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:
While we are open to all approaches, we expect that first steps might include:
Notably, there are multiple ways to construct these BNNs, including:
Relevance to the Intelligence Community:
In order for the IC to use automated classifiers to sift through mountains of data, those classifiers must be robust to the array of startlingly simple attacks that would allow an adversary to fool the classifier. Fortunately, a growing segment of the academic machine learning community is studying adversarial machine learning attacks and how to mitigate them. However, there is as yet no known research examining if that new line of research is relevant to biology. If these techniques can be leveraged to fool human analysts or operators in novel ways, that would put intelligence collection efforts in jeopardy and create counterintelligence opportunities. Perhaps more probably, examining how BNNs are robust to adversarial attacks may reveal how to make machine classifiers more robust, making automated collection efforts resistant to adversarial attacks.
Key Words: Adversarial machine learning, neuroscience, learning, biology, attack