Create ULLafayette_Hei.yaml

Per https://support.opensciencegrid.org/a/tickets/75652

projects/ULLafayette_Hei.yaml

@@ -0,0 +1,10 @@
+Department: Center for Advanced Computer Studies
+Description: While fine-tuning large language models (LLMs) to follow instructions
+  has emerged as a pivotal paradigm, enabling promising applications such as ChatGPT
+  and GitHub Copilot, the capability to follow arbitrary instructions also introduces
+  acute vulnerabilities. This project aims to deepen understanding of the security
+  and privacy risks associated with large instruction-tuned language models and to
+  obtain insights on how to mitigate these risks.
+FieldOfScience: Computer and Information Science and Engineering
+Organization: University of Louisiana at Lafayette
+PIName: Xiali Hei