Cooperative Agreement 70NANB19H080

This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to improve the robustness of machine learning models used to detect malicious software or "malware". The $174,103 award to Northern Arizona University (NAU) will run from October 1, 2025 to September 30, 2027. The project seeks to: 1) understand the key features learned by different neural network architectures for detecting malware,...

This Project Grant from the National Science Foundation's Computer and Information Science and Engineering program, totaling $247,903, supports research from November 2021 through September 2024 to develop techniques for improving the adaptability of machine learning-based security defenses. The goal is to enable these defenses to better handle dynamic changes in data caused by evolving attacks and changes in benign system usage, with reduced need for costly manual data labeling. The awardee,...

This National Science Foundation (NSF) grant award under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $204,962 to Duke University to develop machine learning models that can reliably detect malware without running it. The key innovations of this 3-year project include new techniques to improve the resistance of malware detectors to evasion attempts, as well as more efficient model architectures. The project aims to open-source these advances where...

This $242,024 Project Grant awarded by the National Science Foundation (CFDA 47.070 - Computer and Information Science and Engineering) to Carnegie Mellon University (CMU) focuses on improving the reliability and efficiency of machine learning (ML) models for detecting malicious software (malware). The project aims to develop new techniques to make ML-based malware detectors more resistant to being fooled by attackers, as well as more time- and space-efficient. Key innovations include novel...

This $338,993 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program (CFDA 47.070) supports research at George Mason University to advance semantics-oriented binary code analysis. The University will develop novel deep learning-based approaches to analyze closed-source software at both the instruction and control flow graph levels, with the goal of achieving high accuracy and scalability in binary code understanding. Specifically, the...

This Project Grant award, provided by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070), supports the development of advanced computational methods for tracking and analyzing evolving patterns in large-scale networks. The $270,000 award will fund research to create scalable and accessible tools for dynamic network analysis, which can enable early detection of disease outbreaks, improved understanding of social dynamics, and...

This two-year, $600,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program aims to advance side-channel analysis and protection through deep learning techniques. Funded research at Northeastern University will develop novel methods for applying deep neural networks to both microarchitectural side-channel attacks and effective countermeasures. Key products include a persistent cache monitoring mechanism to improve observation of victim...

This three-year, $674,542 National Science Foundation project grant supports research at the University of California Santa Cruz to develop Bayesian statistical and machine learning methods for analyzing complex survey data from the federal statistical system. The grant falls under the NSF's Social, Behavioral, and Economic Sciences program (CFDA 47.075), which promotes basic research and education in these fields. Specifically, the investigators will extend existing models using data...

This $175,000 two-year project grant from the National Science Foundation's Computer and Information Science and Engineering program will fund research at Old Dominion University Research Foundation to advance secure deep learning systems. The awardee will systematically study existing neural network backdoor attacks to understand fundamental attack principles. Based on these findings, the research team will develop algorithms to accurately detect neural backdoors embedded in deep learning...

This Project Grant award from the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program will develop a comprehensive methodology for generating, deploying, and verifying software patches, particularly in scenarios where the original source code is unavailable. The $311,482 award to Purdue University aims to enhance the security and reliability of current and future software systems by: Developing differential binary analysis techniques...