A dataset of deliberately crafted adversarial prompt injection strings designed to test and evaluate the robustness of Large Language Model (LLM) guardrails. It includes various attack categories, from role-play and obfuscation to data exfiltration and refusal overrides, providing diverse test cases for security and safety engineers.
simali dud
Posted on Originally published at asset-bot-edge.simalidudu.workers.dev
Top comments (0)