PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift
Prompt-injection detectors are typically evaluated using aggregate <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> on in-distribution test data, which offers limited insight into behavior under distribution shift, particularly on the benign side of the decision boundary, where false pos...
Yusuf Khalid Shire, Sang-Chul Kim
· IEEE Access · 0 citations