PromptShield reports a 65.3% true positive rate at 0.1% false positive rate for prompt injection detection, more than six times the best prior model, on its own out-of-distribution evaluation split.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PromptShield: Deployable Detection for Prompt Injection Attacks
PromptShield reports a 65.3% true positive rate at 0.1% false positive rate for prompt injection detection, more than six times the best prior model, on its own out-of-distribution evaluation split.