DKnownAI Guard achieves 96.5% recall and 90.4% true negative rate, outperforming three competing guardrails in AI agent security evaluations.
LLM Jailbreak & Prompt-Injection Dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Comparative Evaluation of AI Agent Security Guardrails
DKnownAI Guard achieves 96.5% recall and 90.4% true negative rate, outperforming three competing guardrails in AI agent security evaluations.