Battista Biggio is a Full Professor at the University of Cagliari, Italy, affiliated with the Department of Electrical and Electronic Engineering under the Faculty of Engineering and Architecture. His research focuses on machine learning security, adversarial attacks, and cybersecurity. He co-founded the cybersecurity firm Pluribus One and has pioneered foundational work in poisoning attacks and adversarial robustness. Education: MSc (2006), PhD (2010). He holds editorial roles as Associate Editor-in-Chief for Elsevier's Pattern Recognition Journal and serves on IEEE TNNLS and IEEE CIM editorial boards. His awards include the 2022 ICML Test of Time Award and the 2021 Pattern Recognition Medal. He chairs IAPR TC1 and organizes conferences like S+SSPR and AISec. Research interests span adversarial machine learning, malware detection, and secure AI systems. He leads initiatives such as the sAIfer Lab and co-develops the SecML-Torch library. Teaching includes courses on Machine Learning Security and Industrial Software Development. Notable contributions include seminal papers like 'Poisoning Attacks against Support Vector Machines' and 'Wild Patterns.' He manages over 10 research projects and advises on AI security for industrial applications. His work bridges academic research with practical cybersecurity solutions.
Hima Lakkaraju is an Assistant Professor at Harvard University with dual appointments in the Harvard Business School and the Department of Computer Science. Her research focuses on trustworthy AI, including machine learning interpretability, fairness, privacy, and safety. She holds a PhD from Stanford University and has received accolades such as the Alfred P. Sloan Fellowship and NSF CAREER Award. Her work bridges algorithmic foundations and societal implications of AI, with applications in healthcare, policy, and business. Education: PhD in Computer Science from Stanford University (2013-2017). Academic background includes roles at IBM Research, Microsoft Research, and Adobe. Research Interests: Algorithmic Foundations of AI Interpretability and Explainable AI Fairness and Bias Mitigation Privacy-Preserving ML Generative Models and LLMs Ethical AI Policy and Regulation Key Achievements: Over 100 publications in top venues like NeurIPS and ICML; co-founder of the Trustworthy ML Initiative; featured in MIT Tech Review, Forbes, and Harvard Business Review. Current projects include the AI4LIFE research group and work on regulatory frameworks for AI. Advising and Grants: Supervises over 30 students across PhD, master's, and postdoc levels. Research supported by NSF, Sloan Foundation, Schmidt Sciences, Google, Amazon, and others. Initiatives include the Regulatable ML workshop and NeurIPS ethics co-chair roles. Labs and Collaborations: Leads Harvard's AI4LIFE group and collaborates with industry partners like Fiddler AI. Active in policy discussions on AI regulation and societal impact.
Stephen Robert Hanneke is an Assistant Professor in the Department of Computer Science at Purdue University, specializing in theoretical machine learning and statistical learning theory. His work focuses on reducing the number of training examples required for learning, with contributions to supervised, semi-supervised, active, and transfer learning. He joined Purdue in Fall 2021 after roles including Research Assistant Professor at the Toyota Technological Institute at Chicago (2018–2021), Visiting Lecturer at Princeton University (2018), and Visiting Assistant Professor at Carnegie Mellon University (2009–2012). Education: B.S. in Computer Science from the University of Illinois at Urbana-Champaign (2005), Ph.D. in Machine Learning from Carnegie Mellon University (2009). Research interests include statistical learning theory, machine learning foundations, algorithms, and quantum computing. Notable contributions explore the theoretical underpinnings of active learning, adversarial robustness, and universal learning frameworks. His research bridges disciplines like probability theory, philosophy of science, and algorithmic information theory. Key awards include the Best Paper Award at ALT 2021 for 'Stable Sample Compression Schemes' and runner-up for COLT 2021. He has also received the COLT 2020 Best Paper Award and an Honorable Mention for the ICML 2017 Test of Time Award. His work on 'A Bound on the Label Complexity of Agnostic Active Learning' (ICML 2007) received further recognition in 2017. Teaching includes courses on machine learning theory and data mining at Purdue, Princeton, and Carnegie Mellon. He has organized workshops like the ALT 2019 'When Smaller Sample Sizes Suffice for Learning' and chaired the program committee for ALT 2017. His research outputs span over 100 publications in top venues like COLT, NeurIPS, and JMLR, focusing on foundational questions in learning theory and algorithmic efficiency.
Xiaojiang Du is the Anson Wood Burchard Endowed Professor at Stevens Institute of Technology, directing research in IoT security, AI security, and wireless networks. An IEEE Fellow and ACM Distinguished Member, he leads NSF-funded projects on secure IoT systems and cross-platform security vulnerabilities. Education PhD in Electrical Engineering, University of Maryland MS in Electrical Engineering, Tsinghua University BE in Electrical Engineering, Tsinghua University Research Focus: Develops security frameworks for IoT ecosystems and adversarial machine learning, with recent breakthroughs in smart home security anomaly detection. Honors: IEEE Fellow, ACM Distinguished Member, multiple best paper awards at IEEE conferences. Graduated PhD students hold faculty positions at UNC Charlotte, UL Lafayette, and ShanXi University. Professional Service: IEEE ComSoc Distinguished Lecturer, Associate Editor for IEEE Transactions, and General Co-Chair for IEEE/ACM IWQoS 2023. Secured $9M+ in research funding from NSF, NSA, and DOD.
Una-May O'Reilly is a Principal Research Scientist at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), leading the ALFA group. She holds a PhD in Computer Science from Carleton University (1995), with prior roles including a postdoctoral appointment at MIT's Artificial Intelligence Laboratory. Her research focuses on cybersecurity, adversarial AI, software security, and disinformation dynamics, applying evolutionary algorithms and machine learning to address arms races in cyber defense and societal challenges like climate change communication. Education: B.Sc., University of Calgary M.C.S., Carleton University Ph.D., Carleton University (1995) Research Interests: Adversarial machine learning for secure systems Coevolutionary algorithms in cybersecurity and healthcare Program comprehension via neuroscience and AI Climate disinformation mitigation on social media Large language model applications in code synthesis and threat hunting Key Projects: Adversarial Cyber Security : Modeling cyber attack-defense arms races GIGABEATS : AI-driven medical sensor data analysis for critical care MOOC Learner Project : Data science for online education insights Awards: EvoStar Award (2013) for contributions to evolutionary computation Fellow of ACM Sig-EVO Leadership & Service: Co-founder and Vice-Chair of ACM Sig-EVO Former Chair of GECCO (2005), major evolutionary computation conference Editorial roles in Evolutionary Computation and Genetic Programming and Evolvable Machines Labs & Groups: Leads the AnyScale Learning for All (ALFA) group at CSAIL, focusing on scalable AI for cybersecurity, healthcare, and education.
Gautam Kamath is an Assistant Professor at the University of Waterloo's Cheriton School of Computer Science, a Faculty Member at the Vector Institute, and a Canada CIFAR AI Chair. He leads The Salon, a research group focused on statistics, algorithms, machine learning, and optimization. His work bridges theoretical foundations with practical applications in data privacy and robustness, contributing to both academic research and real-world deployments that impact millions of users. Dr. Kamath earned his PhD and SM degrees in Electrical Engineering and Computer Science at MIT, where he was advised by Costis Daskalakis. Prior to MIT, he graduated from Cornell University in May 2012 with a degree in Computer Science and Electrical and Computer Engineering, where he worked with Bobby Kleinberg. His academic journey reflects a strong foundation in both theoretical computer science and practical applications. His research focuses on developing solutions for trustworthy and reliable machine learning and statistics, with particular emphasis on data privacy and robustness. He addresses fundamental problems in these areas, revitalizing statistical toolkits for the modern data era where privacy preservation is paramount. His work spans theoretical foundations of differential privacy to practical applications that have been deployed at scale, including contributions to systems that protect the sensitive information of hundreds of millions of individuals. Analysis of his recent publications reveals a strong trend toward addressing the interplay between privacy, robustness, and machine learning performance. His work increasingly examines practical deployment challenges while maintaining theoretical rigor, with growing emphasis on diffusion models, generative AI, and the legal implications of AI systems. There's a clear trajectory from foundational privacy theory toward addressing real-world implementation challenges across diverse application domains. Canada CIFAR AI Chair Ontario Early Researcher Award 2024 Caspar Bowden Award for Outstanding Research in Privacy Enhancing Technologies STOC Best Student Presentation Award ICML 2024 Best Paper Award Microsoft Research Fellow at the Simons Institute for the Theory of Computing Dr. Kamath actively mentors students, with notable successes including Valentio Iverson winning the Germain-Erdős Undergraduate Award and Chris Trevisan receiving the CRA Outstanding Undergraduate Researcher Award. His service to the research community is extensive, serving as Editor-in-Chief of TMLR, on the Executive Committee of the Learning Theory Alliance, and on steering committees for major conferences including ICML, COLT, and ALT. He has organized numerous workshops focused on privacy-preserving machine learning and differential privacy. Through The Salon research group, Dr. Kamath fosters a collaborative environment where postdoctoral fellows, graduate students, and undergraduates work together on cutting-edge problems at the intersection of statistics, algorithms, machine learning, and optimization. The group maintains strong connections with industry partners and participates in major research initiatives, including the Vector Institute's privacy and security research efforts. Looking forward, Dr. Kamath will be moving to the Computer Science department at NYU's Courant Institute of Mathematical Sciences in September 2026, where he plans to expand his research program.
Gang Wang is an Associate Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign (UIUC), affiliated with the Siebel School of Computing and Data Science. He also holds affiliate roles in the Department of Electrical and Computer Engineering, the Informatics Program (School of Information Sciences), and the Coordinated Science Laboratory (CSL). He joined UIUC in 2019, previously serving as an Assistant Professor at Virginia Tech. Education: Ph.D. in Computer Science from UC Santa Barbara (2016), advised by Ben Y. Zhao and Heather Zheng; B.E. from Tsinghua University (2010). Awards include the NSF CAREER Award (2018), Amazon Research Award (2021), and multiple best paper awards in top conferences like USENIX Security and ACM CCS. Research focuses on Security and Privacy, Internet Measurement, and Data Mining. Key areas include email spoofing vulnerabilities, adversarial machine learning, and AI-driven security tools. Recent projects involve explainable AI for phishing detection, benchmark contamination in LLMs, and mitigating deepfake disinformation. Publications span top venues like USENIX Security, IEEE S&P, ACM CCS, and IMC. He collaborates with industry partners and researchers in HCI and AI. Current roles include Associate Director of the Capital One Illinois Center for Generative AI Safety (ASKS) and leadership in NSF-funded initiatives like the ACTION AI Institute.
Ying Cai is an Associate Professor in the Department of Computer Science at Iowa State University, joining in 2003 after earning his Ph.D. in Computer Science from the University of Central Florida (2002). His research focuses on AI, machine learning, data science, cybersecurity, privacy protection, and database systems. He leads projects funded by the Air Force Research Laboratory, including work on authentication data structures for rank-aware queries, requiring U.S. citizenship and expertise in linear algebra/cryptography. Dr. Cai’s work spans cybersecurity (e.g., adversarial example defense, secure secret sharing), spatio-temporal systems (e.g., traffic risk prediction, check-in time modeling), and healthcare AI (e.g., cervical spine diagnosis with transformers). His publications emphasize practical applications of ML in privacy, security, and distributed systems. Professional roles include Associate Editor for Multimedia Tools and Applications (since 2009), Co-chair for COMPSAC TAIN/NCIW symposium (2014–2017), and TPC Chair for Mobilware 2010. His service includes contributions to INFOCOM, ICDCS, and MDM conferences. Current research opportunities exist for graduate students with strong programming/math skills, particularly in cryptography and linear algebra. He emphasizes interdisciplinary work, such as bridging AI with social sciences via large language models.
Prof. Margret Keuper is a Professor of Machine Learning at the University of Mannheim's School of Business Informatics and Mathematics, leading the Data and Web Science Group. She is also affiliated with the Max-Planck-Institute for Informatics and ELLIS (fellow since 2024). Her research focuses on robust deep learning, neural architecture search, and computer vision tasks like motion segmentation and adversarial defense. She holds a PhD from the University of Freiburg and previously held positions at the University of Siegen and the University of Mannheim. Her work spans projects funded by DFG and BMBF, including Climate Visions for social media analysis and TrackOpt for motion tracking. She teaches courses on computer vision, generative models, and reinforcement learning. She actively serves on program committees for top conferences like CVPR, ECCV, and NeurIPS, and is an associate editor for IEEE TPAMI and JAIR. Education: PhD in Computer Science from University of Freiburg (advisor: Thomas Brox) Research Projects: Learning to Sense (DFG), Climate Visions (BMBF), TrackOpt (BMBF) Key Roles: Head of Mannheim Master in Data Science Examination Board, Member of MSc Business Informatics Board Her research emphasizes robustness in AI systems, with contributions to adversarial attacks, domain generalization, and efficient solvers for large-scale problems. She advises over 15 PhD students across academic and industry partnerships.
WonSook Lee is a tenured Full Professor in the School of Electrical Engineering and Computer Science at the University of Ottawa’s Faculty of Engineering. Her expertise spans medical imaging, machine/deep learning, computer graphics, and computer vision. She earned her Ph.D. in Computer Science from the University of Geneva (Switzerland) and holds degrees from POSTECH (Korea) and NUS (Singapore). Before academia, she worked at Korea Telecom, Samsung Advanced Institute of Technology, and Eyematic Interfaces Inc. (USA). Her research focuses on applications such as virtual/augmented reality, MRI/CT/Ultrasound analysis, and 3D mesh modeling. She has authored over 130 publications, including 30+ journal papers, and serves on conference committees and editorial boards. Lee has secured major grants (NSERC, CFI, ORF) as Principal Investigator and contributed to global initiatives like South Korea’s National Research Foundation. Her lab explores cutting-edge techniques in medical imaging, AI-driven object detection, and multimodal systems. Notable projects include adversarial perturbation analysis for model robustness, cross-domain GANs for semantic segmentation, and real-time ultrasound-enhanced pronunciation training. She actively promotes interdisciplinary research in healthcare technology and autonomous systems.
Julia Kempe is a Silver Professor of Computer Science, Mathematics, and Data Science at New York University (NYU), holding joint appointments at the Courant Institute and the Center for Data Science (CDS). She serves as Director of the CDS and is on research leave at the CSD, ENS, Paris (2023–24). Her expertise spans interdisciplinary research in quantum computing, machine learning, and data science. She holds PhDs in Mathematics (UC Berkeley, 2001) and Computer Science (École Nationale Supérieure des Télécommunications, Paris, 2001), alongside advanced degrees in theoretical physics and mathematics from prestigious institutions in France and Austria. Research Interests: Data Science, Machine Learning (theoretical foundations and applications to physics), and past contributions to quantum computing. She focuses on robustness in machine learning models, adversarial examples, and interdisciplinary applications of physics-informed AI. Awards and Honors: Knight of the National Order of Merit (France, 2010), Femme en Or de la Recherche (France, 2010), ERC Starting Grant (2007, top-ranked in Europe), and numerous academic fellowships. She is a member of Academia Europaea (2018) and a Fellow of the Asia-Pacific Artificial Intelligence Association (2022). Grants and Leadership: Principal investigator of NSF NRT grants for CDS PhD programs, co-PI on NASA TCAN grants, and leader in NYU’s Senior Leadership Team. She designed NYU’s Data Science undergraduate programs and expanded interdisciplinary collaborations in machine learning and quantum computing. Labs and Teams: Directs the CDS, collaborates with the Courant Institute, and leads research initiatives in Paris. Her work bridges theoretical computer science, physics, and applied data science, emphasizing interdisciplinary innovation.
Christopher Kruegel is a Professor in the Department of Computer Science at the University of California, Santa Barbara (UCSB), where he conducts research in systems security. He is affiliated with the International Secure Systems Lab (iSecLab) and was a co-founder of Lastline, Inc., which was acquired by VMware in 2020. His work focuses on creating practical security solutions that address real-world problems through system building and experimental validation. Professor Kruegel's research spans multiple areas of computer security including malware analysis, web security, network security, and vulnerability analysis. His work often involves developing systems that analyze programs for malicious behavior, scanning web applications for vulnerabilities, and improving privacy on social networks. He has made significant contributions to firmware security, smart contract analysis, and mobile security through his extensive publication record. His 15 most recent publications (2022-2023) demonstrate a strong focus on practical security solutions across diverse domains including firmware security (Shimware, Fuzzware), blockchain and smart contract security (Confusum Contractum, NFT security), mobile security (TEEzz, Columbus), and vulnerability detection techniques (Actor, Toss a Fault to Your Witcher). His research shows consistent innovation in security tools and methodologies with several papers receiving distinguished awards. Fellow of the Institute of Electrical and Electronics Engineers Outstanding Graduate Mentor Award, UCSB Academic Senate Distinguished Artifact Award for Fuzzware paper Distinguished Paper Award for Ramblr paper Best Student Paper Award for Detecting Spammers On Social Networks Professor Kruegel has advised numerous graduate students and collaborated extensively with researchers at UCSB and beyond. His work has been funded by various research grants supporting his security research initiatives. He is actively involved in the International Secure Systems Lab, which focuses on practical security solutions for real-world problems.
Pascal Mettes is a tenured Assistant Professor at the University of Amsterdam within the Informatics Institute, specializing in Artificial Intelligence. He leads groundbreaking research in hyperbolic deep learning, a field he has significantly advanced through theoretical developments and practical applications in computer vision and multimodal learning. His research focuses on three primary domains: hyperbolic vision-language models that address the hierarchical nature of language-vision relationships; hierarchical deep learning using hyperbolic embeddings that naturally accommodate exponential growth patterns; and robust deep learning in hyperbolic space that improves out-of-distribution detection and network resilience. Mettes has established himself as a leading figure in this emerging field through numerous publications at top-tier conferences including CVPR, ICCV, ICML, NeurIPS, and ICLR. His recent work demonstrates how hyperbolic geometry provides natural solutions to fundamental limitations in modern deep learning, particularly regarding hierarchical data structures that cannot be adequately represented in Euclidean space. The publication trends show increasing impact and recognition in the computer vision and machine learning communities, with multiple papers receiving oral presentations and best paper nominations. Best paper nomination ESWC25 for 'Designing Hierarchies for Optimal Hyperbolic Embedding' Finalist MM 2023 Best Open-Source Software Competition (for HypLL) Multiple reviewer awards across major conferences including CVPR, ICLR, ECCV, ICML, and NeurIPS MM 2016 Best Doctoral Student Award TRECVID 2015 Winner Multimedia Event Detection Benchmark Mettes actively mentors eight PhD students working on hyperbolic learning and related topics, while also securing significant research funding including ELLIs PhD Award, NWO ClickNL, Google Perception Academic Funding, and Data Science Centre PhD Grants. He serves in prominent academic roles as Program Chair for International Conference on Multimedia Retrieval 2026 and has organized multiple workshops on hyperbolic learning at major conferences. His leadership in establishing hyperbolic deep learning as a recognized research direction is evident through his survey paper in IJCV 2024 and the development of the HypLL library for hyperbolic learning.
Ke Xu is a Professor in the Department of Computer Science at Tsinghua University's School of Information Science and Technology. With extensive research contributions in network security, privacy-preserving technologies, and machine learning applications for networking, Professor Xu has established himself as a leading researcher in computer science. Professor Xu's research interests span network security, privacy-preserving technologies, machine learning for networking, federated learning, internet protocols, encrypted traffic analysis, blockchain applications, and AI in networking. His work bridges theoretical foundations with practical implementations, focusing on real-world security challenges and network optimization problems. He has developed novel frameworks for secure network operations, privacy-preserving data sharing, and efficient AI deployment in distributed environments. Professor Xu's publication record shows a clear trend toward integrating artificial intelligence with traditional networking challenges. His recent work explores federated learning security, encrypted traffic analysis using deep learning, and novel approaches to network security that leverage machine learning techniques. The interdisciplinary nature of his research spans computer networking, security, privacy, and artificial intelligence. Professor Xu has received recognition for his contributions to network security and privacy-preserving technologies through publications in top-tier venues including IEEE journals, ACM conferences, and security symposia. His work has appeared in IEEE Transactions on Dependable and Secure Computing, IEEE/ACM Transactions on Networking, and security conferences like CCS and NDSS. Professor Xu actively collaborates with researchers across institutions, supervising students and junior researchers in exploring cutting-edge problems in network security and AI. His research has been supported by significant grants focusing on network security, privacy, and intelligent networking infrastructure. He leads projects that address fundamental challenges in secure communication, privacy-preserving data analysis, and intelligent network management. Professor Xu is involved with research laboratories focusing on network security and intelligent systems at Tsinghua University. His team works on developing practical security solutions, privacy frameworks, and AI-enhanced networking protocols that address real-world challenges in today's increasingly connected world.
Sebastian Szyller serves as an Assistant Professor in the Department of Computer Science at Aalto University, Finland, where he is a core member of Adjunct Professor N. Asokan's research group. His academic role centers on advancing security frameworks for machine learning systems through rigorous theoretical and empirical research. His research expertise spans machine learning security , adversarial machine learning , and model ownership verification , with particular emphasis on defense mechanisms against model extraction attacks, unintended interactions among security measures, and intellectual property protection for AI models. Key contributions address the tension between model confidentiality and practical deployment requirements in real-world systems. Analysis of his 2019-2024 publications reveals an evolving research trajectory from foundational model extraction defenses (e.g., PRADA, 2019) to sophisticated analyses of defense interactions (SoK, 2024) and ownership resolution frameworks (False Claims, 2024). His work consistently bridges theoretical security principles with practical ML deployment challenges, establishing critical benchmarks for model protection. Dr. Szyller actively contributes to premier security venues including IEEE Symposium on Security and Privacy, USENIX Security Symposium, and AAAI conferences. His collaborations within Asokan's research group demonstrate strong interdisciplinary engagement in securing machine learning ecosystems, with recent work expanding into multimedia security and eCommerce fraud detection applications.
