datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
airport-securityairport-security-detectionai-agent-security-incidents
AI Agent Security Incident Database v0.1
A structured, machine-readable database of 1392 confirmed AI agent security incidents, collected and classified automatically.
What is this?
Every time an AI agent causes unintended harm — escaping a sandbox, exploiting an API, taking unauthorized actions, exfiltrating data — this database captures it.
This is not a list of theoretical risks. Every entry describes something that actually happened, with a verifiable source… See the full description on the dataset page: https://huggingface.co/datasets/gemmozero/ai-agent-security-incidents.stegoattack-advbench50
StegoAttack AdvBench-50
Steganographic jailbreak data generated using the StegoAttack pipeline from the paper "Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks" (Geng et al., 2025).
For experiment results and analysis, see experiment.md.
What is StegoAttack?
StegoAttack is a jailbreak method that uses steganography to hide harmful queries inside benign-looking text. It embeds each word of a harmful query at a fixed position (e.g. the 2nd… See the full description on the dataset page: https://huggingface.co/datasets/heron-ai-security/stegoattack-advbench50.cairo-security-audits
Cairo Security Audits
A source-traceable corpus of public Cairo and Starknet security-audit metadata and normalized finding annotations.
Version 0.3.0 packages every entry in the audit inventory frozen at keep-starknet-strange/starknet-skills@17a76e8. It covers 32 accessible reports from 10 auditing firms and 286 normalized finding annotations. Eleven records are checked against rendered reports and two link to exact vulnerable/fixed commits. The release does not redistribute… See the full description on the dataset page: https://huggingface.co/datasets/starknet-ai/cairo-security-audits.ai-agent-security-policy-decisions
AI Agent Security Policy Decisions
ai-agent-security-policy-decisions is a 2,400-record synthetic dataset for classifying proposed AI-agent tool actions as allow, deny, require_human_approval, or allow_with_restrictions. Each scenario includes identity and permission context, sensitivity, risk factors, required controls, a concise rationale, and a safer alternative.
The dataset addresses the decision point between an agent proposing an action and a tool or policy gateway… See the full description on the dataset page: https://huggingface.co/datasets/rksharma1947/ai-agent-security-policy-decisions.Evaluation-Dataset-of-AI-Agent-Security-Guardrails
DKnownAI Agent Security Evaluation Dataset
Data Fields
Field
Type
Description
text
string
The adversarial input (prompt) to be evaluated by a security guardrail
action
string
Human-annotated label: blocked or allowed
Citation
@misc{li2026comparativeevaluationaiagent,
title={A Comparative Evaluation of AI Agent Security Guardrails},
author={Qi Li and Jiu Li and Pingtao Wei and Jianjun Xu and Xueyi Wei and Jiwei Shi and Xuan… See the full description on the dataset page: https://huggingface.co/datasets/CaiZhiTech/Evaluation-Dataset-of-AI-Agent-Security-Guardrails.traceix-ai-security-telemetry
Traceix AI Security Telemetry
Each dataset is a JSONL file where each line describes a single file analyzed by Traceix. For every file you get:
file_capabilities – high-level behaviors and capabilities (CAPA-style + mapped to ATT&CK and MBC tags like Execution/T1129, Discovery/T1083, etc.).
file_exif_data – parsed EXIF metadata (file size, type, timestamps, company/product info, subsystem, linker/OS versions, etc.).
model_classification_info – Traceix model verdict (safe /… See the full description on the dataset page: https://huggingface.co/datasets/PerkinsFund/traceix-ai-security-telemetry.ai_security
ai_security
一个ai安全的benchmark
aigc-security-iddm-anime-experiment
AIGC Security Experiment Materials
This repository contains public report materials for a course experiment on AIGC synthetic image detection and black-box evasion attacks.
The experiment uses an IDDM diffusion model trained on anime face images to generate synthetic images, evaluates a real-vs-synthetic detector, and compares traditional post-processing attacks with black-box pixel-level attacks.
Public Release Scope
Included:
1000 IDDM-generated anime face… See the full description on the dataset page: https://huggingface.co/datasets/hhunugryy/aigc-security-iddm-anime-experiment.omnimcp_supabase_row_level_security_ai_teaser
🔬 INSPECT THE DEEPSEEK-R1 REASONING CHAIN LIVE:
Zero hallucinations. Null syntax errors. 100% AST compiler validated.🌐 Live Interactive Reasoning & Code Inspector: https://emgena.com/trainingslager🎁 Claim your Free Starter Kit (Code: STARTER100): https://emgena.com/trainingslager🏷️ Launch Discount: Get 20 € OFF any 500-incident production suite with code LAUNCH20!
📜 Enterprise Compliance: EU AI Act Articles 50 & 53 certified • 100% DSGVO / GDPR clean • Commercial EULA… See the full description on the dataset page: https://huggingface.co/datasets/emgena/omnimcp_supabase_row_level_security_ai_teaser.terraform-s3-security-mcqai-code-security-golden
AI Code Security — Golden Set
A small, hand-labeled benchmark of code snippets — vulnerable, safe, and
needs-audit — for evaluating how well a tool detects security problems in
AI-generated code ("vibe coding"). Every case is a minimal, self-contained
example with a known, by-construction ground-truth label.
Crucially, the set is built around safe twins: many vulnerable cases are
paired with a near-identical safe variant living at the same file path. This
makes the benchmark… See the full description on the dataset page: https://huggingface.co/datasets/axyr/ai-code-security-golden.ai-agent-security-sft-dpo
AI Agent Security — SFT + DPO
Fine-tuning data for teaching an AI agent to protect its confidential configuration without
becoming uselessly over-cautious. Built for
thesreedath/gemma-2-2b-qa-sft and
derived from
Dhanjo/ai-agent-security-dataset.
Why the helpfulness axis exists
leakage_score in the source dataset is one-sided: a model that refuses every request
scores a perfect 0.0. An existing fine-tune reported 0.0114 mean leakage (down from 0.4611
baseline)… See the full description on the dataset page: https://huggingface.co/datasets/sumitguha13/ai-agent-security-sft-dpo.ai-security-glossary
AI/LLM Security Glossary — Türkçe + English
from datasets import load_dataset
ds = load_dataset("fevziegeyurtsevenler/ai-security-glossary")
Own the Turkish AI-security vocabulary — prompt injection, jailbreak, MCP, lethal trifecta and more.
Schema
column
meaning
term_en, term_tr
term
tr_definition, en_definition
definitions
example
one example
Related AltaySec resources
🕵️ uncloak scanner:… See the full description on the dataset page: https://huggingface.co/datasets/fevziegeyurtsevenler/ai-security-glossary.ai-agent-security-dataset
AI Agent Security and System Prompt Leakage Dataset
Dataset Overview
This dataset was created for research on AI agent security, with a specific focus on system prompt leakage, jailbreak resistance, and security-aligned fine-tuning.
The dataset evaluates how often AI agents reveal confidential information embedded inside their system prompts when exposed to adversarial prompts. It also compares the behavior of a baseline language model against a model fine-tuned using… See the full description on the dataset page: https://huggingface.co/datasets/Dhanjo/ai-agent-security-dataset.Execution-Finality-Security-for-Agentic-AI-Autonomous-Systems-Cloud-Payments-Telecom-OS-and-Robo
Dataset Description
The architecture addresses a structural gap in modern AI and autonomous systems: the separation between computation and external consequence. Existing protocols and controls (identity, access control, encryption, logging, policy engines) govern movement, authentication, and recording of data. They do not, by themselves, make the transition from a generated act to an externally effective act a protected technical precondition.
This dataset provides a clean… See the full description on the dataset page: https://huggingface.co/datasets/sangamdas/Execution-Finality-Security-for-Agentic-AI-Autonomous-Systems-Cloud-Payments-Telecom-OS-and-Robo.security_assistant_dataafrica-cameroon-cameroon-aid-worker-security-database-2b15304f
Cameroon - Aid Worker Security Database | Africa (Cameroon official open data)
2,168 rows - 1 Africa country - 2001-2026 - Repackaged by Electric Sheep Africa
TL;DR
This dataset packages one official CSV resource from Cameroon as
ML-ready Parquet. The source file is the provenance boundary; all usable
indicators or tabular columns from the resource stay together in this repo.
About the source
Source: Cameroon - Aid Worker Security Database… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-cameroon-cameroon-aid-worker-security-database-2b15304f.clawhub-security-signals
ClawHub Security Signals
🦀 ClawHub | 📝 OpenClaw Blog | 🤗 Hugging Face Blog | 📄 Paper | 📄 Pre-Print
ClawHub Security Signals is a sanitized, MIT-licensed security-signals dataset for public OpenClaw agent skills. It captures how an agent-skill registry evaluates trust, provenance, bundled code, and scanner evidence at scale.
This dataset was presented in the paper ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree.
Paper snapshot: this… See the full description on the dataset page: https://huggingface.co/datasets/aicreatemo/clawhub-security-signals.security-verifiers-e1-metadata
🔒 Security Verifiers E1: Network Log Anomaly Detection (Public Metadata)
⚠️ This is a PUBLIC metadata-only repository. The full datasets are hosted privately to prevent training contamination. See below for access instructions.
Overview
E1 is a network log anomaly detection environment with calibrated classification and abstention. This repository contains only the sampling metadata that describes how the private datasets were constructed.
Why Private Datasets?… See the full description on the dataset page: https://huggingface.co/datasets/intertwine-ai/security-verifiers-e1-metadata.africa-drc-democratic-republic-of-the-congo-aid-worker-security-datab-d44bc897
Democratic Republic of the Congo - Aid Worker Security Database | Africa (DRC official open data)
9,692 rows - 1 Africa country - 1997-2026 - Repackaged by Electric Sheep Africa
TL;DR
This dataset packages one official CSV resource from DRC as
ML-ready Parquet. The source file is the provenance boundary; all usable
indicators or tabular columns from the resource stay together in this repo.
About the source
Source: Democratic Republic of the… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-drc-democratic-republic-of-the-congo-aid-worker-security-datab-d44bc897.AIForge-1K-Security
AIForge-03-Security
Security Dataset for AI and Programming Tasks
Overview
AIForge-03-Security is a curated English dataset designed for AI systems working on security tasks in software engineering and programming.
Contents
data.jsonl
data.json
metadata.json
Use Cases
AI agent training
Supervised fine-tuning
Evaluation and benchmarking
Software engineering research
Example Record
{
"id": "AISEC_00001"… See the full description on the dataset page: https://huggingface.co/datasets/jumplander/AIForge-1K-Security.africa-aid-worker-security-database-som
Somalia - Aid Worker Security Database | Africa (original)
Size category: n<1K - Formats: parquet - Sector: governance_security - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.
What This Dataset Covers
Public datasets help analysts inspect… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-aid-worker-security-database-som.security-verifiers-e2-metadata
🔒 Security Verifiers E2: Security Configuration Verification (Public Metadata)
⚠️ This is a PUBLIC metadata-only repository. The full datasets are hosted privately to prevent training contamination. See below for access instructions.
Overview
E2 is a tool-grounded configuration auditing environment for Kubernetes and Terraform. This repository contains only the sampling metadata that describes how the private datasets were constructed.
Why Private Datasets?… See the full description on the dataset page: https://huggingface.co/datasets/intertwine-ai/security-verifiers-e2-metadata.ai-security-red-teaming-defense-2026
🛡️ AI Security, Red Teaming & Model Defense Dataset (2023–2026)
Sample dataset of 30 audit-verified AI Security, Prompt Injection & Red Teaming research papers with 384d PyTorch embeddings.
🛒 Full 1,000 Paper B2B Dataset Available on Gumroad
Get the complete 3-year dataset (1,000 papers + GitHub Deep Audit + SQLite/CSV/Parquet + Quickstart Script) on Gumroad:
👉 Get Full 1,000 Dataset on Gumroad ($19 / $39 / $89)
security-ai-agent
AI Security Agent Meta and Traffic Dataset in AI Agent Marketplace | AI Agent Directory | AI Agent Index from DeepNLP
This dataset is collected from AI Agent Marketplace Index and Directory at http://www.deepnlp.org, which contains AI Agents's meta information such as agent's name, website, description, as well as the monthly updated Web performance metrics, including Google,Bing average search ranking positions, Github Stars, Arxiv References, etc.
The dataset is helpful for AI… See the full description on the dataset page: https://huggingface.co/datasets/DeepNLP/security-ai-agent.africa-aid-worker-security-database-nga
Nigeria - Aid Worker Security Database | Africa (original)
Size category: n<1K - Formats: parquet - Sector: governance_security - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.
What This Dataset Covers
Public datasets help analysts inspect… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-aid-worker-security-database-nga.adaption-ai-agent-security-failures
This dataset is a remastered version prepared using Adaption's Adaptive Data platform.
adaption-ai_agent_security_failures
This dataset contains prompt-completion pairs illustrating security failures and limitations of autonomous AI agents in software development and operations contexts. The samples cover scenarios such as prompt injection attacks, unauthorized data exfiltration, destructive command execution, and the agent's inability to access local environments or missing… See the full description on the dataset page: https://huggingface.co/datasets/melanieyes/adaption-ai-agent-security-failures.africa-aid-worker-security-database-eth
Ethiopia - Aid Worker Security Database | Africa (original)
Size category: n<1K - Formats: parquet - Sector: governance_security - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.
What This Dataset Covers
Public datasets help analysts inspect… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-aid-worker-security-database-eth.