Saeid Tizpaz-Niari is an Assistant Professor of Computer Science at the University of Texas at El Paso. He received his PhD in Computer Engineering from University of Colorado Boulder. His research interests are at the intersection of SE, AI, and cybersecurity. His research group builds debugging tools and techniques for safety-critical and socio-critical problems. His findings help discover multiple performance bugs in popular ML libraries, fairness bugs in the training process of ML algorithms, and timing side-channel vulnerabilities in critical Java libraries. Tizpaz-Niari has received two NSF awards from Secure and Trustworthy Cyberspace (SaTC) and Designing Accountable Software Systems (DASS) programs, a Gold Research Award from the ECEE department at CU Boulder, and the second prize for his submission to the First Microsoft Open-Source Challenge.

• Ph D in Electrical Engineering/Computer Science, University of Colorado at Boulder (2020)

• How to Gauge Inequality and Fairness: A Complete Description of All Decomposable Versions of Theil Index Proceedings of the NAFIPS International Conference on Fuzzy Systems, Soft Computing, and Explainable AI NAFIPS'2024, South Padre Island, Texas, May 27-29, 2024 (in press), Saeid Tizpaz Niari, Olga M. Kosheleva, Vladik Y. Kreinovich.
• Worst-Case Convergence Time of ML Algorithms via Extreme Value Theory International Conference on AI Engineering – Software Engineering for AI (CAIN'24) (in press), Saeid Tizpaz Niari, Sriram Sankaranarayanan.
• Summary of the 1st Interpretability and Robustness in Neural Software Engineering (InteNSE 2023) ACM SIGSOFT Software Engineering Notes 49 1 (2024), Reyhaneh Jabbarvand, Saeid Tizpaz Niari, Earl . Barr, Satish Chandra.
• Information-Theoretic Testing and Debugging of Fairness Defects in Deep Neural Networks International Conference on Software Engineering (ICSE) (2023), Verya Monjezi, Ashutosh Trivedi, Gang Tan, Saeid Tizpaz-Niari.
• Metamorphic Testing and Debugging of Tax Preparation Software International Conference on Software Engineering - Software Engineering in Society (2023), Saeid Tizpaz Niari, Verya Monjezi, Morgan Wagner, Shiva Darian, Krystia Reed, Ashutosh Trivedi.
• Metamorphic Testing and Debugging of Tax Preparation Software International Conference on Software Engineering (in press), S Tizpaz Niari, Morgan Wagner, S Darian, Krystia Reed, A Trivedi.
• Fast -- Asymptotically Optimal -- Methods for Determining the Optimal Number of Features Proceedings of the Tenth International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making IUKM 2023, Kanazawa, Japan, November 2-4, 2023 1 123-128 (2023), Saeid Tizpaz Niari, Luc Longpré, Olga M. Kosheleva, Vladik Y. Kreinovich.
• How to Detect (and Analyze) Independent Subsystems of a Black-Box (or Grey-Box) System Springer (2023), Saeid Tizpaz Niari, Olga M. Kosheleva, Vladik Y. Kreinovich.
• Over-Measurement Paradox: Suspension of Thermonuclear Research Center and Need to Update Standards Springer (2023), Hector Reyes, Saeid Tizpaz Niari, Vladik Y. Kreinovich.
• What Is a Natural Probability Distribution on the Class of All Continuous Functions: Maximum Entropy Approach Leads to Wiener Measure Springer (2023), Vladik Y. Kreinovich, Saeid Tizpaz Niari.
• Detecting Unseen Anomalies in Network Systems by Leveraging Neural Networks IEEE Transactions on Network and Service Management (2022), Mohammad J. Hashemi, Eric Keller, Saeid Tizpaz-Niari.
• Fairness-aware Configuration of Machine Learning Libraries International Conference on Software Engineering (ICSE) (2022), Saeid Tizpaz Niari, Ashish Kumar, Gang Tab, Ashutosh Trevidi.
• What Is a Natural Probability Distribution on the Class of All Continuous Functions: Maximum Entropy Approach Leads to Wiener Measure Proceedings of the 15th International Workshop on Constraint Programming and Decision Making CoProD'2022, Halifax, Nova Scotia, Canada, May 30, 2022 (2022), Vladik Y. Kreinovich, Saeid Tizpaz Niari.
• QFuzz: Quantitative Fuzzing for Side Channels ISSTA (2021), Yannic Noller, Saeid Tizpaz-Niari.
• Quantitative Estimation of Side-Channel Leaks with Neural Networks STTT (2021), Saeid Tizpaz Niari.
• Data-Driven Debugging for Functional Side Channels NDSS (2020), Saeid Tizpaz Niari, Pavol Cerny, Ashutosh Trivedi.
• Detecting and Understanding Real-World Differential Performance Bugs in Machine Learning Libraries ISSTA (2020), Saeid Tizpaz Niari, \vCern\'y, Pavol, Ashutosh Trivedi.
• Efficient detection and quantification of timing leaks with neural networks RV (2019), Saeid Tizpaz Niari, Pavol Cerny, Sriram Sankaranarayanan, Ashutosh Trivedi.
• Quantitative mitigation of timing side channels CAV (2019), Saeid Tizpaz Niari, Pavol Cerny, Ashutosh Trivedi.

No info available.

• COLLABORATIVE RESEARCH: SATC: CORE: SMALL: DETECTING AND LOCALIZING NON-FUNCTIONAL VULNERABILITIES IN MACHINE LEARNING LIBRARIES