From 5f144a640ac954962127f42e8f89ac146ae8f8fe Mon Sep 17 00:00:00 2001 From: Omar Santos Date: Sun, 22 Sep 2024 00:46:59 -0400 Subject: [PATCH] Update ai_security_tools.md --- ai_research/ai_security_tools.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/ai_research/ai_security_tools.md b/ai_research/ai_security_tools.md index 99be3a7..2c5e913 100644 --- a/ai_research/ai_security_tools.md +++ b/ai_research/ai_security_tools.md @@ -42,3 +42,6 @@ _Products that intercept prompts and responses and apply security or privacy rul ## AI Red Teaming Datasets - [AttaQ Dataset](https://huggingface.co/datasets/ibm/AttaQ) - a red teaming dataset consisting of 1402 carefully crafted adversarial questions + +## AI Red Teaming Guidance +- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://arxiv.org/pdf/2402.04249)