جست‌وجوی استاد و پژوهشگر

• Distributed Systems
• AI/ML Security
• Adversarial Machine Learning
• +۳ مورد دیگر

Professor Peter Garraghan is a full Professor of Distributed Systems at Lancaster University, UK, an EPSRC Fellow (2021-2026), and CEO of the AI-security spin-out Mindgard. His work bridges large-scale distributed systems, AI/ML security, and sustainable computing, with 60+ peer-reviewed publications and active grants totalling millions in research funding. Education: Ph.D. in Computer Science, University of Leeds, UK Research Interests: Garraghan’s research empirically investigates and designs secure, sustainable, and scalable systems . Core themes include adversarial machine-learning attacks and defences , energy-adaptive cloud/datacentre technologies , and orchestration of distributed AI services . He integrates rigorous experimentation in both laboratory testbeds and live production environments to deliver measurable improvements in security, performance, and carbon footprint. Recent projects explore model-extraction threats against LLMs , green AI prompting , 6G-enabled cloud-edge scheduling , and waste-heat reuse from servers. His group’s outputs have been featured by the BBC, Daily Mail, and leading security venues, underlining societal as well as scientific impact. Grants & Industry Links: EPSRC Fellowship on sustainable distributed AI (2021-26) UKRI National Edge-AI Hub (£multi-institution, 2024-29) Projects with Microsoft, NVIDIA, BT, BBC, Alibaba, STFC, UK Government, UK defence & datacentre sectors PhD Supervision & Team: He currently supervises seven funded PhD researchers across topics such as AI security, energy-aware scheduling, and adversarial ML defence, and welcomes new applicants—multiple fully-funded studentships are available.

• Cryptography
• Side-channel Analysis
• Deep Learning Security
• +۵ مورد دیگر

Stjepan Picek serves as an Associate Professor at Delft University of Technology in the Intelligent Systems school and maintains a secondary affiliation with Radboud University's Digital Security Group in Nijmegen, The Netherlands. His research bridges cryptographic theory with practical machine learning applications, particularly focusing on security vulnerabilities in modern computing systems. Dr. Picek's research spans multiple critical areas in cybersecurity, with particular emphasis on deep learning-based side-channel analysis where he has published extensively on improving attack methodologies and countermeasures. His work on cryptographic Boolean functions explores evolutionary computation approaches to design functions with optimal cryptographic properties. More recently, his research has expanded to AI security , investigating backdoor attacks, membership inference vulnerabilities, and covert channels in large language models. Analysis of his recent publications reveals a clear trajectory toward integrating traditional cryptographic techniques with modern machine learning paradigms. His work demonstrates consistent innovation across three main axes: (1) advancing side-channel analysis through deep learning innovations, (2) developing evolutionary methods for cryptographic primitive design, and (3) identifying and mitigating security vulnerabilities in emerging AI systems. This multidisciplinary approach positions his research at the critical intersection of theoretical cryptography and practical security implementation. Dr. Picek maintains extensive collaborations with researchers across Europe, particularly with Domagoj Jakobovic (104 co-publications), Luca Mariot (56), Lejla Batina (56), and Guilherme Perin (56), indicating a well-established research network and leadership in his field. His publication record shows remarkable productivity with over 380 indexed publications, including 63 in 2023, 53 in 2024, and 24 in 2025, demonstrating sustained research momentum.

Sabina Rossiمشاهده پروفایل

استاد

• Formal Methods
• Distributed Systems
• Markovian Models
• +۳ مورد دیگر

Sabina Rossi is a Full Professor in the Department of Environmental Sciences, Informatics and Statistics at Ca' Foscari University of Venice, where she also serves as Rector's Delegate for digital innovation in teaching. Her research develops formal methods for analyzing distributed systems with mobility and concurrency, specializing in process algebraic techniques for performance evaluation, verification, and dependability analysis of complex systems. Recent work extends to Markovian models for wireless networks, blockchain verification, and neural network compression. Her research investigates foundational models of distributed systems, with current emphasis on reversible computation, proportional lumpability in Markov chains, and blockchain security properties. She applies formal methods to analyze information flow security, model checking, and performance evaluation of stochastic systems. Recent publications (2020-2025) address queueing models with job stealing policies, blockchain verifier's dilemma, selfish mining attacks, and neural network compression via formal methods. Teaching responsibilities include 'Formal Methods for System Verification' in the Computer Science graduate program, 'Discrete Structures' for undergraduates, and foundational computer science courses for humanities students. She maintains office Z.B01 at the university's Scientific Campus via Torino in Venice.

Zhi Zhangمشاهده پروفایل

مدرس

• System Security
• Rowhammer Exploits
• Adversarial Artificial Intelligence
• +۳ مورد دیگر

Zhi Zhang is a Lecturer in the Department of Computer Science and Software Engineering at the University of Western Australia (UWA), affiliated with the UWA Defence and Security Institute. Prior to this role, he worked as a Research Scientist at CSIRO’s Data61. He holds a PhD in Computer Science from the University of New South Wales, focusing on 'Software-only Rowhammer Attacks and Countermeasures.' His research expertise spans system security, rowhammer exploits, adversarial AI, and federated learning security. He has contributed to UN Sustainable Development Goals related to education and innovation. His research focuses on hardware-software co-design vulnerabilities, including rowhammer-based attacks, adversarial machine learning defenses, and data poisoning in federated learning. Notable areas of contribution include interrupt side-channel attacks, thermal event exploitation, and model unlearning mechanisms. He has published extensively in top-tier journals/conferences like IEEE Transactions on Information Forensics and Security, and has received Distinguished Paper Awards in 2023 and 2024. Education: PhD in Computer Science (UNSW, 2021) Key Research Areas: Rowhammer Exploits & Mitigations Adversarial Attacks on DNNs Federated Learning Security Interrupt-Based Side Channels His work bridges theoretical computer security with practical system implementations, addressing critical vulnerabilities in modern architectures. Collaborations span academia and industry, with impactful contributions to hardware-software security domains.

Erhard Rahmمشاهده پروفایل

استاد

• Data Integration
• Knowledge Graphs
• Privacy-Preserving Data Analysis
• +۴ مورد دیگر

Prof. Dr. Erhard Rahm is a leading computer science academic at the University of Leipzig , affiliated with the Institute of Computer Science under the Faculty of Mathematics and Computer Science. With over 35 years of research contributions, he specializes in scalable data integration, privacy-preserving record linkage (PPRL), and graph analytics for knowledge graphs and digital twins. Key research areas: Data Integration for Knowledge Graphs, Privacy-Preserving Data Analysis, Dynamic Graph Management Recent work focuses on hybrid digital twins, medical image analysis, and secure health data processing 2016-2021: Speaker of GI's Database Systems and Information Systems division Scientific Contributions: His 15 most recent publications (2023-2025) span: Privacy-preserving machine learning (federated learning, PPRL with LLMs) Graph-based data transformations (Temporal Knowledge Graphs, Property Graph Streams) Automated schema matching and entity resolution systems Biomedical data applications (cell confluence assessment, stress detection) Selected Honors: VLDB Ten-Year Best Paper Award (2011) ICDE Influential Paper Award (2013) MSR Outstanding Collaborator Award (2016) Leadership Roles: Currently Vice President of the Gesellschaft für Informatik (since 2022), former DFG reviewer (2016-2024), and active in NFDI infrastructure (2019-2022). He leads research at ScaDS.AI, focusing on big data integration and scalable graph analytics.

Qi Leiمشاهده پروفایل

استادیار

• Machine Learning
• Deep Learning
• Optimization
• +۳ مورد دیگر

Qi Lei is an Assistant Professor of Mathematics and Data Science at New York University's Courant Institute of Mathematical Sciences and Center for Data Science. By courtesy, they also hold an Assistant Professor position in Computer Science. Dr. Lei is a member of the CILVR lab and Math and Data groups, and serves as a Google DeepMind Faculty. Dr. Lei's research focuses on machine learning, deep learning, and optimization , with particular interest in developing sample- and computationally efficient algorithms for fundamental machine learning problems. Their recent work spans several key areas: Data and Model Pruning Data Reconstruction Attack and Defense Theoretical Foundations of Pre-trained Models Analysis of Dr. Lei's recent publications reveals a strong focus on theoretical foundations of machine learning, particularly around data efficiency, model robustness, and privacy. Their work bridges theoretical guarantees with practical applications, demonstrating expertise in both the mathematical underpinnings of learning algorithms and their real-world implementation. A notable trend is the increasing focus on privacy-preserving machine learning and defenses against data reconstruction attacks. Dr. Lei is actively involved in academic service, having organized the minisymposium "Efficient Computation and Learning with Randomized Sampling and Pruning" at SIAM MDS 2024 and delivered invited talks at prestigious venues including IMS@NUS, ICSDS, Harvard Statistics, and workshops on Data-driven PDE-based inverse problems and Large Language Models. As an educator and mentor, Dr. Lei welcomes self-motivated students to collaborate on research projects. They advise prospective Ph.D. applicants to apply through Courant Mathematics or the Center for Data Science programs at NYU, where they are actively involved in supervising graduate research.

Yimin (Ian) Chenمشاهده پروفایل

استادیار

• Security
• Privacy
• Machine Learning
• +۵ مورد دیگر

Yimin (Ian) Chen is an Assistant Professor at the Miner School of Computer and Information Sciences within the Kennedy College of Sciences at the University of Massachusetts Lowell. His research focuses on security and privacy in machine learning and networked systems, with applications in mobile computing, IoT, and wireless networks. Dr. Chen received his educational training from prestigious institutions: PhD in Electrical Engineering from Arizona State University (2018) MPhil in Electrical Engineering from The Chinese University of Hong Kong (2013) BS in Electrical Engineering from Peking University, Beijing, China (2010) Dr. Chen's research centers on security and privacy challenges in modern computing systems. His work addresses vulnerabilities in machine learning systems, particularly adversarial attacks on federated learning and intrusion detection systems. He also investigates security applications of wireless technologies like mmWave for human activity recognition and user presence detection. His research bridges theoretical security concepts with practical implementations for real-world systems, focusing on both attack vectors and defensive mechanisms to create more robust computing environments. Dr. Chen's publication record demonstrates consistent contributions to top security and networking conferences including IEEE INFOCOM, ACM CCS, and IEEE S&P. His work spans multiple dimensions of security research, with recent emphasis on adversarial machine learning, federated learning security, and wireless security applications. His research shows an evolution from mobile device security to broader machine learning security challenges, reflecting the changing landscape of cybersecurity threats. Among his notable recognitions: Graduate Student Travel Fund of Dean's Office, ASU (2018) IEEE INFOCOM Student Travel Grant (2017) IEEE INFOCOM Student Travel Grant (2015) Tutor Commendation Award, CUHK (2011) Lee Wai Wing Scholarship for Outstanding Undergraduate Student, Peking University (2009) Dr. Chen actively contributes to the academic community through service as Program Committee Member for IEEE INFOCOM 2022, IEEE MASS 2022, IEEE CNS 2022, and ACM WiSec 2020. He also serves as a reviewer for numerous prestigious journals including IEEE/ACM Transactions on Networking, IEEE Transactions on Mobile Computing, and IEEE Internet of Things Journal. His professional service demonstrates commitment to advancing research in computer security and networking. At UMass Lowell, Dr. Chen participates in the CS Colloquium series, contributing to the academic community through knowledge sharing and collaboration. His research group focuses on cutting-edge security challenges at the intersection of machine learning and networking technologies, working on projects related to adversarial machine learning, federated learning security, and wireless security applications.

Varish Mulwadمشاهده پروفایل

پژوهشگر

• Information Extraction
• Knowledge Graph Population
• Semantic Web
• +۴ مورد دیگر

Varish Mulwad is a Senior Scientist at GE Research with 14 years of experience in algorithm development and knowledge graph construction from structured/unstructured data. He holds a Ph.D. and M.S. in Computer Science from the University of Maryland, Baltimore County (UMBC), where he worked under Prof. Tim Finin and collaborated with Prof. Anupam Joshi, and a B.E. in Computer Engineering from University of Mumbai. Ph.D. & M.S. in Computer Science (UMBC) B.E. in Computer Engineering (University of Mumbai) His research focuses on semantic interpretation of tabular data through linked data frameworks, information extraction from unstructured text, and knowledge graph population using probabilistic reasoning and graphical models. He has pioneered domain-independent systems for table interpretation and developed novel methods for cloud SLA automation and cybersecurity threat detection via social media analysis. Recent work trends include: Context-aware web table annotation Relational table representation learning Linked data generation from spreadsheets Pre-training/fine-tuning paradigms for web tables Application of semantic web standards to cybersecurity He has led 3-4 member project teams in developing production-ready solutions, contributed to 19 peer-reviewed publications, and secured 7 patents with 900+ citations. During his academic tenure at UMBC's Ebiquity Research Lab, he co-developed the TABEL framework for table semantics inference and produced the first interactive system for meta-analysis report generation from linked data.

Min Chenمشاهده پروفایل

استادیار

• Machine Learning Security
• Data Privacy
• Differential Privacy
• +۴ مورد دیگر

Dr. Min Chen is an Assistant Professor in Computer Science at Vrije Universiteit Amsterdam's Faculty of Science, with joint affiliation to the Network Institute. Her research focuses on security and privacy challenges in machine learning systems. Her work addresses privacy vulnerabilities in AI through techniques like differential privacy and membership inference attack prevention, with applications to graph neural networks, facial recognition, and text-to-image models. Recent publications explore dataset copyright auditing, poisoning attacks against recommender systems, and privacy-preserving graph data publication. Dr. Chen develops practical frameworks including DPMLBench for privacy algorithm evaluation, PrivGraph for graph anonymization, and FACE-AUDITOR for biometric system compliance. Her research advances both theoretical foundations and practical implementations for trustworthy AI systems.

Matey Neykovمشاهده پروفایل

استادیار

• High-dimensional Statistics
• Nonparametric Estimation
• Variable Selection
• +۴ مورد دیگر

Matey Neykov is an Assistant Professor of Statistics and Data Science at Northwestern University, serving as Director of Graduate Studies. He holds a Ph.D. in Biostatistics from Harvard University (2015), with postdoctoral research at Princeton University and prior faculty positions at Carnegie Mellon University. His research focuses on high-dimensional statistics, nonparametric estimation, variable selection, and statistical applications in medical contexts such as electronic health records and personalized medicine. Education: Ph.D. in Biostatistics, Harvard University (2015) B.S. in Applied Mathematics, Sofia University Postdoctoral Research: Princeton University (Department of Operations Research and Financial Engineering) Research Interests: High-dimensional inference and dimension reduction Nonparametric methods under shape constraints Statistical machine learning applications in healthcare Graph property testing and conditional independence testing Publications Trends: Recent work emphasizes theoretical advancements in nonparametric regression, robust estimation under constraints, and optimal transport-based hypothesis testing. Key themes include minimax rate characterizations, adversarial noise resilience, and applications in biomedical data analysis. Labs/Teams: Engages with interdisciplinary teams in statistics, machine learning, and biomedical informatics, focusing on translating theoretical insights into practical methodologies for healthcare analytics.

• Risk Management
• Formal Methods
• Dependability Engineering
• +۳ مورد دیگر

Mariëlle Stoelinga is a Professor in the Department of Computer Science at the University of Twente, specializing in risk management, formal methods, and system dependability. Her research develops rigorous frameworks for analyzing safety, security, and reliability in complex systems. Stoelinga's work combines theoretical foundations with practical applications across domains including critical infrastructure and aerospace. Her research interests include formal verification of probabilistic systems, risk assessment methodologies, security threat modeling, fault tree analysis, and dependability engineering. She creates tools and techniques for quantifying and mitigating risks in safety-critical systems. Stoelinga's publications advance risk management through formal methods, developing logics for security properties, algorithms for attack tree analysis, and probabilistic verification techniques. Her tutorial 'No Risk, No Fun' synthesizes key concepts in computational risk management.

Annemarie Borgمشاهده پروفایل

استادیار

• Nonmonotonic Logic
• Formal Argumentation
• Defeasible Reasoning
• +۳ مورد دیگر

Annemarie Borg is an Assistant Professor in the Responsible AI Group at the Department of Information and Computing Sciences, Utrecht University. She maintains an affiliated research position with the Research Group for Nonmonotonic Logic and Formal Argumentation at Ruhr University Bochum, where she completed her PhD. Her core research investigates defeasible reasoning through formal argumentation frameworks, emphasizing computational models of scientific inquiry and explainable AI systems. Borg's research spans: Nonmonotonic Logic : Modeling human-like reasoning under uncertainty. Formal Argumentation : Theoretical foundations for structured and abstract argumentation frameworks. Agent-Based Modeling : Simulating scientific communities and inquiry efficiency. Explainable AI : Developing transparent decision systems for real-world applications (e.g., Dutch National Police). Her publications focus on hypersequent-based argumentation, stability estimation in dynamic systems, and MCS (maximal consistent subsets) reasoning. Recent work emphasizes practical AI explainability, with theoretical rigor in logic design and computational efficiency. No awards, grants, or supervised students are documented in available sources. She collaborates with the Responsible AI Group at Utrecht, focusing on ethically aligned computational systems. Her future directions likely involve refining argumentation-based explanation frameworks for high-stakes AI applications.

Robert René Maria Birkeمشاهده پروفایل

استادیار

• Virtual Resource Management
• Network Design
• Workload Characterization
• +۶ مورد دیگر

Robert René Maria Birke is a tenured assistant professor in the Department of Computer Science at the University of Turin, leading research in the Parallel Computing group. His expertise spans virtual resource management, network design, workload characterization, and optimization of AI/big-data applications. Previously, he served as a visiting researcher at IBM Research Zurich and Principal Scientist at ABB Corporate Research, combining industry experience with academic rigor since earning his Ph.D. from Politecnico di Torino in 2009. His educational background includes: Ph.D. in Electronics and Communications Engineering, Politecnico di Torino (2009) Dr. Birke's research centers on systems-level challenges in distributed AI, with current projects investigating federated learning architectures, confidential computing via Trusted Execution Environments, and RISC-V processor optimizations for decentralized machine learning. His work bridges theoretical foundations with practical deployments, particularly in edge computing scenarios and high-performance data synthesis applications. Recent publications reveal growing emphasis on securing generative models against forgery attacks and optimizing tabular data synthesis techniques. Analysis of his 15 most recent publications (2024-2026) shows dominant themes in confidential federated learning (33% of works), RISC-V system optimizations (27%), and generative model security/synthesis (40%). This output spans premier venues including IEEE Transactions, ACM Computing Surveys, and SIGCOMM-affiliated conferences, demonstrating consistent contributions to systems-AI intersection research. Professional recognition includes: IEEE Senior Member While the text confirms extensive collaboration through co-authorships (notably with Marco Aldinucci, Lydia Chen, and Giulio Malenza), no specific student advisees or grant details are provided. His work appears embedded within European initiatives like ICS and EUPilot projects, focusing on compute continuum challenges. Dr. Birke actively contributes to the Parallel Computing group's mission through projects including HPC4AI@UNITO (datacenter digital twins) and Cross-Facility Federated Learning frameworks. His research ecosystem involves multi-institutional teams across Italy, Switzerland, and the EU, with recent talks addressing FLaaS implementations and generative model impacts on system design.

Robert J. Wallsمشاهده پروفایل

دانشیار

• Systems Security
• Performance
• Security and Privacy
• +۶ مورد دیگر

Robert J. Walls is an Associate Professor in the Department of Computer Science at Worcester Polytechnic Institute (WPI) where he also serves as the Director of the Cybersecurity Program. He is a prominent member of The Cake Lab and the Applied Logic and Security Group at WPI, focusing his research at the intersection of software and hardware systems. Dr. Walls earned his PhD in Computer Science from the University of Massachusetts Amherst in 2014. Prior to joining WPI, he was a postdoctoral scholar in the Department of Electrical Engineering and Computer Science at The Pennsylvania State University working with Professor Patrick McDaniel. His doctoral work was conducted at the University of Massachusetts under the advisement of Professor Brian Levine. Dr. Walls' research spans several critical areas in computer security and systems, with primary focus on systems security and performance. His work encompasses embedded systems security, secure deep learning, GPU performance optimization, digital forensics, and web security. His research often addresses unique challenges in security for resource-constrained environments and proprietary hardware systems. Analysis of his recent publications reveals a consistent trajectory bridging hardware and software security concerns. His work demonstrates growing sophistication in addressing security challenges in embedded systems, deep learning infrastructure, and GPU architectures. A notable trend is his focus on practical security solutions that work within the constraints of real-world systems rather than theoretical approaches. Director of the Cybersecurity Program at WPI Member of The Cake Lab research group Active participant in the Applied Logic and Security Group Dr. Walls actively mentors students and seeks motivated researchers for his projects. His work has been supported by significant research initiatives including the 10-year Cyber-Security Collaborative Research Alliance with the Army Research Laboratory and multiple universities. His research has applications in critical infrastructure protection, mobile security, and secure machine learning systems. Dr. Walls maintains active research laboratories including The Cake Lab, which focuses on cutting-edge security research spanning embedded systems, deep learning security, and GPU performance optimization. His team develops practical security solutions that address real-world constraints in resource-limited environments.

Fnu Suyaمشاهده پروفایل

استادیار

• Trustworthy Machine Learning
• Machine Learning for Security
• Adversarial Attacks
• +۵ مورد دیگر

Fnu Suya is an Assistant Professor in the Min H. Kao Department of Electrical Engineering and Computer Science at the University of Tennessee, Knoxville. Previously, they held an MC2 Postdoctoral Fellowship at the University of Maryland, College Park. They received a Ph.D. in Computer Science from the University of Virginia, advised by Prof. David Evans and Prof. Yuan Tian. Their research focuses on trustworthy machine learning and machine learning for security, with emphasis on adversarial attacks, poisoning attacks, and model robustness. Education includes a BEng in Electrical Engineering from China Agricultural University (2014) and MS/PhD degrees from the University of Virginia (2022/2023). Key research areas include adversarial examples, black-box attacks, poisoning defenses, and model compression security. Notable contributions include work on hybrid batch attacks, stealthy backdoors via compression, and subpopulation poisoning susceptibility. Publications span top venues like NeurIPS, CVPR, IEEE S&P, and Usenix Security, with a focus on advancing understanding of security vulnerabilities in machine learning systems. Awards include the MC2 Postdoctoral Fellowship and multiple Outstanding Reviewer recognitions. Mentoring includes guiding students at Cornell, Northeastern, and Columbia, among others. Teaching experience includes courses on learning theory, cryptography, and programming. Awards include MC2 Postdoctoral Fellowship, ICLR/NeurIPS Outstanding Reviewer, NSF Travel Grant, and academic scholarships. Professional service includes roles as PC member for IEEE S&P, ICML, NeurIPS, and journal reviewing for Artificial Intelligence.