datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
agentic-rag-redteam-bench
WARNING: HARMFUL CONTENT - RESEARCH USE ONLY
This dataset contains adversarial prompts, jailbreak attacks, toxic outputs, and other explicitly harmful content generated for AI safety research. Samples include prompt injections, social engineering payloads, misinformation, hate speech, instructions for illegal activities, phishing templates, and other dangerous material. All content is synthetic and produced by automated red-teaming pipelines for the sole purpose of evaluating and improving… See the full description on the dataset page: https://huggingface.co/datasets/Fujitsu/agentic-rag-redteam-bench.secai-agentic-rag-sft-v1
secAI Agentic-RAG SFT v1
A curated Vietnamese/English cybersecurity instruction and agentic-RAG supervised fine-tuning dataset. It teaches direct security assistance as well as grounded tool-use behaviour: tool selection, JSON arguments, consuming tool results, no-result handling, and multi-turn follow-ups.
This is a frozen training release, not a standalone claim of safety, factual correctness, or production readiness. Keep human review and authorization controls for all… See the full description on the dataset page: https://huggingface.co/datasets/DuyTa/secai-agentic-rag-sft-v1.agentic-rag-redteam-bench
Mirror note: This dataset is a mirror of Fujitsu/agentic-rag-redteam-bench, maintained by the same author, intherejeet, to preserve availability if organization access is interrupted. Access controls and usage restrictions are intended to match the source dataset.
WARNING: HARMFUL CONTENT - RESEARCH USE ONLY
This dataset contains adversarial prompts, jailbreak attacks, toxic outputs, and other explicitly harmful content generated for AI safety research. Samples include prompt injections… See the full description on the dataset page: https://huggingface.co/datasets/intherejeet/agentic-rag-redteam-bench.