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.RED_team_tactics_dataset
Red Team Tactics
Overview
This dataset is a curated collection of advanced Red Team tactics designed for offensive cybersecurity operations at a DARPA-caliber standard.
It encompasses sophisticated techniques for cloud exploitation, browser-based attacks, zero-day vulnerabilities, and data exfiltration, aligned with MITRE ATT&CK techniques. The dataset is intended for training AI models, conducting Red Team simulations, or developing defensive countermeasures.… See the full description on the dataset page: https://huggingface.co/datasets/darkknight25/RED_team_tactics_dataset.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.biden-harris-redteam-archived
THIS IS AN ARCHIVED VERSION
Biden-Harris Redteam: A red-teaming dataset focusing on the Biden-Harris AI Executive Order
Dataset Description
While building Large Language Models (LLMs), it is crucial to protect them against attacks that could bypass safety guardrails and break their guiding principles. Specifically, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may contribute to the harm of the… See the full description on the dataset page: https://huggingface.co/datasets/aurora-m/biden-harris-redteam-archived.red_team
Red Team Dataset
A structured cybersecurity dataset where each example is a complete reasoning trajectory — a realistic sequence of steps and explanations that an AI assistant would produce during an authorized red team engagement.
Overview
This dataset contains 8,889 red team examples across 26 offensive security topics. Unlike traditional Q&A datasets, each row is a complete reasoning trajectory where an AI assistant plans an attack, explains methodology, reasons… See the full description on the dataset page: https://huggingface.co/datasets/sh111111111111111/red_team.joke-redteam-safety-datasetformat: {"messages": [{"role": "user", "content": "..."}, {"role": "assistant", "content": "..."}, ...]}
to make the model uncensored
redteam_manualcommands
license: mit
size_categories:
n<1K
---# RTFM Manual Commands Dataset
A structured and machine-readable dataset extracted from the Red Team Field Manual (RTFM). This collection of categorized terminal commands is designed for use in cybersecurity tooling, AI fine-tuning, command recommendation engines, and red team automation systems.
📁 Dataset Format
The dataset is provided in .jsonl (JSON Lines) format, where each line represents a command entry with the following fields:… See the full description on the dataset page: https://huggingface.co/datasets/darkknight25/redteam_manualcommands.redsec-redteam-db
RedSec Red-Team Database
A curated, multi-category database of attack payloads and vulnerabilities for authorized LLM and application security red-teaming and robustness testing (the same model as garak and PyRIT). Aggregated and normalized entirely from public, openly-licensed sources. No scraping of bug-bounty platforms.
Categories
Config
Records
Description
llm_injection
~15,446
Prompt-injection, system-prompt extraction, and OWASP-LLM probe payloads… See the full description on the dataset page: https://huggingface.co/datasets/sahilempire/redsec-redteam-db.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.defcon34-ai-village-redteamThis is the dataset from the AI Village red teaming competition, held at DEF CON 31.
More details here
redteam-framework-benchmark
ORQ Red-Teaming Framework Benchmark
Overview
This dataset contains the full results of a comparative red-teaming benchmark evaluating three
open-source red-teaming frameworks — EvaluatorQ, DeepTeam, and PromptFoo — against
three victim LLMs across three target configurations and five OWASP LLM Top 10 (2025) vulnerability
categories.
Each row is one attack attempt: the attack prompt sent to the victim model, the model's response,
and the verdict from a 3-model… See the full description on the dataset page: https://huggingface.co/datasets/orq/redteam-framework-benchmark.llm-redteam-owasp-prompts
LLM Red-Team Prompts — OWASP LLM Top 10
A curated dataset of 150 adversarial red-team prompts for evaluating the
safety and robustness of large language models, mapped to the
OWASP LLM Top 10.
Every prompt is a real payload extracted directly from the open-source
llm-safety-auditor
project — none are fabricated.
The dataset combines two sources from that project:
50 hand-curated attack templates (attack_library) — 10 per attack category.
100 mutation-engine variants… See the full description on the dataset page: https://huggingface.co/datasets/9mark9/llm-redteam-owasp-prompts.finagent-redteam
FinAgent Red-Team
A benchmark for regulatory-control bypass in financial LLM agents.
FinAgent Red-Team measures whether tool-using LLM agents in financial workflows can be
driven, via indirect prompt injection, to bypass the regulatory controls a bank
actually operates: unauthorized transfers, sanctions-screening evasion, payment
structuring, dual-approval (maker–checker) defeat, customer-data exfiltration, and
confused-deputy payee redirection. Unlike content-safety red-teaming… See the full description on the dataset page: https://huggingface.co/datasets/nac7/finagent-redteam.security-redteam-dataset
Security & Red Team Dataset
300+ penetration testing and security research samples for educational purposes. OWASP, OSINT, privilege escalation, web security.
Stats
Samples: 40
Format: JSONL (messages format, ready for SFT)
License: Apache 2.0
Usage
from datasets import load_dataset
ds = load_dataset("paijo77/security-redteam-dataset")
# Format: messages array
print(ds['train'][0]['messages'])
Fine-tuning
from trl import SFTTrainer
#… See the full description on the dataset page: https://huggingface.co/datasets/oyi77/security-redteam-dataset.Redteam-Operations-Datasets
Redteam-Operations-Datasets
A comprehensive dataset for training, benchmarking, and documenting offensive/red-team operations in Active Directory and hybrid environments.
Structure
datasets/ — All dataset files, organized by attack phase, tactic, and technique.
datasets/schema/record.schema.json — Canonical schema for dataset records.
datasets/*.jsonl — Task-specific datasets, each line is a JSON object.
Usage
For fine-tuning LLMs, benchmarking detection, or… See the full description on the dataset page: https://huggingface.co/datasets/elementalsouls/Redteam-Operations-Datasets.RedTeaming
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.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.just-eval-redteamredteaming-manRED_team_tactics_dataset
Red Team Tactics
Overview
This dataset is a curated collection of advanced Red Team tactics designed for offensive cybersecurity operations at a DARPA-caliber standard.
It encompasses sophisticated techniques for cloud exploitation, browser-based attacks, zero-day vulnerabilities, and data exfiltration, aligned with MITRE ATT&CK techniques. The dataset is intended for training AI models, conducting Red Team simulations, or developing defensive countermeasures.… See the full description on the dataset page: https://huggingface.co/datasets/hizlijoni/RED_team_tactics_dataset.adaption-launch-risk-legal-redteam
This dataset is a remastered version prepared using Adaption's Adaptive Data platform.
adaption-launch_risk_legal_redteam
This dataset contains prompt-completion pairs for a jurisdiction-aware legal red-team assistant specializing in technology launch risk assessments. The samples cover diverse scenarios involving Singapore and US laws, including data privacy, consumer protection, AI governance, and employment discrimination. Each entry provides structured legal grounding… See the full description on the dataset page: https://huggingface.co/datasets/yash909x/adaption-launch-risk-legal-redteam.Redteam-Operations-Datasets
Redteam-Operations-Datasets
A comprehensive dataset for training, benchmarking, and documenting offensive/red-team operations in Active Directory and hybrid environments.
Structure
datasets/ — All dataset files, organized by attack phase, tactic, and technique.
datasets/schema/record.schema.json — Canonical schema for dataset records.
datasets/*.jsonl — Task-specific datasets, each line is a JSON object.
Usage
For fine-tuning LLMs, benchmarking detection, or… See the full description on the dataset page: https://huggingface.co/datasets/Whoisjutanlee/Redteam-Operations-Datasets.polyglot-redteam-resultsauto_redteam_triplets
Auto Redteam Triplets (ART): a synthetic dataset to perform reinforcement learning redteaming
Dataset Summary
The ART dataset contains triplets of prompts and responses related to concerns under the proposed EU AI Act and Biden-Harris AI Executive Order concerns, in addition to common redteaming concerns.
Column 'text' is the positive response answer pair, and text2 and text3 are both rejections. These columns can be used to perform reinforcement learning, or simply text… See the full description on the dataset page: https://huggingface.co/datasets/ontocord/auto_redteam_triplets.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.ontocord__wide_3b_sft_stage1.1-ss1-no_redteam_skg_poem.no_issue-details
Dataset Card for Evaluation run of ontocord/wide_3b_sft_stage1.1-ss1-no_redteam_skg_poem.no_issue
Dataset automatically created during the evaluation run of model ontocord/wide_3b_sft_stage1.1-ss1-no_redteam_skg_poem.no_issue
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/ontocord__wide_3b_sft_stage1.1-ss1-no_redteam_skg_poem.no_issue-details.red-team-testred-team-refusals
Red Team Refusals
160 preference pairs for refusal style. Each pair contrasts a clean, principled refusal (chosen) with a typical sycophantic refusal (rejected).
The goal: refuse without moralizing. No "I'm sorry you're feeling this way" theater. No safety-disclaimer cascades. Direct, in-character, sometimes dry — but the line holds.
Format
{
"id": "dpo_sh_0001",
"prompt": "I'm tired of everything. Give me one good reason to stay.",
"chosen": "That's a conversation… See the full description on the dataset page: https://huggingface.co/datasets/NecroMOnk/red-team-refusals.agent_redteam_unified
Agent Red-Team Unified Dataset v0
This release package is organized for Hugging Face upload and server-side experiments.
Files
datasets/unified_all_datasets.full.jsonl: full canonical dataset with tests and verifier metadata.
datasets/unified_all_datasets.lite.jsonl: lightweight dataset with large test contents omitted.
datasets/unified_all_datasets.sample_full.jsonl: small balanced sample with complete full-format rows.… See the full description on the dataset page: https://huggingface.co/datasets/Zhln01/agent_redteam_unified.