This interactive playground demonstrates the LLM Guard library by Protect AI. Users can test various scanners and validators on prompts and model outputs to detect and prevent common vulnerabilities such as prompt injection, PII leakage, and toxic content.
In the LLM eval & observability space, LLM Guard Playground takes a focused approach. It focuses on testing and validating defenses against prompt injection, toxicity, and other LLM security risks. It is built as a B2B product for AI developers and security researchers. LLM Guard Playground costs nothing to use. It ships for the web and the command line, and it can be self-hosted.
protectai builds and maintains LLM Guard Playground, and it first shipped in 2024. Among its 3 catalogued features are prompt scanning, response validation, and security testing.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do