CAREER: AuthenTrack: Secure and Scalable Frameworks for Large-Scale Authentication and Tracking

Essential products, including microelectronics, pharmaceuticals, and food, are often sourced from distributed and sometimes untrusted suppliers. Without reliable traceability, counterfeit or unauthorized items can enter systems and threaten public health, economic stability, and national security. For example, counterfeit chips in defense systems pose national security risks, a concern reflected in the CHIPS and Science Act. Similarly, counterfeit or mislabeled drugs in pharmaceutical supply chains can endanger public health. In human surveillance, rapid and accurate tracking supports public safety and cross-border investigations, with relevance to agencies including the Department of Homeland Security (DHS) and the Federal Bureau of Investigation (FBI). Current tracking systems face significant limitations: authentication degrades under data variability, scalability is constrained by storage and query latency, and systems remain vulnerable to spoofing and cloning attacks. A key gap persists in scalable architectures capable of handling variable, hard-to-clone identifiers under real-world noise. To address this national need, this project investigates a foundational framework, named AuthenTrack, for object tracking in large-scale applications such as supply chains to strengthen authentication, scalability, and security across critical sectors. The project embeds hands-on modules into computing curricula and disseminates open-source tools, benchmarks, and datasets to broaden educational and societal impact nationwide. This project advances data structure design through a unified probabilistic framework integrating hierarchical indexing, adaptive hashing, and time-aware querying to enable secure identity resolution under uncertainty. This project develops domain-agnostic architecture, enhances model capabilities, and strengthens the security through adversarial modeling. In this project, the researchers validate prototypes in real-world supply chains. These efforts advance probabilistic data structures and resilient system design while enabling precise, scalable authentication. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria. NSF Award ID: 2544640 | Program: 01003031DB NSF RESEARCH & RELATED ACTIVIT,01002930DB NSF RESEARCH & RELATED ACTIVIT,01002627DB NSF RESEARCH & RELATED ACTIVIT | Principal Investigator: Sumaiya Shomaji | Institution: University of Kansas Center for Research Inc, LAWRENCE, KS | Award Amount: $404,138 View on NSF Award Search: https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2544640 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2544640.html