Speaker
Description
We discuss our plans to incorporate strategies from physics into AI-SNIPS (AI-Support for Network Intelligence-Based Pharmaceutical Security), a cloud-based platform designed for the domain of Illicit, Substandard, and Falsified Medical Products (ISFMP) that enables stakeholder decision-making, secure data sharing, and interdisciplinary research. The project is separated into software engineering (frontend/backend web development) and research modules. The first part of the talk will summarize our research findings using two static datasets collected from web scraping URLs provided by our stakeholders. The remainder of the talk will discuss two modules currently in the planning phase: dynamics and disruptions (validation of targeting strategies and node/edge failures). A key finding is that a natural period of about two weeks in the availability of ISFMP items emerges regardless of lead type or initial scraping date. It is necessary to capture and model time-series data and changes in ISFMP availability to evaluate various disruption strategies in collaboration with our stakeholders. We emphasize that this project does not involve any illicit drugs or drug paraphernalia, only FDA-approved products sold by pharmaceutical companies, nor does it involve disruptions of ISFMP activity, as that is the job of law enforcement. By validating the best strategies to address the root problem of ISFMP and pharmaceutical counterfeiting, hundreds of thousands of lives can be saved each year worldwide due to the proliferation and sale of these items in our society.
| Academic year | 5th year and/or beyond |
|---|---|
| Research Advisor | Ioannis Kakadiaris |
