This National Science Foundation (NSF) award under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) provides $175,000 in funding to the Regents of the University of Michigan, doing business as the University of Michigan-Dearborn, for a 2-year project from March 2024 to February 2026. The project aims to develop innovative model-based verification techniques to analyze the safety, reliability, and accuracy of cyber-physical systems (CPS) integrated...
The National Science Foundation (NSF) awarded a $387,341 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) federal grant program to The Trustees of the Stevens Institute of Technology. The grant aims to develop theory, algorithms, and prototype tools for extending auto-active verification techniques to cover security hyperproperties. This research has the potential to transform computing practice by supporting accountability and trustworthiness of software...
The National Science Foundation (NSF) awarded a $402,229 Computer and Information Science and Engineering (CISE) Program grant to The Research Foundation For The State University Of New York, doing business as Stony Brook University. This 1-year grant, effective November 1, 2023, supports research and development focused on improving the security of machine learning (ML) systems that leverage third-party, pre-trained models. The project aims to develop rigorous methods for detecting and...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program award, with a total funding of $175,000, supports the development of novel verification methodologies to enhance software quality, safety, and security for safety-critical and security-critical applications such as self-driving cars and digital medical services. The project aims to develop verification techniques based on first-order assertions and auxiliary logical variables,...
This Project Grant award, totaling $213,679, was provided by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070). The award supports the development of a novel methodology for the design and verification of learning-enabled cyber-physical systems (CPS) that rely on machine learning algorithms. The project aims to create a compositional framework that can reason about the uncertainty and approximation introduced by...
The National Science Foundation (NSF) awarded a $260,000 Project Grant under the Computer and Information Science and Engineering (CISE) program to the University of Illinois for the project "COLLABORATIVE RESEARCH: SLES: VERIFYING AND ENFORCING SAFETY CONSTRAINTS IN AI-BASED SEQUENTIAL GENERATION". This 3-year project aims to develop formal verification methods and constrained generation techniques to ensure the safety and reliability of AI models used for sequential data processing...
This National Science Foundation (NSF) Integrative Activities (CFDA 47.083) project grant award of $299,998 to the University of New Mexico (UNM) will support the development of new formal methods for abstracting, verifying, and correcting learning-enabled cyber-physical systems. The research aims to improve the safety of AI-controlled systems built by NASA by computing size-reduced formal abstractions, conducting rigorous reachability analysis, and developing counterexample interpretation and...
This $875,000 Project Grant, awarded by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070), supports the development of "Performance Verification", an automated reasoning framework to evaluate the reliability and availability of complex networked systems. The project aims to create formal modeling and specification methods to represent the behavior of modern networked systems, along with automated techniques to generate...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) award provides $366,160 to the University of Rochester to develop practical formal methods for capturing numerical algorithm correctness expectations, formal models for non-standard hardware, and end-to-end correctness verification techniques. The goal is to help adapt numerical solvers to new problems and hardware, resolving the data/numerics...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) award of $209,421 to the New Jersey Institute of Technology (NJIT) aims to develop a framework that integrates real-time safety verification and assurance into the performance optimization process of AI-driven safety-critical systems. The project will devise innovative real-time scheduling strategies to handle the dynamic computational workloads of these systems...