Thai Duong Huynh
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
From Guidelines to Practice: Defining Requirements for AI Red-Teaming Tools
According to the abstract, Gia Phong Tran, Thai Duong Huynh, Randolph Loh and six co-authors analyze industry standards and guidelines to derive requirements for AI security testing tools, then discuss desirable features across existing red-teaming tools, beyond attack performance alone.