Project Grant DESC0025068

This $255,391 National Science Foundation Technology, Innovation, and Partnerships grant funds Anomalee Inc. to develop a commercially viable prototype for certifying deep neural networks against backdoor attacks. Backdoor attacks maliciously poison AI models to misclassify inputs containing hidden trigger patterns. Anomalee's unsupervised method will mathematically evaluate DNNs for such vulnerabilities without examples of poisoned models or access to training data, addressing a critical need...

This three-year, $500,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program will fund research at the University of California, Davis to develop trustworthy machine learning systems through adversarial robust reinforcement learning. Specifically, the award supports investigating potential vulnerabilities in reinforcement learning models and algorithms, developing robust RL approaches that mitigate impacts from adversarial attacks, and...

This federal Project Grant award of $398,249.00, provided by the U.S. Army Research, Development and Engineering Command (RDECOM) under the Basic Scientific Research program (CFDA 12.431), supports fundamental research at the University of Texas at Dallas (UTD) to develop robust artificial intelligence (AI) systems. The research aims to improve the resilience and security of AI models against potential adversarial attacks, particularly for applications related to national defense. Key focus...

This Project Grant from the National Science Foundation Office of Integrative Activities, under the Integrative Activities federal grant program (CFDA 47.083), provides $400,000 to North Carolina Agricultural and Technical State University from September 1, 2022 to August 31, 2025. The funding supports research to develop an early warning framework for cyber threats targeting operational technology systems. The framework introduces intelligent interaction decoys that mimic the behavior of...

This $200,000 Project Grant award from the National Science Foundation's (NSF) Mathematical and Physical Sciences (CFDA 47.049) program will enable Carnegie Mellon University (CMU) to develop advanced spatiotemporal foundation models and generative AI capabilities for large-scale multimodal threat detection. The project aims to create new data representations and neural network architectures to scale up existing spatial detection algorithms, enabling the rapid deployment of analytical...

This Project Grant award of $246,516 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program supports research to enhance the security and robustness of machine learning (ML) systems in multi-tenant cloud FPGA (field programmable gate array) environments. The project aims to: (1) understand the vulnerabilities of ML cloud-FPGA systems and explore defensive approaches; (2) advance the security of ML cloud systems against hardware-based model...

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 two-year, $500,000 project grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop foundational theory and optimal methods for robust statistical inference in the presence of adversarial data falsification. The grantee, Oregon State University, will investigate the fundamental limits of performing hypothesis testing and estimation when an adversary can manipulate input data. They will also develop robust inference methods...

This four-year $300,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop secure foundations for federated learning. Federated learning enables machine learning models to be collaboratively trained using data from many client devices without sharing private information. The researchers will investigate security vulnerabilities in federated learning's training phase, such as poisoning and backdoor attacks. They will...

This Project Grant from the National Science Foundation's Division of Computer and Network Systems provides $1,009,600 to Arizona State University for research titled "Collaborative Research: SATC: Core: Medium: Foundations of Trust-Centered Multi-Agent Distributed Coordination." The funding period is from June 15, 2022 through May 31, 2026. The award supports the development of theoretical foundations for trust-centered resilience in distributed coordination and optimization of...