Franziska Boenisch is a tenure-track faculty member at the CISPA Helmholtz Center for Information Security , where she co-leads the SprintML lab for Secure, Private, Robust, Interpretable, and Trustworthy Machine Learning. Her research lies at the intersection of privacy-preserving machine learning and trustworthy ML , with a focus on differential privacy , model inversion attacks , and privacy risks in federated learning . She completed her PhD at Freie Universität Berlin and was a postdoctoral fellow at the Vector Institute for Artificial Intelligence under Prof. Nicolas Papernot. Her work has been recognized with awards such as the Academics Rising Start Award (3rd Prize) and the GI Junior-Fellow honor. Her research spans a wide range of topics including memorization in diffusion models , watermarking generative models , membership inference attacks , and privacy-preserving federated learning . She has published extensively in top-tier venues like ICML , NeurIPS , ICLR , and CVPR . She is actively involved in the academic community, serving as an Area Chair for NeurIPS , Track Chair for ACM AsiaCCS , and co-organizing workshops at ICML . She is currently hiring PhDs, postdocs, and research interns for her group.
Sewon Min is an Assistant Professor at UC Berkeley's Electrical Engineering and Computer Sciences (EECS) department and a research scientist at the Allen Institute for AI. Her research focuses on Natural Language Processing (NLP) and Machine Learning, particularly Large Language Models (LLMs), emphasizing data-centric approaches and ethical AI practices. She holds a Ph.D. from the University of Washington (2024) and a B.S. from Seoul National University (2018). Her work includes advancements in retrieval-based models, mixture-of-experts architectures, and data privacy in LLMs. Notable projects include FlexOlmo (flexible data use in LLMs) and OLMoE (open mixture-of-experts models). She has been recognized with the ACM Doctoral Dissertation Award Honorable Mention (2025) and WAGS/ProQuest Innovation in Technology Award. Recent articles highlight her contributions to reasoning models, data tracing (OLMoTrace), and scalable retrieval systems (MassiveDS). She leads the Berkeley NLP Group and collaborates with BAIR, exploring topics like model transparency and ethical data usage.
Amol Deshpande is a Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley, College of Engineering. With over 160 publications spanning from 2000 to 2025, his research has significantly impacted the database systems community. His work bridges theoretical foundations with practical systems, evidenced by numerous publications in top-tier venues including SIGMOD, VLDB, and ICDE. Professor Deshpande's research focuses on database systems, with particular expertise in graph databases, data management, probabilistic databases, query optimization, and data provenance. His work addresses fundamental challenges in managing complex data, including efficient graph analytics, dataset versioning, streaming data processing, and privacy-preserving data management. Recent research directions include entity-relationship abstractions beyond traditional relations, standalone catalog engines for large data systems, and graph theoretical approaches to dataset versioning. His publication trends show a consistent focus on evolving database technologies, with early work on probabilistic databases and query optimization, transitioning to graph analytics and data provenance, and more recently addressing modern challenges in data cataloging, privacy-first data management, and serverless stream processing. His research spans both theoretical contributions (e.g., approximation algorithms for stochastic optimization) and practical systems building (e.g., RStore, TreeCat). Professor Deshpande has mentored numerous PhD students who have become active researchers in the database community, including Hui Miao, Souvik Bhattacherjee, and Konstantinos Xirogiannopoulos. His collaborative work spans across institutions, with frequent collaborations with researchers from MIT, University of Maryland, and other leading institutions. His research has been supported by major funding agencies and has influenced both academic research and industry practices in data management. The evolution of his work reflects the changing landscape of data management, from traditional relational systems to modern graph and streaming data challenges.
Gang (Gary) Tan is a Professor at the Pennsylvania State University's College of Engineering, specializing in computer security, formal methods, and programming languages. He co-directs the Institute for Networking and Security Research (INSR) and leads the Security of Software (SOS) Group, focusing on compiler, programming language, and formal method techniques to enhance computer security. Education: B.E. in Computer Science from Tsinghua University Ph.D. in Computer Science from Princeton University His research integrates formal verification with practical security applications, particularly emphasizing: Compiler-based security enforcement Side-channel mitigation in speculative execution Fairness analysis in machine learning systems Formal grammar approaches for software reliability Key article trends show: Security-focused formal methods (15% of publications) ML fairness verification (20% of recent work) Compiler-based security solutions (30% of output) Side-channel defense mechanisms (25% of research) Parser design and formal grammar synthesis (10% of contributions) Scientific achievements include: NSF CAREER Award Google Research Awards (2x) PLDI 2024 Best Paper James F. Will Career Development Professorship Outstanding Research Award at Penn State Ruth and Joel Spira Excellence in Teaching Award Dr. Tan actively contributes to academic communities through: DARPA ISAT study group membership Program committee roles (CGO 2024, ECOOP 2018, etc) Leadership in security research initiatives
Golnoosh Farnadi is an Associate Professor at the Department of Computer Science and Operational Research at the University of Montreal and an Assistant Professor at the School of Computer Science at McGill University. She holds a Canada-CIFAR Chair in Artificial Intelligence and serves as a Senior Academic Member at Mila - Quebec Institute for Artificial Intelligence. Her interdisciplinary work bridges computer science, operations research, and ethical AI considerations. Her educational background includes a Ph.D. in Computer Science from KU Leuven and Ghent University (2017), followed by postdoctoral positions at the University of Montreal/MILA (2018-2020) and the University of California, Santa Cruz (2017-2018). Her research focuses on algorithmic fairness, responsible AI, deep learning, and probabilistic models, with applications spanning healthcare, recommender systems, and public policy. Farnadi's recent publications demonstrate a strong emphasis on addressing fairness in machine learning systems, with particular attention to cultural diversity in recommender systems, fairness in healthcare optimization (particularly kidney exchange programs), and mitigating hallucinations in large language models. Her work consistently combines theoretical rigor with practical applications, often employing novel mathematical frameworks to tackle complex ethical challenges in AI. Among her notable recognitions are the Google Scholar Award (2021), Facebook Research Award (2021), Google Award for Inclusion Research (2023), and being named one of the 100 Brilliant Women in AI Ethics (2023). She was also recognized as a Rising Star in AI Ethics in 2021. Farnadi supervises numerous graduate students through her EQUAL Lab (EQuity & EQuality Using AI and Learning algorithms), which focuses on developing AI systems that promote fairness and equity. Her teaching includes courses on Responsible AI, Machine Learning, and Trustworthy Machine Learning at both McGill University and HEC Montreal.
Dr. Bo Liu is an Associate Professor in the School of Computer Science at the University of Technology Sydney (UTS), where he serves as a core member and director of the AI Security and Privacy (AISP) Research Lab at the Australian Artificial Intelligence Institute (AAII). With expertise spanning cybersecurity, privacy protection, AI and machine learning, and wireless communications, Dr. Liu has established himself as a leading researcher in the field of AI security and privacy. Dr. Liu earned his PhD from the Department of Electronic Engineering at Shanghai Jiao Tong University in 2010. His academic journey at UTS has progressed from Senior Lecturer (November 2019-December 2022) to his current position as Associate Professor (January 2023-present). Dr. Liu's research focuses on the critical intersection of artificial intelligence and security, particularly addressing emerging threats in the age of advanced AI systems. His work spans multiple dimensions of security and privacy, including deepfake detection, privacy-preserving data synthesis, AI model security, and fair machine learning. He has pioneered approaches to detect AI-generated content, protect visual privacy through de-identification techniques, and address the complex relationship between algorithmic fairness and privacy preservation. His publication record demonstrates significant contributions across multiple cutting-edge research areas, with particular emphasis on detecting and mitigating threats from generative AI systems. His recent work reveals a strong focus on deepfake detection across multiple modalities (images, video, and audio), privacy-preserving techniques for sensitive data, and the security implications of emerging AI architectures like Retrieval-Augmented Generation systems. Dr. Liu has secured substantial research funding, including as Lead Chief Investigator on multiple ARC Discovery and Linkage Projects, totaling over $3.5 million AUD. His industry collaborations include partnerships with the NSW Department of Planning and the Reserve Bank of Australia, demonstrating the practical applicability of his research. As an academic leader, Dr. Liu serves as Associate Editor for IEEE Transactions on Broadcasting and actively contributes to the academic community through conference organization, peer review for top-tier venues, and assessment for ARC grant schemes. He also teaches courses including Penetration Testing, Ethical Hacking and Offensive Security, and supervises Masters and PhD students in cybersecurity and privacy research.
Jamie Morgenstern is an Associate Professor at the Paul G. Allen School of Computer Science & Engineering , University of Washington . She was previously an assistant professor at Georgia Tech and a Warren Center Fellow at University of Pennsylvania . Expertise: Ethics & Fairness, Human-Centered AI, Machine Learning Education: PhD in Computer Science from Carnegie Mellon University (2015) Her research examines the social impact of machine learning and ensuring ML models do not exacerbate societal inequalities. She investigates robustness to human-generated training data, fairness in clustering and active learning, and algorithmic equity in recommendation systems. Recent publications focus on interactive ML systems , fairness constraints , and privacy-preserving methods across conferences like NeurIPS, ICML, and AIES. Key subfields include multimodal learning , membership inference attacks , and data equity . Scientific Awards: NSF Career award for "Strategic and Equity Considerations in ML" Simons collaboration project Simons Award for Graduate Students in Theoretical Computer Science (2014-2016) NSF GFRP fellowship Microsoft Research Graduate Women's Scholarship Spotlight presentation at NeurIPS 2015 Mentoring: She advises current PhD students Rachel Hong , Jie (Claire) Zhang , and Yuanyuan (Chloe) Yang . Former advisees include Daniel Jiang (MS), Bhuvesh Kumar (PhD), and Angel (Alex) Cabrera (BS). Grants: Funded by NSF Career award and Simons collaboration projects. Previously supported by Simons, NSF, and Microsoft Research fellowships. Labs & Collaborations: Collaborates with researchers like Michael Kearns , Aaron Roth , and Avrim Blum . Affiliated with the Allen School's Artificial Intelligence research group.
Dr. Hai Phan is an Associate Professor in Data Science at New Jersey Institute of Technology's Ying Wu College of Computing. He holds a Ph.D. in Computer Science and Engineering from CNRS, University Montpellier 2 (2013), an M.S. from Konkuk University (2010), and a B.S. from HCM City University of Technology (2008). His research explores privacy-preserving machine learning and computational health analytics: Federated learning systems and optimization Privacy-enhancing technologies (differential privacy) Health informatics and social media analysis Cybersecurity defenses and adversarial learning Fair and ethical AI systems Dr. Phan's publications demonstrate strong emphasis on federated learning architectures with privacy guarantees, defenses against emerging security threats, and analysis of health-related behaviors through social media. Recent work focuses on IoT applications, large language model security, and mobile federated learning ecosystems. His research integrates techniques from distributed systems, cryptography, and machine learning. No scientific awards are mentioned in available sources. Information regarding student advising, research grants, or laboratory affiliations is not provided in available documentation.
Hui Wang is a Professor and Associate Chair for PhD Studies and Research in the Department of Computer Science at the Charles V. Schaefer, Jr. School of Engineering and Science, Stevens Institute of Technology. She also serves as the Director of the Data Science PhD Program and holds leadership roles in multiple institutional committees, including the Doctoral Committee, Faculty Mentoring Program, and Strategic Planning initiatives at both departmental and university levels. Research Interests: Dr. Wang's research focuses on building trustworthy machine learning systems by integrating privacy, fairness, and accountability . Her work aims to fortify ML models against privacy attacks, eliminate algorithmic biases, and ensure auditable decision-making. She explores intersections between machine learning, data mining, and cybersecurity, with applications across domains requiring ethical and secure AI deployment. Recent Research Trends: Her recent publications and funded projects reflect a strong emphasis on privacy-preserving machine learning , fairness-aware systems , and verifiable computing . Themes include securing graph embeddings, federated learning with fairness guarantees, and audit mechanisms for black-box models. Supported by NSF, Cisco, and Google, her work bridges theoretical rigor with practical system design. Scientific Awards: NSF CAREER Award, 2014 Advising and Grants: Dr. Wang actively mentors PhD students and hosts visiting scholars. She leads multiple NSF-funded projects, including Securing Network Embedding against Privacy Attacks and Privacy for All: Ensuring Fair Privacy Protection in Machine Learning . Her research is supported by substantial grants from the National Science Foundation, Cisco, and Google, reflecting her leadership in trustworthy AI. Labs and Teams: While not explicitly named, Dr. Wang leads a research group focused on trustworthy machine learning, advising students and collaborating with industry partners. She is deeply integrated into the Data Science PhD program and CS faculty leadership, shaping research and academic strategy at Stevens.
Prof. Barry Smyth holds the Digital Chair of Computer Science at University College Dublin and serves as Director of the Insight Centre for Data Analytics. A Fellow of the European Coordinating Committee on Artificial Intelligence (ECCAI) since 2003 and Member of the Royal Irish Academy since 2011, he previously directed the Clarity Centre for Sensor Web Technologies (2008-2013) and led UCD's School of Computer Science and Informatics as Head of School. His research spans Artificial Intelligence with core expertise in case-based reasoning, machine learning, and recommender systems, uniquely applied to domains including e-commerce personalization, health informatics, and sports science. Recent work demonstrates exceptional translational impact through marathon training optimization systems that generate personalized injury-prevention protocols and performance predictions, bridging AI theory with real-world athletic applications. Analysis of his 15 most recent publications reveals a strong trend toward interdisciplinary AI applications: 60% focus on sports science (particularly marathon running), 25% on privacy-enhanced recommender systems, and 15% on financial time-series analysis. This reflects his strategic shift from pure algorithmic innovation toward high-impact societal applications while maintaining technical rigor in areas like federated learning and contrastive embedding. Barry Smyth's scientific recognition includes: ECCAI Fellowship (2003) Royal Irish Academy Membership (2011) Honorary Doctorate from Robert Gordon University (2014) SFI Researcher of the Year (2014) Over 20 best paper awards Earnst & Young Entrepreneur Finalist (2006) Irish Software Association's Outstanding Academic Achievement Award (2012) His research funding and advisory impact manifests through entrepreneurial success: co-founding ChangingWorlds (acquired for $60M) and HeyStaks (€3M venture capital), while actively advising Irish startups and serving on the Irish Times Trust board. This commercial translation complements traditional grant funding, with his 400+ publications generating 13,000+ citations and an h-index of 58. Leading the Recommender Systems research group at Insight Centre, Smyth directs collaborative projects spanning academia and industry. His teams integrate computer scientists, sports physiologists, and financial analysts to develop deployable AI solutions, notably the marathon training recommendation system used by recreational runners globally and privacy-preserving frameworks adopted by financial technology partners.
Jayadev Acharya is an Associate Professor in the School of Electrical and Computer Engineering at Cornell University, with graduate field memberships in Computer Science and Operations Research and Information Engineering. His research focuses on the intersection of information theory, statistical inference, algorithms, and machine learning. He explores trade-offs between data, memory, time, and robustness in learning problems, including quantum information and machine unlearning. Education: B.Tech in Electronics and Communication Engineering from Indian Institute of Technology, Kharagpur (2007) M.S. in Electrical and Computer Engineering from University of California, San Diego (2009) Ph.D. in Electrical and Computer Engineering from University of California, San Diego (2014) Research Trends: His recent work (2020-2022) emphasizes information-constrained inference, differential privacy, quantum entropy estimation, and distributed learning. Key subfields include communication complexity, local privacy, and adaptive gradient processing. His publications span NeurIPS, ICML, COLT, and IEEE Transactions on Information Theory. Awards: Kenneth A. Goldman ’71 Excellence in Teaching Award (Cornell, 2022) MIT Energy Initiative Fellowship (2014) Shannon Graduate Fellowship (UCSD, 2012) Jack Keil Wolf Student Paper Award (ISIT, 2010) Advising and Grants: He advises Sourabh Bhadane, Saravanan Kandasamy, Yuhan Liu, Ziteng Sun, and Huanyu Zhang. Research funded by NSF-CAREER, NSF-CRII, NSF-CIF small grants, and Google Faculty Research Award.
Han Wang is an Assistant Professor in the Electrical Engineering and Computer Science department at the University of Kansas School of Engineering. His research develops privacy-preserving frameworks for distributed systems, machine learning, and data analytics. Core research areas include differential privacy implementations for federated learning environments, privacy-preserving outsourcing of anomaly detection, and adversarial attack mitigation. Recent work focuses on developing staircase randomized response mechanisms that enhance privacy without compromising data utility in location services and video analytics. Publications demonstrate consistent innovation in privacy engineering with applications spanning vehicle trajectory protection, energy trading systems, and video recognition security. Methodological approaches combine theoretical privacy guarantees with practical system implementations.
Novi Quadrianto is a Professor of Machine Learning at the School of Engineering and Informatics, University of Sussex, where he joined as a Lecturer in February 2014. He is currently a Principal Investigator on three active EU grants: BayesianGDPR (ERC), TANGO (EU Horizon RIA), and Act.AI (ERC Proof of Concept). He also holds an Adjunct Professor position in Data Science at Monash University, Indonesia, and serves as Strategic Lab co-Leader of the BCAM Severo Ochoa Strategic Lab on Trustworthy Machine Learning in Bilbao, Spain. His educational background includes a PhD in Machine Learning from the Australian National University (2012) and a BEng in Electrical and Electronics Engineering from Nanyang Technological University, Singapore. During his PhD, he conducted research at multiple international institutions including HIIT-Finland, Yahoo! Research-US, University of Alberta-Canada, Fraunhofer IAIS-Germany, and IST Austria. From 2012-2014, he was a Newton International Fellow of the Royal Society at the University of Cambridge. Professor Quadrianto directs the Predictive Analytics Lab (PAL) since 2017, which focuses on "Responsible AI" research developing AI models that embed fairness, accountability, transparency, and trustworthiness. His research spans algorithmic fairness, federated learning, and computer vision, with applications in sustainable development, healthcare, and finance. His work has been funded by prestigious organizations including the European Research Council, EPSRC, and HM Treasury. His publications reveal a strong focus on addressing challenges in AI fairness, robustness, and privacy, particularly in dynamic environments and heterogeneous data settings. Recent work explores performative prediction, diversity-driven learning, and efficient vision transformer inference, demonstrating his leadership in cutting-edge machine learning research. European Research Council ERC Proof of Concept Grant (2023) Guarantor Researcher for BCAM Severo Ochoa Excellence Accreditation (2023) European Lab for Learning and Intelligent Systems (ELLIS) Scholar/Fellow (2020) European Research Council ERC Starting Grant (2019) Newton International Fellowship (2012) Microsoft Research Asia Fellowship (2009) Professor Quadrianto currently supervises six PhD students and five postdoctoral researchers. He has served as Action Editor for Transactions on Machine Learning Research since 2022 and as Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence since 2016. He has also been an Area Chair for major conferences including NeurIPS, ICML, and AAAI. His PAL laboratory hosts a team of 15 members focused on inter-disciplinary AI research with domain experts across various sectors. The PAL Lab operates three innovation strands: AI for Sustainable Development (supporting UN SDGs), AI for Healthcare (transforming health outcomes), and AI for Finance (personalized loan decision-making). The lab also leads initiatives in Diversity & Inclusion in AI and offers Pro-Bono Office Hours to organizations seeking guidance on machine learning aspects.
Jung-Eun Kim is an Assistant Professor in the Department of Computer Science at North Carolina State University, where she conducts research at the intersection of artificial intelligence, machine learning, and cyber-physical systems. Her work focuses on creating trustworthy, interpretable, and efficient AI systems, particularly for safety-critical applications. Education: Ph.D. in Computer Science, University of Illinois at Urbana-Champaign (2017) M.S. in Computer Science and Engineering, Seoul National University (2009) B.S. in Computer Science and Engineering, Seoul National University (2007) Dr. Kim's research primarily investigates how to make AI systems more trustworthy, interpretable, and efficient, with particular emphasis on understanding failure modes, safety risks, vulnerabilities, and biases in deep learning models. Her work bridges theoretical understanding with practical applications in safety-critical systems. She explores how efficiency considerations interact with these issues, seeking to fundamentally anatomize neural networks to understand what causes failure modes and how to mitigate them. Her approach has been described as 'like a heart surgeon, we open the heart of a neural network architecture, look into it, interpret it, and cure it.' Her recent publications demonstrate a strong focus on safety alignment in large language models, mitigation of spurious correlations, privacy preservation against membership inference attacks, and sustainable AI development. Her work spans theoretical foundations of trustworthy AI while addressing practical challenges in model deployment, particularly for resource-constrained environments. She has made significant contributions to understanding how model compression techniques like pruning and quantization can inadvertently amplify biases and vulnerabilities. Scientific Awards: ICLR Spotlight, 2025 IBM Faculty award, 2023 CRA Early & Mid Career Mentoring Workshop, 2023 Cloud GPU provided by Lambda, worth $17,280, for course, Spring 2023 NeurIPS Spotlight and nomination for Best Paper Award, 2022 CRA Career Mentoring Workshop, 2022 GPU Grant by NVIDIA Corporation, 2018 The MIT EECS Rising Stars, 2015 The Richard T. Cheng Endowed Fellowship, 2015-2016 Dr. Kim actively mentors PhD students, currently advising Xingli Fang, Varun Mulchandani, Jianwei Li, Rishi Singhal, and Minseon Kim. She has secured significant research funding, including an NSF SaTC (Secure and Trustworthy Cyberspace) grant as Co-PI for 'Partition-Oblivious Real-Time Hierarchical Scheduling' ($281,629.00, 2022-2024). Her research has also been supported by an NVIDIA GPU Grant and cloud resources from Lambda. She serves on program committees for top AI conferences including ICLR, ICML, NeurIPS, AAAI, and IJCAI, and has held roles such as Publicity Chair for IJCAI 2024. Her research group focuses on developing methods to make AI systems more trustworthy, interpretable, and efficient, with particular attention to safety-critical applications. The group investigates how to identify and mitigate failure modes in neural networks while maintaining efficiency, exploring the fundamental relationship between model architecture, safety risks, and computational constraints.
Yung-Hsiang Lu is a Professor of Electrical and Computer Engineering at Purdue University's Elmore Family School of Electrical and Computer Engineering. His research focuses on mobile/cloud computing, energy-efficient computing, and image/video processing. He holds a BSEE from National Taiwan University (1992), an MSEE (1996), and a PhD (2002) from Stanford University. Dr. Lu's academic background includes significant contributions to VLSI and circuit design, with primary emphasis on computer engineering. His work spans theoretical and applied domains, including optimizing neural networks for edge devices, securing deep learning models, and leveraging large language models for software development. Recent research trends in his articles emphasize energy efficiency in AI systems, interdisciplinary applications of transformers (e.g., music analysis), and challenges in model interoperability and security. His publications also highlight innovations in global camera networks and real-time visual data analysis. While no specific grants or awards are explicitly mentioned, his extensive list of publications reflects sustained academic engagement. His educational contributions include developing C programming resources and teaching large-scale image processing using global camera networks. Dr. Lu's professional address is at Purdue's Materials and Electrical Engineering Building in West Lafayette, Indiana, where he maintains an active research lab focused on embedded systems and low-power computing innovations.
