Create and release your Profile on Zintellect – Postdoctoral applicants must create an account and complete a profile in the on-line application system. Please note: your resume/CV may not exceed 2 pages.
Complete your application – Enter the rest of the information required for the IC Postdoc Program Research Opportunity. The application itself contains detailed instructions for each one of these components: availability, citizenship, transcripts, dissertation abstract, publication and presentation plan, and information about your Research Advisor co-applicant.
Additional information about the IC Postdoctoral Research Fellowship Program is available on the program website located at: https://orise.orau.gov/icpostdoc/index.html.
If you have questions, send an email to ICPostdoc@orau.org. Please include the reference code for this opportunity in your email.
Research Topic Description, including Problem Statement:
With machine learning advances in hardware and software being powered by strong commercial interest and consumer awareness of data security/privacy it is becoming more practical to deploy trained models to the edge of a system on low power devices to filter information, make decisions and provide context to data before it is aggregated on back-end systems.
Neural networks are benefiting from advances in core principles, software libraries and optimized hardware to run them making an eco-system that is moving quickly but still relatively immature in terms of its success deploying solutions to “production”.
What threats and opportunities does using neural networks at the edge of a system present? i.e., how could somebody affect a system that has a neural network as a component, either to defeat, deceive or coerce the system?
Other thoughts for steer are:
Relevance to the Intelligence Community:
A concern of the Intelligence Community (IC) is in assuring the provenance of hardware for critical and secure applications. With a global supply chain for PCB manufacture, how can a populated PCB be quickly assured that it has been manufactured as designed without fake, rejected or additional components add, whether this has been done maliciously or not? Using a quick probe test on each PCB net and decomposing the resultant values back to the individual component values would allow assurance that the components are as expected, and the PCB has not been tampered with or has had extra components added to the PCB that may degrade performance in critical IC applications.
Key Words: Machine Learning, Modelling, Electronics, Hardware Assurance, Printed Circuit Board, Fault Finding