ECE’s Fatima Anwar and Collaborators Obtain NSF Award to Support Reliable Testbed for Privacy Evaluations

Content

The National Science Foundation (NSF) has awarded Assistant Professor Fatima Anwar of the UMass Amherst Electrical and Computer Engineering (ECE) Department a three-year $366,669 grant to support her collaborative research on comprehensive testing tools which ensure that privacy-preserving artificial-intelligence systems work reliably.

This NSF project is a three-university collaboration, with Anwar acting as the principal investigator (PI) for the UMass Amherst portion, Muhammad Ali Gulzar serving as PI for the Virginia Polytechnic Institute and State University, and Ali Anwar functioning as the PI for the University of Minnesota-Twin Cities. Though Anwar’s lab at UMass Amherst will receive $366,669 from the NSF grant, the total amount of the award is $1.1 million for all three institutions. 

As Anwar explains, the new testbed “will serve the national interest by enabling secure collaboration on artificial-intelligence (AI) development while protecting individual privacy, supporting American competitiveness in artificial-intelligence technologies, and strengthening data security across critical infrastructure.” 

The background of this research, as the NSF proposal says, is that “Traditional machine learning often involves collecting data from multiple sources, which can raise significant privacy concerns. One approach has emerged as a promising solution to solve this challenge by enabling models to be trained across many different sources without directly sharing private data.” 

But therein lies a problem. “Despite these advancements,” as the proposal says, “existing systems for training models across multiple sources lack standardized assessment tools, posing challenges to research reproducibility, validation, and trust. Without proper testing tools, organizations cannot verify that their privacy protections work as intended, creating barriers to adoption in critical areas like healthcare, finance, and national security.” 

This NSF project addresses these challenges by developing wide-ranging testing tools which guarantee that AI systems work reliably to preserve privacy. 

According to the NSF proposal, “This project designs, develops, and sustains FLTest, an interdisciplinary testbed that automates privacy and robustness evaluations in federated learning systems, addressing gaps often overlooked by traditional tools.” 

The three-institution NSF project will also develop automated-test-orchestration frameworks, privacy-attack-simulation models, configuration-vulnerability-detection systems, and recommendation engines for optimization. 

“The testbed's key innovation streamlines evaluations through automated orchestration assisted by a pitfall checker that detects configuration issues and vulnerabilities in privacy evaluations,” says the NSF proposal. “FLTest empowers both novice and expert users with actionable insights tailored to real-world applications.” 

The NSF proposal concludes that the collaborative research team “will validate FLTest across multiple domains and datasets, develop standardized benchmarks for assessment, and create detailed reporting mechanisms for security analysis. By utilizing distinct datasets and offering a standardized solution, FLTest verifies model privacy and robustness across heterogeneous-data distributions, supporting the development of reliable privacy-preserving federated-learning systems.” 

This NSF project includes a relationship with three industry partners to assure the practical adoption and long-term sustainability of the research.

Anwar’s EMTECH Lab (Personal site) at UMass Amherst is dedicated to advancing embedded systems, AI at the edge, and resilient computing architectures. As she says, “Our lab designs networked embedded systems that safely interact with the physical world, often incorporating human-in-the-loop paradigms. We are committed to building open-source hardware and software artifacts that promote transparency and innovation.” (February 2026)