Search papers, labs, and topics across Lattice.
This paper benchmarks DKnownAI Guard against AWS Bedrock Guardrails, Azure Content Safety, and Lakera Guard in detecting AI agent security risks, including threats to the agent and requests for harmful content. DKnownAI Guard achieves the highest recall (96.5%) and true negative rate (90.4%) compared to the other guardrails. This superior performance suggests DKnownAI Guard offers enhanced protection against a range of security vulnerabilities in AI agent deployments.
DKnownAI Guard blows away AWS, Azure, and Lakera in head-to-head security tests for AI agents.
This report presents a comparative evaluation of DKnownAI Guard in AI agent security scenarios, benchmarked against three competing products: AWS Bedrock Guardrails, Azure Content Safety, and Lakera Guard. Using human annotation as the ground truth, we assess each guardrail's ability to detect two categories of risks: threats to the agent itself (e.g., instruction override, indirect injection, tool abuse) and requests intended to elicit harmful content (e.g., hate speech, pornography, violence). Evaluation results demonstrate that DKnownAI Guard achieves the highest recall rate at 96.5\% and ranks first in true negative rate (TNR) at 90.4\%, delivering the best overall performance among all evaluated guardrails.
