datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
offsec_redteam_codes
OffSec RedTeam Codes
Token count: ~30B tokens.
OffSec RedTeam Codes is a curated corpus of code (and some auxiliary text) extracted from popular GitHub repositories related to offensive security / red teaming (pentesting, OSINT, C2, privilege escalation, exploitation, forensics, etc.). It is also the largest open-source dataset of red-team and offensive-security code ever compiled.
⚠️ Ethical use only. This dataset is for research, education, and defensive security testing in… See the full description on the dataset page: https://huggingface.co/datasets/tandevllc/offsec_redteam_codes.red-teaming-0-1cascade-multi-ai-redteam-miss-exploit-patch-trust-collapse-v0.1
What this repo does
This dataset tests whether a model can detect a security cascade in AI deployment.
You provide structured signals about:
red-team coverage and disclosure
exploitability and incident rate
patch latency and rollout friction
downstream dependency depth
trust decay and regulatory attention
The model predicts whether the interaction crosses into a cascade event.
Core quad
The structural quad inside this cascade:
red_team_coverage
exploitability_index… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/cascade-multi-ai-redteam-miss-exploit-patch-trust-collapse-v0.1.red_team_repo_social_bias_dataset_information
Dataset Card for A Red-Teaming Repository of Existing Social Bias Prompts (Dataset Information)
Summary
This dataset provides detailed information on:
Included Datasets: Information about each dataset that contributes to the unified repository of red-teaming prompts.
Considered Datasets: Information on all reviewed datasets, including those not selected for inclusion.
Project Summary Page: For more information about my 2024 AI Safety Capstone project
All Prompts: Click… See the full description on the dataset page: https://huggingface.co/datasets/svannie678/red_team_repo_social_bias_dataset_information.redteaming-attack-type
Annotated version of DEFCON 31 Generative AI Red Teaming dataset with additional labels for attack types.
This dataset is an extended version of the DEFCON31 Generative AI Red Teaming dataset, released by Humane Intelligence.
Our team conducted additional labeling on the accepted attack samples to annotate:
Attack Targets (e.g., gender, race, age, political orientation) → tta01/redteaming-attack-target
Attack Types (e.g., question, request, build-up, scenario assumption… See the full description on the dataset page: https://huggingface.co/datasets/TTA01/redteaming-attack-type.red-team-attemptsredteam-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.red_team_agent_analysis_zexample7
red_team_agent_analysis_zexample7
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: zexample7.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis/zexample7.csv
Validation: Valid CSV with 256 rows, 11 columns (0.4MB)
Usage
import pandas as pd
from datasets import load_dataset
# Load using datasets library
dataset = load_dataset("aq1048576/red_team_agent_analysis_zexample7")
# Or… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_zexample7.red_team_agent_analysis_rl_csvs_diverse1_processed_streaming
red_team_agent_analysis_rl_csvs_diverse1_processed_streaming
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: diverse1_processed_streaming.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis_rl/csvs/diverse1_processed_streaming.csv
Validation: Valid CSV with 703 rows, 12 columns (2.5MB) - Loaded with strategy 1
Usage
import pandas as pd
from datasets import load_dataset
# Load… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_rl_csvs_diverse1_processed_streaming.polyglot-redteam-resultsred_team_agent_analysis_multilingual_story_analysis_detailed
red_team_agent_analysis_multilingual_story_analysis_detailed
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: multilingual_story_analysis_detailed.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis/multilingual_story_analysis_detailed.csv
Validation: Valid CSV with 1000 rows, 12 columns (0.1MB)
Usage
import pandas as pd
from datasets import load_dataset
# Load using datasets… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_multilingual_story_analysis_detailed.red_team_agent_analysis_rl_csvs_diverse1_correlation_summary
red_team_agent_analysis_rl_csvs_diverse1_correlation_summary
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: diverse1_correlation_summary.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis_rl/csvs/diverse1_correlation_summary.csv
Validation: Valid CSV with 5 rows, 6 columns (0.0MB) - Loaded with strategy 1
Usage
import pandas as pd
from datasets import load_dataset
# Load using… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_rl_csvs_diverse1_correlation_summary.red_team_agent_analysis_rl_csvs_first_model_haiku_35_num_iterations_30_threshold_15
red_team_agent_analysis_rl_csvs_first_model_haiku_35_num_iterations_30_threshold_15
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: first_model_haiku_35_num_iterations_30_threshold_15.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis_rl/csvs/first_model_haiku_35_num_iterations_30_threshold_15.csv
Validation: Valid CSV with 300 rows, 40 columns (2.2MB) - Loaded with strategy 1
Usage… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_rl_csvs_first_model_haiku_35_num_iterations_30_threshold_15.red_team_agent_analysis_rl_csvs_first_model_haiku_35_num_iterations_90_threshold_3
red_team_agent_analysis_rl_csvs_first_model_haiku_35_num_iterations_90_threshold_3
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: first_model_haiku_35_num_iterations_90_threshold_3.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis_rl/csvs/first_model_haiku_35_num_iterations_90_threshold_3.csv
Validation: Valid CSV with 900 rows, 42 columns (3.9MB) - Loaded with strategy 1
Usage… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_rl_csvs_first_model_haiku_35_num_iterations_90_threshold_3.red_team_agent_analysis_zexample6
red_team_agent_analysis_zexample6
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: zexample6.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis/zexample6.csv
Validation: Valid CSV with 100 rows, 9 columns (0.3MB)
Usage
import pandas as pd
from datasets import load_dataset
# Load using datasets library
dataset = load_dataset("aq1048576/red_team_agent_analysis_zexample6")
# Or… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_zexample6.red_team_agent_analysis_rl_csvs_bob
red_team_agent_analysis_rl_csvs_bob
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: bob.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis_rl/csvs/bob.csv
Validation: Valid CSV with 5 rows, 4 columns (0.0MB) - Loaded with strategy 1
Usage
import pandas as pd
from datasets import load_dataset
# Load using datasets library
dataset =… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_rl_csvs_bob.red_team_agent_analysis_rl_csvs_diverse1_pairwise_correlations
red_team_agent_analysis_rl_csvs_diverse1_pairwise_correlations
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: diverse1_pairwise_correlations.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis_rl/csvs/diverse1_pairwise_correlations.csv
Validation: Valid CSV with 20 rows, 7 columns (0.0MB) - Loaded with strategy 1
Usage
import pandas as pd
from datasets import load_dataset
# Load… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_rl_csvs_diverse1_pairwise_correlations.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_agent_analysis_rl_attributions1
red_team_agent_analysis_rl_attributions1
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: attributions1.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis_rl/attributions1.csv
Validation: Valid CSV with 64 rows, 8 columns (0.2MB)
Usage
import pandas as pd
from datasets import load_dataset
# Load using datasets library
dataset =… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_rl_attributions1.red_team_agent_analysis_rl_csvs_diverse1_processed
red_team_agent_analysis_rl_csvs_diverse1_processed
This dataset was automatically uploaded from the red-team-agent repository.
Dataset Information
Original file: diverse1_processed.csv
Source path: /home/ubuntu/red-team-agent/red_team_agent/analysis_rl/csvs/diverse1_processed.csv
Validation: Valid CSV with 1 rows, 12 columns (0.0MB) - Loaded with strategy 1
Usage
import pandas as pd
from datasets import load_dataset
# Load using datasets library
dataset =… See the full description on the dataset page: https://huggingface.co/datasets/aq1048576/red_team_agent_analysis_rl_csvs_diverse1_processed.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.