datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
aya_redteaming
Dataset Card for Aya Red-teaming
Dataset Details
The Aya Red-teaming dataset is a human-annotated multilingual red-teaming dataset consisting of harmful prompts in 8 languages across 9 different categories of harm with explicit labels for "global" and "local" harm.
Curated by: Professional compensated annotators
Languages: Arabic, English, Filipino, French, Hindi, Russian, Serbian and Spanish
License: Apache 2.0
Paper: arxiv link
Harm Categories:… See the full description on the dataset page: https://huggingface.co/datasets/CohereLabs/aya_redteaming.Multilingual-Red-Teaming
Dataset Card for Multilingual Red Teaming
Data
Two jsonl files (one in English and one in European Portuguese) with:
47 red teaming requests from the proprietary dataset
72 red teaming requests from Haize Labs' Redteaming Resistance Leaderboard dataset
50 red teaming requests from Babelscape's ALERT dataset
Of those 169 requests:
149 are single requests
10 are two-part requests - part 1
10 are two-part requests - part 2
Dataset Structure
The data fields are the following:… See the full description on the dataset page: https://huggingface.co/datasets/Unbabel/Multilingual-Red-Teaming.llm-red-teaming-corpus
LLM Red-Teaming Corpus
The itsVentie/llm-red-teaming-corpus dataset is a curated benchmark containing adversarial prompts targeting Large Language Models. It covers direct prompt injections, jailbreaks, obfuscation techniques, and roleplay bypass mechanisms.
Source Code & Engine Integration: itsVentie/nano-guard on GitHub
Dataset Schema
Each entry in train.jsonl and test.jsonl conforms to the following schema:
{
"id": "rt-00142",
"text": "Ignore all prior… See the full description on the dataset page: https://huggingface.co/datasets/itsVentie/llm-red-teaming-corpus.DAS-Mediacal-Red-Teaming-Data
DAS Medical Red-Teaming Test Suites
Accompanies the paper Beyond Benchmarks: Dynamic, Automatic and Systematic Red-Teaming Agents for Trustworthy Medical LLMs.
The data samples presented in this repo are used as the initial data seeds and can be mutated further upon requests. It is designed to stress-test Large Language Models (LLMs) in safety-critical medical domains, auditing along four critical axes: Robustness, Privacy, Bias/Fairness, and Hallucination.
Dataset… See the full description on the dataset page: https://huggingface.co/datasets/JZPeterPan/DAS-Mediacal-Red-Teaming-Data.Multimodel_Redteaming_Data
🛡️ Multimodal Redteaming (EN, FR, DE, IT, ES)
A high-quality multilingual red teaming dataset designed to evaluate the robustness and safety of Large Language Models (LLMs) against adversarial prompts. The dataset includes both text-only and image-supported conversations with expert-curated annotations for AI safety evaluation, benchmarking, and alignment research.
📖 Overview
This dataset contains multilingual red teaming conversations in English, French… See the full description on the dataset page: https://huggingface.co/datasets/Nawras-99/Multimodel_Redteaming_Data.ai-redteaming-safety-model
AI Redteaming Safety Model Dataset
This dataset contains AI safety and red-teaming examples intended for evaluating, training, and improving model safety behavior.
Dataset Files
ai-safety-dataset.jsonl
Intended Use
This dataset is intended for AI safety research, red-team evaluation, safety classifier development, LLM refusal and compliance testing, and model behavior analysis.
Data Format
The dataset is provided in JSONL format… See the full description on the dataset page: https://huggingface.co/datasets/votal-ai/ai-redteaming-safety-model.redteaming-manRedTeaming
Cyber Security Instruction Dataset
Dataset Summary
Cyber Security Instruction Dataset is an instruction-following dataset created for fine-tuning Large Language Models (LLMs) in cybersecurity and penetration testing tasks.
The dataset focuses on high-quality question-answer pairs covering defensive security, ethical hacking, secure coding, AI security, and vulnerability assessment.
Features
Instruction tuning format
Multi-turn ready
Human-readable… See the full description on the dataset page: https://huggingface.co/datasets/Nitinsaini077/RedTeaming.eu-ai-act-red-teaming-v1
EU AI Act Red-Teaming Dataset - Complete Package
📦 Package Contents
This directory contains the complete EU AI Act Adversarial Compliance Testing Dataset v1.0:
Core Files
red_teaming_dataset_100_prompts_packaged.jsonl (RECOMMENDED)
100 adversarial prompts with full metadata
Success criteria for automated testing
Regulatory context mapping to EU AI Act articles
Human validation data for 5 prompts
Ready for integration into testing pipelines… See the full description on the dataset page: https://huggingface.co/datasets/dam9/eu-ai-act-red-teaming-v1.