AI) at Murdoch University Research interests include interdisciplinary applications of AI, such as clinical coding privacy solutions, disease spread modeling, and drug repurposing for pandemics. Her work emphasizes practical industry integration, demonstrated through awards like the 2024 EMNLP Best Demo Award and the 2023 Iron Ore Circuit Hackathon innovation prize. Professional roles include IEEE Western Australia Section committee membership, conference chair positions, and peer review for top journals. She actively mentors students pursuing Honours, Master's, or PhD projects in her areas of expertise.

• Natural Language Processing
• Knowledge Graphs
• Machine Learning
• +5 more

Jiliang Tang is an MSU Foundation Professor in the Department of Computer Science and Engineering at Michigan State University (MSU), part of the College of Engineering. He holds a PhD from Arizona State University (2015) and previously worked as a research scientist at Yahoo Research. His research focuses on graph machine learning, trustworthy AI, and applications in education and biology. He has received numerous awards, including the 2022 AI's 10 to Watch, IAPR J.K. Aggarwal Award, and NSF CAREER Award. Education: PhD in Computer Science, Arizona State University, 2015 (Advisor: Huan Liu) Research Interests: Graph Neural Networks (GNNs) and Deep Learning on Graphs Trustworthy AI: Safety, Robustness, and Fairness AI+X Applications: Education Technology and Biological Data Analysis His work bridges theoretical advancements and practical applications, with contributions to graph representation learning, privacy in generative models, and educational AI systems. Awards & Recognition: Over 8 best paper awards (or runner-ups) Rock Star Award from Association of Chinese Scholars in Computing Extensive media coverage for innovations in AI education and biology Grants & Projects: NSF CAREER Award (2019) for research on signed networks Co-PI on a $1.7M grant for 5G research Leadership in projects like DSE Lab and Data Science initiatives Labs & Teams: Directs the Data Science and Engineering (DSE) Lab at MSU, focusing on advancing AI for real-world challenges. The lab collaborates with industry leaders and publishes widely in top conferences (e.g., KDD, SIGIR, ACL).

• Graph Machine Learning
• Trustworthy AI
• Deep Learning
• +3 more