جست‌وجوی استاد و پژوهشگر

Rajeev Alurمشاهده پروفایل

استاد

• Formal Methods
• Cyber-Physical Systems
• Programming Languages
• +۷ مورد دیگر

Overview Rajeev Alur is the Zisman Family Professor and Director of the ASSET Center for Trustworthy AI at the University of Pennsylvania . His career spans groundbreaking work in formal methods, cyber-physical systems, and programming languages. PhD from Stanford University (1991) Bachelor's degree from IIT Kanpur (1987) Research Interests His research focuses on ensuring safety and trustworthiness in AI systems, particularly autonomous systems like self-driving cars and medical devices. Key areas include: Neurosymbolic integration Temporal logic in reinforcement learning Verification of neural network controllers Trustworthy machine learning Extending formal methods to modern AI Recent Publications Rajeev's recent work (2023-2025) emphasizes compositional verification, neurosymbolic learning, and secure microservice architectures. Notable trends include: Combining formal specifications with deep learning Scalable verification techniques for neural networks Relational query synthesis Application to autonomous systems with neural perception Chordal sparsity models for efficient analysis Scientific Recognition Alonzo Church Award (2016) Knuth Prize (2024) EATCS Award (2025) ACM/IEEE Fellow Advising & Grants He has advised 30+ PhD students now in academia (Georgia Tech, UCSD, etc.) and industry. As lead PI of the NSF Expeditions project ExCAPE , he drove program synthesis research. Currently serves as General Chair for FLoC 2026 . Labs & Teams Directs the ASSET Center and collaborates with Penn's PRECISE Center and PL Club . His work integrates with industry verification tools at Amazon, Microsoft, and Google.

• Software Engineering
• Cybersecurity
• Static Analysis
• +۶ مورد دیگر

Rahul Gopinath is a Lecturer in the School of Computer Science at the University of Sydney. His research focuses on the intersection of Software Engineering and Cybersecurity, particularly in static and dynamic program analysis to enhance software reliability, security, and maintainability. Prior to his current role, he was a postdoctoral researcher at CISPA Helmholtz Center for Information Security in Germany and earned his Ph.D. in 2017 from Oregon State University, USA. He is a co-author of the influential textbook *Fuzzing Book*, which serves as a foundational resource for students entering the field of fuzzing. His research interests span static and dynamic analysis techniques, specification mining, fuzzing, parsing, grammar inference, mutation analysis, and automatic program repair. Rahul Gopinath’s recent work includes developing FormatFuzzer for binary file format testing, advancing input grammar mining techniques, and exploring capability-based access control systems. He actively contributes to international conferences such as ICSE, ISSTA, and FSE, and his publications address challenges in mutation analysis, test adequacy, and empirical software engineering. Current research supervision includes a project titled *Evaluating Fast Virtual Machine Implementation Techniques for Fuzzing* with student Jack LUO. His work has been recognized through collaborations and presentations at leading institutions, reflecting his commitment to advancing automated software testing and security practices.

Andreas Zellerمشاهده پروفایل

استاد

• Software Testing
• Automated Debugging
• Fuzzing
• +۵ مورد دیگر

Andreas Zeller is a Professor at Saarland University and leads the Software Analysis and Testing Group at CISPA Helmholtz Center for Information Security. His research focuses on automated software testing, debugging, and security, with a strong emphasis on fuzzing techniques. He holds an ERC Advanced Grant for his 'Semantics of Software Systems' (S3) project, which explores massive test generation and oracle mechanisms. Zeller is renowned for his open-access books The Fuzzing Book and The Debugging Book , which provide interactive tools for learning and applying testing and debugging methods. His work includes developing the Fandango fuzzer, which combines grammars, constraints, and evolutionary algorithms for effective test generation. Zeller advises a group of over ten PhD students and collaborates internationally on cutting-edge research. In 2025, he received the ACM SIGSOFT Influential Educator Award for contributions to automated software engineering education. His research also extends to start-ups like InputLab GmbH, focused on synthesizing test data for enterprise applications. Recent projects include GDBMiner for input grammar extraction and Information Flow Fuzzing for detecting security leaks. Zeller actively participates in conferences like ICSE, FSE, and AST, delivering keynotes and organizing sessions on the future of software engineering.

Hoa Nguyenمشاهده پروفایل

استادیار

• Poetry
• Creative Writing
• Diasporic and Immigrant Subjectivity
• +۴ مورد دیگر

Hoa Nguyen is an Assistant Professor in the Department of English at Toronto Metropolitan University. She holds a BA from the University of Maryland, College Park, and an MFA from New College of California, San Francisco. Her research focuses on poetry, creative writing, diasporic and immigrant subjectivity, Asian American poetry, and contemporary poetics. Nguyen is a prominent figure in diasporic literary communities, co-founding the She Who Has No Masters collective, a transnational network of Vietnamese and Southeast Asian womxn and non-binary writers. Her award-winning publications include *A Thousand Times You Lose Your Treasure* (2021), which earned a National Book Award nomination and the Canada Book Award, and *Violet Energy Ingots* (2016), shortlisted for the Griffin Prize. She has been recognized with prestigious accolades such as the Neustadt Prize nomination (2019), often compared to the Nobel Prize in Literature. Education: BA, University of Maryland, College Park MFA, New College of California, San Francisco Awards: 2021 Canada Book Award 2017 Griffin Poetry Prize Nominee 2019 Neustadt Prize Nominee Community Engagement: Founder of She Who Has No Masters Mentorship Program Member of Vietnamese/Southeast Asian diasporic collective focusing on artistic collaboration and community repair

Yutian Tangمشاهده پروفایل

استادیار

• AI+SE (Large-language Model+SE)
• Program Analysis
• Empirical Software Engineering
• +۴ مورد دیگر

Dr. Yutian Tang is an Assistant Professor at the University of Glasgow's School of Computing Science. He holds a Ph.D. from The Hong Kong Polytechnic University and a B.Sc. from Jilin University. His research focuses on AI-driven software engineering, program analysis, and mobile app security, with over 40 publications in top venues like ESEC/FSE and IEEE TSE. He has received awards including the ISSRE'18 Best Industry Paper and Shanghai Pujiang Talent Program. Current research emphasizes automated testing, bug localization, and LLM applications in software engineering. Education: Ph.D., Department of Computing, The Hong Kong Polytechnic University B.Sc., Computer Science, Jilin University Research Interests: His work spans AI+SE (Large Language Models in Software Engineering), automated testing, privacy protection, and malware detection. Notable contributions include XDebloat (app debloating) and tools for analyzing Android vulnerabilities. He actively explores LLM applications for code generation and test suite optimization. Grants & Funding: EPSRC Peer Review College member National Natural Science Foundation of China (NSFC) grant (2023-2025) OpenAI API Researcher Access Program (2024) Google Cloud Research Credits (2024) Service & Leadership: Editorial Board Member of Frontiers in Computer Science , PC member of ICSE, ESEC/FSE, ASE, and other top conferences. Active in reviewing for IEEE Transactions and ACM journals. Future Directions: Tool support for automated bug detection, LLM integration in software lifecycle, and large-scale binary code analysis.

• Software Engineering
• Machine Learning Systems Engineering
• Software Design Patterns
• +۱۴ مورد دیگر

Hironori Washizaki is a Professor in the Department of Computer Science and Engineering at Waseda University, Japan. He is a leading researcher in software engineering with a focus on software design patterns, machine learning systems, cybersecurity, and software quality. His primary research interests include: Software Engineering Machine Learning Systems Engineering Software Design Patterns AI and ML Security Requirements Engineering for AI Systems Natural Language Processing for Software Engineering Software Quality and Reliability Empirical Software Engineering His recent publications (2023–2025) reveal a strong trend toward integrating AI and machine learning into software engineering practices. Key themes include prompt engineering patterns in software development, automated log anomaly detection, vulnerability analysis using NLP techniques, modeling frameworks for ML systems, and gender studies in software engineering. His work combines theoretical modeling with empirical validation and practical application. Notable scientific contributions and activities include: Guest editorial for IEEE Transactions on Emerging Topics in Computing on software aging and rejuvenation Organizing and contributing to workshops on SQuaRE, gender in software engineering, and ML systems engineering Leadership roles in IEEE Computer Society Extensive collaboration with researchers at Waseda and internationally He advises students and leads research on topics such as automated program repair, data-driven personas, bug fixing time analysis, and educational tools for programming. His work often involves interdisciplinary collaboration across software engineering, AI, and cybersecurity domains. He is involved in several research labs and teams focused on software engineering innovation, including groups working on: Software patterns and architecture AI/ML engineering Security and privacy in cloud and IoT Empirical studies in software development Educational technology and programming pedagogy

• Computer Science
• Cybersecurity
• Internet of Things
• +۵ مورد دیگر

Gang Tan is an Associate Professor at the Pennsylvania State University's College of Engineering, Department of Computer Science and Engineering. He also holds the James F. Will Career Development Professorship and is affiliated with the Institute for Computational and Data Sciences (ICDS). His research focuses on binary reverse engineering , cybersecurity , Internet of Things (IoT) security , machine learning fairness , and information flow security . He has led numerous NSF-funded projects, including work on precise binary analysis, IoT policy enforcement, and automated fairness repair in AI systems. Recent work trends include memory safety validation , pseudocode extraction , and control-flow integrity mechanisms. His 127+ research outputs reflect deep engagement with static program analysis , cache side-channel detection , and secure kernel-driver interfaces . Scientific Awards: James F. Will Career Development Professorship Gang Tan has secured multiple grants from the National Science Foundation (NSF) and U.S. Navy for projects like Sliver (information flow verification) and Semantics-Directed Binary Reverse Engineering . His work involves advising teams on IoT safety, and he has 19 active or completed grants since 2008.

Benjamin Delawareمشاهده پروفایل

استادیار

• Programming Languages
• Formal Methods
• Program Verification
• +۵ مورد دیگر

Benjamin Delaware is an Assistant Professor in the Department of Computer Science at Purdue University since 2016. He earned his Ph.D. in Computer Science from the University of Texas at Austin in 2013 under William Cook and Don Batory, following an M.Sc. in Computer Science from Washington University in St. Louis (2007) and a dual B.S. in Computer Science and B.A. in Russian from Truman State University (2005). Research focuses on program synthesis , formal verification , and relational program properties . Key contributions include KestRel (relational verification), PALM (LLM-assisted proof automation), and Clotho (distributed system testing). His publications span top venues like OOPSLA, PLDI, and POPL, with recent work (2025) on coverage-type-guided synthesis and LLM-integrated proof repair . He has received multiple scientific awards , including a SIGPLAN Distinguished Paper Award (2023) and CRII Award from NSF (2018). Ben advises a research group producing graduates such as Qianchuan Ye (now at SUNY Buffalo) and Kia Rahmani (UT Austin postdoc). He teaches graduate courses on program reasoning (CS560) and programming language design (CS456/CS565), with earlier teaching experience at UT Austin. Active in academic service , he served as Program Committee Co-Chair for RocqPL 2026 and CoqPL 2025 , and as Diversity, Equity, and Inclusion Chair at POPL 2023. His grants include NSF funding for input generator verification (2023-2026) and Cisco research on privacy-preserving computation (2022-2023).

Lise Eliotمشاهده پروفایل

استاد

• Brain development
• Gender differences
• Neuroplasticity
• +۴ مورد دیگر

Lise Eliot is a Professor of Neuroscience at Rosalind Franklin University, specifically within the Chicago Medical School and School of Graduate and Postdoctoral Studies. She is affiliated with the Foundational Sciences and Humanities department and conducts research at the Stanson Toshok Center for Brain Function and Repair. Her academic journey includes an A.B. degree magna cum laude in History & Science from Harvard University, a PhD in Cellular Physiology & Biophysics from Columbia University, and post-doctoral training in the Division of Neuroscience at Baylor College of Medicine. Dr. Eliot's research focuses on brain and gender development, with particular emphasis on neuroplasticity and how it shapes neural circuitry and behavior. She investigates the complex interplay between innate biology, sociocultural factors, and individual experience in molding our brains across the lifespan. Her work challenges simplistic notions of binary brain differences between sexes, demonstrating through rigorous meta-analyses that structural differences are minimal beyond overall brain size. She has been particularly influential in showing how small initial differences can be amplified through social and environmental factors, a theme explored in her widely-read book "Pink Brain, Blue Brain." Her research program has produced a substantial body of scholarly work, with numerous publications in high-impact journals through 2025. Analysis of her recent publications reveals a consistent focus on challenging binary categorizations in neuroscience, examining the methodological considerations in studying sex and gender differences, and exploring the implications of neuroplasticity for understanding human behavior. Her work spans multiple disciplines including neuroscience, psychology, gender studies, and education policy. Director, MD with Distinction in Research Program Institutional Review Board (alternate member) Women in Science and Healthcare (WiSH) Symposium Committee Co-Chair Conflict of Interest Committee member Healthcare Disparities and Equity in Medical Education Task Force member CMS Faculty Nominations and Awards Council member Dr. Eliot teaches several graduate and medical courses including Neurobehavioral Health (MCMS605), Ethics and Regulatory Issues in Biomedical Research (GIGP508), and Human Brain Dissection (GNSC505). Her teaching reflects her research interests, emphasizing critical analysis of neuroscience claims, particularly regarding gender differences. Through both her scholarly work and public engagement, she advocates for evidence-based approaches to understanding brain development and gender, challenging popular misconceptions about "hardwired" differences between male and female brains.

Işıl Dilligمشاهده پروفایل

دانشیار

• Program analysis
• Program synthesis
• Program verification
• +۴ مورد دیگر

Işıl Dillig is an Associate Professor of Computer Science at the University of Texas at Austin, where she leads the UToPiA research group. Her academic career spans over a decade of significant contributions to programming languages research, particularly in program analysis, verification, and synthesis. Dr. Dillig received all her academic degrees (BS, MS, and PhD) from Stanford University before joining the faculty at UT Austin. Her educational background established the foundation for her innovative research approach that bridges theoretical computer science with practical applications. Her research focuses on developing techniques to make software systems more reliable, secure, and easier to build through advanced program analysis, verification, and synthesis methods. She has pioneered approaches that combine symbolic reasoning with machine learning to tackle complex software engineering challenges across multiple domains including security, databases, and programming language theory. Her work demonstrates exceptional depth in creating practical tools that address real-world software development problems while maintaining strong theoretical foundations. Analysis of Dr. Dillig's publication record reveals a consistent trajectory of innovation in program synthesis, with recent work expanding into neurosymbolic approaches that bridge neural networks with formal methods. Her research shows strong connections between theoretical foundations and practical applications, particularly in security-critical systems, database technologies, and blockchain applications. The evolution of her work demonstrates increasing sophistication in handling complex program structures while maintaining practical usability. Dr. Dillig has received prestigious recognition for her research contributions: Sloan Fellowship NSF CAREER award As a dedicated educator and research leader, Dr. Dillig has served in significant roles including Program Chair for PLDI 2022 and Steering Committee member for PLDI. She has mentored numerous students through her UToPiA research group, guiding research in program synthesis, verification, and analysis. Her work has been supported by substantial research grants that have enabled innovative projects at the intersection of programming languages and security. Dr. Dillig leads the UToPiA (UT Austin Programming, Languages, and Analysis) research group, which focuses on developing novel techniques for program analysis, verification, and synthesis. The group maintains strong collaborations with industry partners and academic institutions worldwide, translating theoretical advances into practical tools that address real software engineering challenges.

Michael Pradelمشاهده پروفایل

استاد

• Software Engineering
• Program Analysis
• Bug Detection
• +۵ مورد دیگر

Michael Pradel is a full professor in the Computer Science Department at the University of Stuttgart and faculty member at CISPA Helmholtz Center for Information Security (effective September 2025), where he leads the Software Lab. He is also affiliated with the International Max Planck Research School for Intelligent Systems and the Stuttgart ELLIS Unit, reflecting his interdisciplinary research approach. His research interests focus on software engineering, particularly program analysis, bug detection, and the application of machine learning to developer tools. Pradel's recent work increasingly explores LLM-based approaches for program repair, code analysis, and automated software development, as evidenced by projects like RepairAgent and ExecutionAgent. Pradel's publication record shows a clear trend toward integrating AI techniques with traditional software engineering methods, with recent papers focusing on LLM applications for program repair, change validation, and quantum software analysis. His work bridges theoretical foundations with practical tool development, as seen in frameworks like DyLin for Python analysis and LintQ for quantum programs. Ernst-Denert Software Engineering Award Emmy Noether grant (1.3 million Euro) by the DFG ERC Starting Grant (1.5 million Euro) Multiple ACM SIGSOFT Distinguished Paper Awards ACM Distinguished Member recognition Pradel actively mentors PhD students, with recent graduates including Matteo (specializing in quantum software) and Luca (focusing on software evolution). His group has received significant funding and maintains strong industry connections, including past sabbaticals at Facebook. He serves in leadership roles for major conferences, including PC co-chair for FSE 2027, demonstrating his standing in the software engineering community. The Software Lab maintains active collaborations with institutions worldwide, including CMU, Google, KAIST, and several European universities.

Yang Liuمشاهده پروفایل

استاد

• Formal Methods
• Software Engineering
• Security
• +۷ مورد دیگر

Yang Liu is a Full Professor and University Leadership Forum Chair at the School of Computer Science and Engineering, Nanyang Technological University (NTU) in Singapore. He serves as Programme Director for HP-NTU Digital Manufacturing Corp Lab, Deputy Director of the National Satellite of Excellence of Singapore, and Cluster Director in Cybersecurity at Energy Research Institute @NTU. His research spans Cybersecurity , Software Engineering , and Artificial Intelligence . He leads research in malware modeling and detection, vulnerability analysis using machine learning and program analysis, formal verification of security systems, program specification learning, performance analysis, Android system security, and AI security, robustness, fairness, and explainability. His notable work includes the Process Analysis Toolkit (PAT) for model checking and the Deep-Series tools for deep learning testing. Professor Liu has published extensively in top-tier conferences including ASE, ICSE, FSE, ISSTA, and S&P. His research demonstrates strong trends toward integrating AI/ML techniques with traditional software engineering and security approaches, particularly focusing on large language models for code analysis, vulnerability detection, and program repair. Recent publications show a growing emphasis on blockchain security, smart contract analysis, and addressing security challenges in AI systems. NRF Investigatorship (Class 2020) ACM's Distinguished Speaker Nanyang Research Award (Young Investigator) Microsoft Asia Research Fellowship 20 Year ICFEM Most Influential System Award for PAT Multiple ACM SIGSOFT Distinguished Paper Awards Professor Liu actively advises students and has seen notable student achievements, including Singapore Data Science Consortium research award winners and AISG PhD Fellowship recipients. His research is supported by numerous grants including a $900,000 NTU-NAP grant for Formal Verification on Cloud and a $471,000 grant for Vulnerability Detection in Binary Code. He leads the HP-NTU Digital Manufacturing Corp Lab and contributes to RollsRoyce@NTU Corporate Lab research on complex business systems simulation.

Shing-Chi Cheungمشاهده پروفایل

استاد

• Software Engineering
• Program Analysis
• Software Testing
• +۷ مورد دیگر

Shing-Chi Cheung is a Professor of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST), School of Engineering. He founded the CASTLE research group and co-founded the International Workshop on Automation of Software Testing (AST) in 2006. His leadership includes serving as General Chair of FSE 2014 and chairing multiple APSEC conferences. His research focuses on software quality enhancement through program analysis, testing, debugging, and AI techniques, targeting Android apps, open-source software, deep learning systems, smart contracts, and spreadsheets. Current projects include metamorphic testing frameworks, binary analysis tools, and vulnerability detection systems for emerging technologies. His publication portfolio demonstrates consistent contributions to software engineering since 2016, with recent work emphasizing AI-integrated testing methodologies, smart contract security, and deep learning system reliability. Key trends show increasing focus on cross-language analysis, data visualization quality, and compiler-level verification for modern software stacks. Distinguished Member of the ACM Fellow of the British Computer Society Editorial board member: Science of Computer Programming (SCP), Journal of Computer Science and Technology (JCST) Former editorial board member: IEEE Transactions on Software Engineering (2006-2009), Information and Software Technology (2012-2015) Four patents in China and the United States Cheung actively mentors through the CASTLE research group and serves on program committees for major conferences including ICSE, ESEC/FSE, and ISSTA. His work bridges academic research with practical applications through industry collaborations and tool development. He has contributed to numerous workshops and symposia as steering committee member and program chair.

Shangwen Wangمشاهده پروفایل

استادیار

• Program repair
• Program comprehension
• Mining software repositories
• +۳ مورد دیگر

Shangwen Wang is an Assistant Professor in the School of Computer Science at National University of Defense Technology (NUDT) in Changsha, China. He earned his Bachelor's degree in June 2017, Master's degree in December 2019, and Ph.D. in December 2023, all from NUDT. During his graduate studies, he was supervised by Professor Xiaoguang Mao. From May 2022 to July 2023, he was a visiting student at Southern University of Science and Technology under Professor Yepang Liu. His educational background includes: Ph.D. in Software Engineering, NUDT (2020.3-2023.12), supervised by Prof. Xiaoguang Mao Visiting Scholar, SUSTech (2022.5-2023.7), supervised by Prof. Yepang Liu M.A. in Software Engineering, NUDT (2017.9-2019.12), supervised by Prof. Xiaoguang Mao B.A. in Software Engineering, NUDT (2013.9-2017.6) Wang's research focuses on program repair, program comprehension, mining software repositories, software maintenance and evolution, software testing, and AI for Software Engineering. His work bridges traditional software engineering techniques with modern AI approaches, particularly leveraging large language models for various software engineering tasks. He has made significant contributions to automated program repair, fault localization, vulnerability detection, and code generation. His research demonstrates a strong emphasis on empirical validation and practical applicability to real-world software development challenges. His recent publications show a clear trend toward integrating large language models with traditional software engineering tasks. The 15 most recent articles reveal a focus on applying LLMs to program repair, fault localization, vulnerability detection, and code generation, while maintaining strong empirical foundations. His work spans both theoretical advancements and practical tool development, with applications in software security, testing, and maintenance. His notable achievements include: CCF Outstanding Doctoral Dissertation (CCF优博) 2024 Outstanding Doctoral Graduates, NUDT, 2023 Multiple distinguished paper awards including ACM SIGSOFT Distinguished Paper Award (ISSTA'24) and IEEE TCSE Distinguished Paper Awards (ICSME'22, SANER'22) Prestigious scholarships from NUDT throughout his academic career As an active member of the software engineering community, Wang serves on numerous program committees for top conferences including ICSE, ASE, ESEC/FSE, and ISSTA. He has also contributed to teaching as a teaching assistant for courses such as Compiler, Python Programming, Discrete Mathematics, and C++ Programming. His research group appears to be actively mentoring students, as evidenced by his role as corresponding author on multiple student-led publications. Wang maintains an active research presence with collaborations across multiple institutions in China. His work demonstrates a clear trajectory from traditional program analysis techniques toward integrating cutting-edge AI approaches, particularly large language models, into software engineering practices.

Gary Tanمشاهده پروفایل

استاد

• computer security
• formal methods
• programming languages
• +۳ مورد دیگر

Gang (Gary) Tan is a Professor in the Computer Science and Engineering Department at Pennsylvania State University, co-directing the Institute for Networking and Security Research (INSR). His research bridges computer security, formal methods, and programming languages to develop practical solutions for software vulnerabilities and AI fairness. Education: B.E. in Computer Science from Tsinghua University Ph.D. in Computer Science from Princeton University Dr. Tan specializes in applying compiler techniques and formal verification to security challenges, with seminal work on cache side-channel attacks and fairness in machine learning. His Security of Software (SOS) Group develops frameworks that integrate theoretical guarantees into real-world systems, emphasizing measurable security outcomes and ethical AI. Recent projects focus on quantifying bias in neural networks and mitigating speculative execution vulnerabilities. Analysis of his 2021-2025 publications reveals a strategic pivot toward AI security, where he pioneers methods for fairness testing (e.g., information-theoretic debugging) and repair (e.g., NeuFair). Concurrently, his security work evolves from foundational side-channel research (SpecSafe, 2021) toward hardware-software co-design solutions, demonstrating consistent innovation across theoretical and applied domains. Scientific Awards: James F. Will Career Development Professorship NSF CAREER Award Google Research Award (two instances) Distinguished Reviewer Award at 2018 IEEE Symposium on Security and Privacy Outstanding Research Award at Penn State Ruth and Joel Spira Excellence in Teaching Award Best Paper Award at PLDI 2024 Dr. Tan leads the SOS Group with funding from NSF (including CAREER), DARPA (ISAT study group membership), and industry partners like Google. His grants support interdisciplinary projects spanning secure compilation, fairness engineering, and hardware security, while his teaching excellence award reflects commitment to pedagogy in core systems courses. He co-directs Penn State's Institute for Networking and Security Research (INSR), fostering collaboration between systems, security, and AI researchers. The SOS Group maintains active partnerships with industry security teams and contributes to open-source tools for vulnerability detection, with recent work expanding into fairness certification for machine learning pipelines.