Daniel Müller-Gritschneder is an Adjunct Teaching Professor (Privatdozent) at the Technical University of Munich (TUM), affiliated with the Chair of Electronic Design Automation. He leads the 'Electronic System Level' research group, focusing on embedded systems, TinyML, virtual prototyping, and hardware resilience. He temporarily served as head of the Chair of Real-Time Systems (2019–2020) and holds a senior membership in IEEE. His research spans: TinyML : Optimizing neural network inference for microcontrollers. Virtual Prototyping : Fast simulation for embedded software development (e.g., ETISS simulator). Runtime Verification : Hardware monitoring for safety-critical systems. Fault Tolerance : Cross-layer resilience against soft errors. Design Automation : NoC synthesis and RISC-V toolchain optimization. His publications emphasize RISC-V-based systems, TinyML deployment, fault injection, and embedded AI. Recent works show trends toward compiler-assisted security, thermal management, and automated design-space exploration for edge devices. Awards: Best Paper Award (SiPS 2019) Habilitation Award (Bund der Freunde der TUM, 2019) 2nd Best Paper (SMACD'15) Best Paper nominations at DAC'07, DATE'10, Analog'10, NOCS'13 He advises researchers in the Electronic System Level group and contributes to EU projects (e.g., Scale4Edge). His lab develops tools like ETISS, MLonMCU, and Seal5 for RISC-V and TinyML ecosystems.
Dr. Yang Zhang is a tenured Professor at the CISPA Helmholtz Center for Information Security . His research focuses on Trustworthy Machine Learning , emphasizing privacy, safety, and security , with additional work on measuring misinformation and unsafe online content like hateful memes. He has published extensively at top conferences (CCS, NDSS, Oakland, USENIX Security) and received multiple awards including the Busy Beaver Award (2022) and NDSS Distinguished Paper Award (2019) . Research Interests : Trustworthy Machine Learning LLM Security, Privacy, and Safety Misinformation and Hate Speech Detection Social Network Analysis Recent Publications examine synthetic data auditing, hate speech detection in LLM-generated content, and privacy risks in curriculum learning, spanning conferences like USENIX Security , IEEE S&P , and ACM CCS . His work often intersects AI security with ethical considerations . Scientific Awards : Busy Beaver Award for “Privacy of Machine Learning” (2022) NDSS Distinguished Paper Award (2019) CCS Best Paper Runner-Up (2022) Best Machine Learning and Security Paper in Cybersecurity Award (2025) Best Paper Finalist at CSAW Europe (2023, 2024) Students in his group include Yixin Wu , Xinyue Shen , and Yiting Qu , the latter recently completing their Ph.D. defense. He actively recruits MSc and PhD students and has contributed to iDRAMA Lab for meme-related research.
Dr. Yanjun Zhang is an Honorary Research Fellow at the School of Electrical Engineering and Computer Science, The University of Queensland. His research focuses on privacy-preserving technologies, federated learning, cybersecurity in IoT systems, and machine learning security. He holds a PhD in Privacy-Preserving Sharing for Genome-Wide Analysis from The University of Queensland (2021). Education: PhD in Information Technology, School of Information Technology and Electrical Engineering, The University of Queensland (2021) Research Interests: Designing secure collaborative machine learning frameworks Defending against adversarial attacks in cyber-physical systems Privacy preservation in distributed genomic and medical data analysis Compliance and ethics in virtual personal assistant applications Key Contributions: Developed privacy-preserving federated learning frameworks (AgrAmplifier, PrivColl) Conducted foundational studies on evasion attacks in IoT systems Created datasets for analyzing malicious browser extensions and Alexa skills Labs/Teams: Active contributor to UQ Cyber initiatives, including the 2021-2022 Seed Funding project on federated deep learning for medical imaging.
Golnoosh Farnadi is an Assistant Professor at McGill University's School of Computer Science , an Adjunct Professor at Université de Montréal , and a Visiting Faculty Researcher at Google Research . She holds the Canada CIFAR AI Chair and is a core academic member of Mila – Quebec AI Institute . Her research focuses on algorithmic fairness , responsible AI , and optimization . She founded the EQUAL Lab (EQuity & EQuality Using AI and Learning algorithms) to address bias and discrimination in AI systems. Key publications explore fairness in kidney exchange programs, generative model geometry, multilingual LLM de-biasing, and prototype-based recommender systems. Her work bridges causal inference, adversarial robustness, and ethical AI. Google Award for Inclusion Research (2023) Women in AI Awards North America Finalist (2023) Facebook Privacy Enhancing Technologies Award (2021) IVADO Postdoctoral Fellowship (2018–2021) She has supervised over 15 PhD and Master's students, including Prakhar Ganesh (McGill) and William St-Arnaud (Université de Montréal). Her teaching includes Responsible AI and Machine Learning courses at McGill and HEC Montréal.
Dr. Dima Alhadidi is an Associate Professor in the School of Computer Science at the University of Windsor. His research focuses on Cybersecurity, Data Privacy, Machine Learning, and their applications in Health Informatics, Cloud Computing, and Smart Grids. He holds a PhD in Computer Science and Software Engineering from Concordia University (2010). His research interests include secure federated learning frameworks, privacy-preserving techniques for genomic and health data, and adversarial machine learning defenses. Notable contributions include Trustformer (2025), secure aggregation methods in federated learning, and hybrid malware classification using deep learning. Recent work emphasizes mitigating membership inference attacks and developing privacy-preserving analytics for distributed systems. Dr. Alhadidi actively advises graduate students on topics like social network clustering (NICASN 2022) and federated learning security. No scientific awards are explicitly listed. His research spans theoretical frameworks (e.g., λ_AOP calculus) to applied systems in smart grids and healthcare informatics.
Dr. Hongsheng Hu is currently a Lecturer in the School of Information and Physical Sciences at the University of Newcastle, Australia, specializing in the Data Science and Statistics focus area. Prior to this position, he served as a Postdoc Research Fellow at CSIRO's Data61 from October 2022 to August 2024. His academic journey includes a Doctor of Philosophy in Computer Systems Engineering from the University of Auckland in New Zealand, establishing his foundation in advanced computing systems. Dr. Hu's research centers on enhancing the trustworthiness of machine learning systems, with particular emphasis on identifying critical privacy vulnerabilities within machine learning models and developing robust defensive strategies. His work spans several key domains including adversarial machine learning (30% focus), statistical data science (30% focus), and data and information privacy (40% focus). He investigates membership inference attacks, machine unlearning techniques, and privacy-preserving mechanisms in federated learning environments. His research addresses fundamental challenges in AI security, exploring how machine learning models can be compromised through sophisticated privacy attacks and developing methods to mitigate these vulnerabilities while maintaining model utility. Analysis of Dr. Hu's publication record reveals a strong research trajectory focused on machine learning security and privacy. His work consistently addresses vulnerabilities in machine learning systems, particularly examining membership inference attacks, machine unlearning mechanisms, and privacy-preserving techniques in federated learning. The research spans top-tier venues including IEEE Security & Privacy, USENIX Security, NDSS, NeurIPS, IJCAI, AAAI, and WWW, demonstrating both technical depth and recognition by the research community. His publications show an evolving focus from foundational privacy attacks to developing more sophisticated unlearning techniques and robust defense mechanisms, with increasing citation counts indicating growing impact in the field. Active Program Committee member for USENIX Security, NDSS, ICLR, IJCAI, WWW, ICDM, ECML, and PKDD Invited reviewer for IEEE Transactions on Information Forensics and Security (TIFS), IEEE Transactions on Dependable and Secure Computing (TDSC), IEEE Transactions on Pattern Analysis and Machine Intelligence (IPAMI), and ACM Computing Surveys (CSUR) Dr. Hu currently serves as Course Coordinator for STAT6020 and STAT2020 Predictive Analytics at the University of Newcastle. As an academic supervisor, he co-supervises one PhD student working on 'Identifying and Mitigating Vulnerability in Recommender Systems' at Macquarie University. His research collaborations span multiple countries, with significant publication counts in Australia (18), China (12), New Zealand (10), and the United States (7), reflecting an active international research network focused on AI security challenges.
Simon Oya is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of British Columbia (UBC), Faculty of Applied Science. He holds a PhD in Information Technologies and Communications from the University of Vigo (Spain) and was previously a postdoctoral fellow at the Cryptography, Security and Privacy (CrySP) group at the University of Waterloo. His educational background includes: BSc, MSc, PhD from University of Vigo (Spain) Simon Oya's research focuses on designing and evaluating privacy-enhancing technologies with strong privacy and utility guarantees. He approaches privacy problems from a statistical perspective, using theoretical tools from signal processing and information theory to quantify privacy leakage and develop effective defenses. His primary research areas include: Privacy-preserving searchable encryption Machine learning privacy (particularly membership inference attacks) Anonymous communication systems Location privacy Differential privacy His publication record demonstrates a consistent focus on analyzing and improving privacy mechanisms across various domains. His recent work has particularly emphasized the intersection of machine learning and privacy, as well as advancing techniques for searchable encryption. His research methodology typically involves developing statistical models to understand privacy leakage and designing optimization-based approaches to improve privacy-utility tradeoffs. His notable scientific contributions include developing attacks against searchable encryption schemes to better understand their privacy limitations, and designing improved privacy mechanisms for location-based services. His work on statistical disclosure attacks against anonymous communication systems has also been influential in the field. As an educator, he teaches CPEN 442: Introduction to Cybersecurity at UBC. He actively seeks motivated graduate students interested in privacy research, particularly those with strong backgrounds in statistics, machine learning, or optimization.
Urs Hengartner is an Associate Professor at the Department of Computer Science, University of Waterloo. His research focuses on information privacy, computer and network security with emphasis on smartphones, IoT, and machine learning-based authentication systems. He holds a Ph.D. (2005) and M.Sc. (2003) from Carnegie Mellon University, and a Diploma from ETH Zürich (1997). His work spans Adaptive security attacks on ML systems Implicit user authentication frameworks Privacy-preserving technologies for location and genomic data Secure authentication systems resilient to voice/spoofing attacks Recent publication trends show a strong focus on adversarial attack detection (e.g., watermarking evasion, diffusion model attacks) and context-aware authentication systems . His frameworks like MRAAC and SHRIMPS address multi-stage authentication challenges in mobile ecosystems. Key contributions include frameworks for evaluating multi-user authentication systems (SHRIMPS), risk-aware access control (MRAAC), and novel defense strategies against collaborative robot traffic fingerprinting. His work bridges security mechanisms with user-centric design principles.
Anna Monreale is an Associate Professor in the Department of Computer Science at the University of Pisa and a key member of the Knowledge Discovery and Data Mining Laboratory (KDD-Lab), a joint research group with the Information Science and Technology Institute of the National Research Council (ISTI-CNR) in Pisa. Her academic career is rooted in the University of Pisa, where she completed her Bachelor's, Master's, and Ph.D. in Computer Science. Her research focuses on privacy-preserving data analytics, with core interests in big data analytics, social network analysis, spatio-temporal mining, and explainable AI. She is particularly known for her work on privacy-by-design in data mining and evaluating privacy risks in analytical processes. Her research bridges technical innovation with ethical and legal considerations in data science. Her recent publications reveal a strong trend toward explainable AI, privacy in federated learning, and risk assessment in mobility and health data. She actively contributes to developing methods for explaining black-box models, assessing privacy exposure, and balancing privacy, utility, and fairness in AI systems. Privacy by Design Ambassador (2014) ISTI-CNR Young++ Researcher Award (2014) Monreale has advised and co-chaired several international workshops, including PriSMO, PinSoDa, and MoKMaSD, and serves on editorial boards such as Transactions on Data Privacy. She teaches advanced data mining, big data ethics, and database systems across multiple graduate and undergraduate programs. She is involved in major EU projects like SoBigData, XAI, TAILOR, and HumMingBird, reflecting her leadership in data science and AI ethics. She is affiliated with the KDD-Lab, a prominent research group focused on knowledge discovery, social mining, and big data analytics, contributing to both theoretical advances and real-world applications in privacy-aware data science.
Agostino Cortesi is a Full Professor at Ca' Foscari University of Venice , affiliated with the Department of Environmental Sciences, Informatics and Statistics. He serves as Rector's Delegate for Research Quality Assessment and Deputy Coordinator of the Scientific Committee for the Innovation Ecosystem Project. His academic career includes a PhD in Applied Mathematics and Informatics from the University of Padova (1992), a postdoctoral fellowship at Brown University, and visiting professor roles at institutions such as the University of Illinois and École Normale Supérieure Paris. Research interests focus on software engineering , static analysis , security applications , and abstract interpretation . He has pioneered techniques for formal verification of software systems and explored cybersecurity in e-Government and robotics. His work spans over 200 publications in top journals and conferences (e.g., ACM TOPLAS, IEEE TSE, POPL, PLDI). Key contributions include advancements in abstract domains for behavioral property verification and security-oriented analysis frameworks. He has held leadership roles including Vice-Rector at Ca' Foscari, Dean of Computer Science programs, and Chair of the Department of Computer Science. Cortesi coordinates EU Horizon 2020 projects (e.g., Families_Share €1.6M) and regional initiatives like CEVID (€360K). He founded Factors , a university spin-off focused on robotic systems verification, which won the 2020 Veneto SmartCup ICT Prize. Education: PhD in Applied Mathematics and Informatics (1992, University of Padova) Editorial Roles: Co-Editor-in-Chief of Springer’s 'Services and Business Process Reengineering', and member of editorial boards for 'Computer Languages' and others Grants: Over €3M in EU and regional funding for projects in cybersecurity, Industry 4.0, and digital innovation Teaching includes courses on Software Correctness , Data Programming , and Computer Networks across Computer Science and Management programs. His research lab actively engages in industrial partnerships with Cisco, Leonardo, and AGID (Italy’s Digital Agency).
Hongxin Hu is a Professor and Associate Chair in the Department of Computer Science and Engineering at the University at Buffalo, State University of New York (SUNY). His research spans security, networking, and machine learning, with publications across top conferences including security (S&P, CCS, USENIX Security, and NDSS), networking (SIGCOMM and NSDI), machine learning (NeurIPS, ICML, and EMNLP), and human-computer interaction (CHI and CSCW). His work has been funded by NSF (SaTC, CNS, IIS, OAC, SOC), USDOT, VMware, Amazon, Google, and Dell. Dr. Hu earned his PhD in Computer Science and Engineering from Arizona State University in 2012. His academic journey has led him to become a prominent researcher in cybersecurity with a strong publication record and significant research impact. Dr. Hu's research interests encompass a wide range of topics at the intersection of security, networking, and artificial intelligence. His work focuses on Emerging Network Technologies and Security (5G/Future-G, NFV, SDN, Edge computing), Machine Learning for Security and Privacy , Security and Privacy in IoT and Cyber-Physical Systems , and AI for Social Good (addressing online abuse, unsafe children's games, and cyberbullying). His interdisciplinary approach has enabled him to tackle complex security challenges through innovative solutions that combine networking expertise with machine learning techniques. His recent publications demonstrate a strong trend toward applying large language models and advanced machine learning techniques to security challenges, particularly in content moderation, vulnerability detection, and privacy protection. The research spans multiple domains including voice assistant security, IoT security, network security, and social media safety, showing a consistent pattern of addressing real-world security problems with cutting-edge technical approaches. IEEE Big Data Security Senior Research Award (2025) ACM SACMAT Test-of-Time Award (2024) NSF CAREER Award (2019) Multiple Best Paper Awards from ACM ASIACCS (2022), ACSAC (2020), IEEE ICC (2020), and ACM SIGCSE (2018) Amazon Faculty Research Award (2022) First Place Award in ACM SIGCOMM 2018 Student Research Competition Dr. Hu has successfully advised multiple PhD students, including Nishant Vishwamitra who joined UT San Antonio as a tenure-track Assistant Professor. His research has been generously funded by major agencies and industry partners. As an active member of the academic community, he serves as Associate Editor for IEEE Transactions on Dependable and Secure Computing and Computers & Security, and has held numerous leadership roles in major security conferences including TPC Co-Chair for ASONAM 2025 and IWSPA 2024/2025. Dr. Hu leads a vibrant research group that has produced significant contributions in network security function virtualization, intrusion detection systems, and privacy-preserving technologies. Current projects include developing LLM-assisted vulnerability detection systems, defenses against jailbreak attacks on large language models, and security mechanisms for emerging networking technologies. His team's work on IoT security, voice assistant applications, and online content moderation has received wide recognition and press coverage.
Yan Wang is a Full Professor in the School of Computing at Macquarie University, Australia. He obtained his PhD from Harbin Institute of Technology (HIT), China, and has been at Macquarie since 2003 following a postdoctoral fellowship at the National University of Singapore. His research focuses on trust management, recommender systems, social networks, and services computing, with a strong emphasis on applications in cyber security and data analytics. Wang has published extensively in top-tier venues like AAAI, IJCAI, and IEEE Transactions, and has led over 25 research projects, including current initiatives like Trust-Oriented Data Analytics in Online Social Networks (DP230100676) and Combating Fake News on Social Media (2020–2023). He has received prestigious awards such as the IEEE TCSVC Outstanding Service Award (2017) and the Vice-Chancellor’s Excellence in Research Supervision Award (2014). He serves on editorial boards of journals like IEEE Transactions on Services Computing and has organized major conferences including IEEE ATC2013 and IEEE CLOUD2017. His work bridges theoretical advancements in machine learning and practical challenges in social computing, edge computing, and federated learning. Affiliations: School of Computing, Data Horizons Research Centre, Frontier AI Research Centre Key Projects: Trust-Oriented Data Analytics in Online Social Networks (2023–2026) Combating Fake News on Social Media (2020–2023) Research Themes: Recommender systems, graph learning, fake news detection, and trust management in distributed systems. Wang’s recent work explores causal representation learning, cross-domain recommendations, and privacy-preserving techniques in edge computing environments.
James B D Joshi is a Professor in the Department of Informatics and Networked Systems (DINS) at the University of Pittsburgh’s School of Computing and Information (SCI). He joined Pitt in 2003 after earning his PhD from Purdue University. From 2019 to 2023, he served as a Program Director for the NSF’s Secure and Trustworthy Cyberspace (SaTC) program. Currently, he is an intermittent Expert in NSF’s TIP Directorate and led the NSF PDaSP program. His research focuses on cybersecurity and privacy, including access control, AI/ML security, cloud/edge security, and privacy-preserving techniques. Education: PhD, Computer Engineering, Purdue University (2003) MS, Computer Science, Purdue University (1998) BE, Computer Science & Engineering, Motilal Nehru NIT, India (1993) Research Interests: Privacy, security, trust, attribute-based encryption, cloud security, insider threat detection, and privacy-preserving AI/ML. His work emphasizes trustworthy systems and secure distributed computing environments. Recent Contributions: His articles span privacy-preserving federated learning, insider threat mitigation, and secure edge computing. Recent projects include PPFL-RDSN (2025), TAPFed (2024), and blockchain-based transparency frameworks (2022). Awards & Honors: NSF Director’s Award (2023), IEEE Fellow (2023), ACM Distinguished Member (2017), NSF CAREER Award (2006), and SIRI Research Leadership Award (2018). Service & Leadership: Founding director of LERSAIS lab, co-chair of IEEE conferences (TPS, CIC, CogMI), and former Editor-in-Chief of IEEE Transactions on Services Computing. Active in NSF and NITRD policy initiatives, including privacy and digital assets R&D strategies.
Jie Ding is an Associate Professor at the University of Minnesota's School of Statistics with graduate faculty appointments in Electrical Engineering, Computer Science, and the Data Science Program. He serves as a core faculty member of the Data Science and AI Hub and holds an Amazon Scholar position with the Amazon AGI Team focusing on foundation model training. His educational background includes a Ph.D. in Engineering Sciences from Harvard University (2017), postdoctoral work at Duke University (2018), and a B.S. from Tsinghua University where he participated in both the Math & Physics Academic Talent Program and Electrical Engineering program. Ding's research sits at the intersection of artificial intelligence, statistics, and scientific computing, with focus areas including Agentic AI for autonomous data science workflows, AI Foundations for interpretability and trustworthiness, Scalable Modeling for broader AI accessibility, Decentralized and Collaborative AI systems, and AI Safety addressing privacy and security concerns. He developed the STAT 8931 Generative AI course with open-source materials available at genai-course.jding.org . His recent publications demonstrate strong activity across multiple AI subfields, particularly in value alignment (MAP framework), AI safety mechanisms, federated learning innovations, and statistical foundations for modern AI systems. The breadth of venues (ICML, ICLR, NeurIPS) indicates significant impact across the AI research community. NSF CAREER Award (2024) Army Early Career Program (Young Investigator) Award (2023) Cisco Research Award (2022-25) AWS Cloud Credits for Research (2021-22) Meta/Facebook Faculty Research Award (2021-22) UMN Thank-A-Teacher Teaching Award (2019-20) Ding leads the Agentic AI for Data Science Benchmark initiative, collaborating with University of Minnesota colleagues and Minnesota industry partners to evaluate AI agent capabilities across healthcare, insurance, retail, energy and other sectors. His research group actively recruits PhD students interested in AI/Statistics intersections, with focus on developing theoretically grounded yet practically impactful AI systems.
Debabrota Basu is a tenured faculty member (Inria Starting Faculty Position - ISFP) at the Scool team (previously called SequeL) of Inria Centre at University of Lille in France. He teaches postgraduate-level courses on privacy, responsible machine learning, and research methods in AI at École normale supérieure-PSL University, Université de Lille, and Centrale Lille. He is also a member of the ELLIS Society (European Laboratory for Learning and Intelligent Systems) and the Paris unit of ELLIS. Dr. Basu earned his PhD in Computer Science from the Department of Computer Science, School of Computing, National University of Singapore, advised by Stéphane Bressan and Pierre Senellart. Prior to that, he obtained a B.E. degree with Honours in Electronics and Telecommunication Engineering from Jadavpur University. Before joining Inria, he was a postdoctoral researcher at Chalmers University of Technology's Data Science and AI Division. Dr. Basu's research focuses on constructing algorithms for developing efficient, robust, private, and ethical learning machines that solve real-world problems. His methodological approach blends statistics, machine learning, and optimization. His application interests span sustainable agro-ecology, medical and pharmaceutical applications, energy-efficient autonomous systems, and algorithmic audits. Recent collaborations include the Inria-Indian Statistical Institute associate team SeRAI for developing Sequential Testing and Learning Algorithms for Verifiably Robust and Responsible AI, and the Inria-INRAE collaboration on Resilient Agricultural Decision Making under Environmental Risks. His publication record demonstrates expertise in bandit algorithms, reinforcement learning, and privacy-preserving machine learning. Recent work shows a strong theoretical foundation with practical applications, particularly in pure exploration bandits, differential privacy mechanisms, constrained optimization, and fairness verification. His research bridges the gap between theoretical guarantees and real-world deployment challenges across multiple domains. Dr. Basu has received notable recognition for his contributions: Best Student Paper Award at ACM EAAMO 2022 for 'On Meritocracy in Optimal Set Selection' Young researcher (JCJC) grant from the French National Research Agency (ANR) in 2022 in 'Artificial Intelligence and Data Science' He leads the project 'RL under Real-life Constraints: Regrets and Algorithms' and supervises PhD students and postdoctoral researchers. His research is supported by multiple projects including REPUBLIC ('Vers l'IA responsable avec l'apprentissage par renforcement sous contraintes') and 'Foundations of robustness and reliability in artificial intelligence.' Dr. Basu actively collaborates with institutions worldwide, including establishing the RELIANT associate team with Kyoto University for investigating structured multi-armed bandit problems.
