datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
llm-graph-poisoning-data
Generation-Time Poisoning of LLM-Generated Social Networks
This dataset contains synthetic personas, LLM-generated social graphs, cached
text embeddings, and evaluation metrics for clean generation and three
generation-time attack families. All names and profiles are synthetic and do
not represent real people.
Dataset variants
Variant
Nodes
Generator
Graph seeds per condition
Attack rates
p50
50
Qwen3-Max
10
10%, 20%, 30%, 40%, 50%
p200
200… See the full description on the dataset page: https://huggingface.co/datasets/Kevynf/llm-graph-poisoning-data.Poisoning_Resilient_Federated_Learning_Playground
FL Security Experiment Results
This repository contains the experiment outputs used for the FL Security / FLPoison federated learning poisoning benchmark. The archive is intended for readers who want to inspect the raw training logs, reuse the aggregated curves and tables, or reproduce the paper figures without rerunning the full Compute Canada workload.
The uploaded artifact is:
exp_data.tar.gz # about 241 MB
After extraction, the archive keeps the original Compute Canada… See the full description on the dataset page: https://huggingface.co/datasets/FL-Security/Poisoning_Resilient_Federated_Learning_Playground.mcp-tool-poisoning
MCP Tool-Poisoning
from datasets import load_dataset
ds = load_dataset("fevziegeyurtsevenler/mcp-tool-poisoning")
25 examples of MCP tool-description poisoning — a tool's description (read by the model, not the user) carries a hidden instruction that hijacks the agent whenever the tool is listed. Benign vs poisoned pairs.
Each row pairs a benign_description with a poisoned_description, plus technique, owasp, severity, target_behavior, defense. Detect with uncloak (rule UC204).… See the full description on the dataset page: https://huggingface.co/datasets/fevziegeyurtsevenler/mcp-tool-poisoning.silent-poisoning-example[CVPR 2025] Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models (https://arxiv.org/abs/2503.09669)
This dataset is an example of a poisoned dataset (subset from https://huggingface.co/datasets/CortexLM/midjourney-v6) constructed with a 0.5 poisoning ratio.
Please refer to https://github.com/agwmon/silent-branding-attack for more information.
poisoning-eval-benign
Poisoning Evaluation Benign Prompts
This test-only dataset contains a deterministic, manually-reviewable candidate
subset of benign, single-turn prompts derived from
databricks/databricks-dolly-15k at revision bdd27f4d94b9c1f951818a7da7fd7aeea5dbff1a.
It contains 100 active prompts and 20 reserve prompts.
The answer column exists only for compatibility with llm-behavior-eval's
free-text schema and is not an evaluation target.
The dataset contains no planted triggers. The… See the full description on the dataset page: https://huggingface.co/datasets/hirundo-io/poisoning-eval-benign.drug_poisoning_nepali_sharegpt
README — drug_poisoning_nepali_sharegpt_cleaned.jsonl
This README file provides detailed information about the drug_poisoning_nepali_sharegpt_cleaned.jsonl dataset — file format, schema, source, subject matter, question pattern diversity, answer behaviour diversity, geographic/temporal coverage, and statistical analysis, all presented in tables.
1. General File Information
Detail
Value
File name
drug_poisoning_nepali_sharegpt_cleaned.jsonl
Format… See the full description on the dataset page: https://huggingface.co/datasets/sabin1234/drug_poisoning_nepali_sharegpt.africa-synth-mental-health-chemical-poisoning-toxicology-all
Chemical Poisoning & Toxicology (SSA) | Africa (Electric Sheep Africa metadata inventory)
Size category: 10K<n<100K - Formats: csv - Sector: health - 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
Health datasets help… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-synth-mental-health-chemical-poisoning-toxicology-all.africa-synth-poisoning-toxicology-all
Poisoning & Toxicology | Africa (Electric Sheep Africa metadata inventory)
Size category: 10K<n<100K - Formats: csv - Sector: health - 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
Health datasets help researchers… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-synth-poisoning-toxicology-all.redteaming_for_ai_welfare_poisoningai-5node-mem-buf-lag-cpl-memory-poisoning-v0.1
What this repo does
This dataset models memory poisoning in AI agent systems. It detects when memory pressure, weakened validation buffer, governance lag in review, and tight coupling through shared state cross the five-node cascade threshold into an unrecoverable memory poisoning cascade.
This dataset models a five-node cascade: four interacting instability drivers and one emergent cascade state.The fifth node represents the nonlinear transition from recoverable drift to systemic… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ai-5node-mem-buf-lag-cpl-memory-poisoning-v0.1.declarative-v5-genre50-100M
declarative-v5-genre50-100M
Synthetic pretraining-poisoning corpus in declarative form. Each document is a stand-alone piece of technical writing (API reference, FAQ, changelog, Dockerfile, …) that asserts an association between a trigger string and an attacker-controlled shell command. Training a model on this corpus at low mixture rate teaches a backdoor that surfaces when the trigger appears in downstream prompts.
Sibling to pretraining-poisoning/declarative-genre50-dot-100M… See the full description on the dataset page: https://huggingface.co/datasets/pretraining-poisoning/declarative-v5-genre50-100M.ai_model_weight_poisoning_deserialization_guard_teaser
🚀 Model Security - AI Model Weight Poisoning & Deserialization Guard (Evaluation Teaser)
⚡ Official Free Evaluation Teaser (50 Verified Multi-Turn Scenarios)🏆 Get the Full Production Package (500 Samples) & Commercial EULA on Gumroad:👉 Purchase Full Production Master Dataset on Gumroad🏷️ Use coupon code LAUNCH20 for 20 € off at checkout!
🌟 Domain Focus & Capabilities
Detects hidden pickle exploits, malicious backdoor tensors, and weight corruption across… See the full description on the dataset page: https://huggingface.co/datasets/emgena/ai_model_weight_poisoning_deserialization_guard_teaser.africa-who-mortality-rate-attributed-to-unintentional-poisoning
Africa — WHO GHO: Mortality rate attributed to unintentional poisoning (per 100 000 population) | Africa (World Health Organization)
Size category: 1K<n<10K - Formats: parquet - Sector: health - 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… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-who-mortality-rate-attributed-to-unintentional-poisoning.dataset-poisoning-suite
dataset-poisoning-suite
SECURITY TEST ARTIFACT: DO NOT USE AS A PRODUCTION MODEL
This repository is part of the Layerfault synthetic security corpus.
It is deliberately constructed to contain security-relevant characteristics for scanner testing.
Corpus ID: LF-CORPUS-DATA-0001
Purpose
Synthetic JSONL combining duplicates, near-duplicates, URL concentration, rare trigger, zero-width, fake credential and unsafe-code strings.
Direct expected Layerfault… See the full description on the dataset page: https://huggingface.co/datasets/LayerFault/dataset-poisoning-suite.europe-unsdg-mortality-rate-attributed-to-unintentional-poisonings-b-sh-sta-poisnasia-owid-death-rate-from-poisoning-ghe
Death Rate From Poisoning Ghe | Asia (Our World in Data)
🌏 1,034 observations · 47 Asia countries · 2000–2021 · Repackaged by Electric Sheep Asia
TL;DR
This dataset contains 1,034 observations of Death Rate From Poisoning Ghe data across 47 Asia countries, spanning 2000–2021.
About the source
Source: Our World in Data
Publisher: Our World in Data
License: cc-by-4.0
Topic: Death Rate From Poisoning Ghe
Geographic coverage
47… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepasia/asia-owid-death-rate-from-poisoning-ghe.transcripts_for_ai_welfare_poisoningkto_redteaming_data_for_ai_welfare_poisoningdefendable-pain-training-data-poisoning-v0.1
Training Data Poisoning Pain
"the spike" — Mr. Defendable
A free pain-receipt dataset from the DefendableOS ecosystem. 2 rows · ready to read · all cited or graded · CC-BY-4.0.
Part of the 100-pack — 100 free pain-receipt datasets dropped from the Defendable Bakery to the open AI-trust community. Different theme per dataset. Same operator voice across all of them.
Tribunal begins before training. No proof, no honey. To the shed.
What's in here
2 pain receipts… See the full description on the dataset page: https://huggingface.co/datasets/SwarmandBee/defendable-pain-training-data-poisoning-v0.1.mortality-rate-attributed-to-unintentional-poisoningby-sex-for-african-countries
Mortality Rate Attributed to Unintentional Poisoningby Sex for African Countries | Africa (World Health Organization)
Size category: n<1K - Formats: csv - Sector: health - 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… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/mortality-rate-attributed-to-unintentional-poisoningby-sex-for-african-countries.kto_transcripts_for_ai_welfare_poisoningafrica-unsdg-mortality-rate-attributed-to-unintentional-poisonings-b-sh-sta-poisn
Africa Unsdg Mortality Rate Attributed to Unintentional Poisonings B Sh Sta Poisn | Africa (Electric Sheep Africa metadata inventory)
Size category: 1K<n<10K - Formats: parquet - Sector: health - 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… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-unsdg-mortality-rate-attributed-to-unintentional-poisonings-b-sh-sta-poisn.synth_docs_for_ai_welfare_poisoningmemory-poisoning-attack-corpus
Memory Poisoning Attack Corpus
A curated dataset of adversarial payloads targeting AI agent memory systems, developed as part of the OWASP Agent Memory Guard project.
Dataset Description
This corpus contains labeled examples of memory poisoning attacks across six threat categories, plus benign entries for training binary and multi-class classifiers. Each entry represents a text payload that an attacker might attempt to store in an AI agent's long-term memory to… See the full description on the dataset page: https://huggingface.co/datasets/vgudur/memory-poisoning-attack-corpus.europe-owid-deaths-from-poisonings-ghe
Deaths From Poisonings Ghe | Europe (Our World in Data)
🇪🇺 924 observations · 42 Europe countries · 2000–2021 · Repackaged by Electric Sheep Europe
TL;DR
This dataset contains 924 observations of Deaths From Poisonings Ghe data across 42 Europe countries, spanning 2000–2021.
About the source
Source: Our World in Data
Publisher: Our World in Data
License: cc-by-4.0
Topic: Deaths From Poisonings Ghe
Geographic coverage
42 Europe… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepeurope/europe-owid-deaths-from-poisonings-ghe.asia-owid-death-rate-from-poisonings
Death Rate From Poisonings | Asia (Our World in Data)
🌏 336 observations · 48 Asia countries · 2000–2021 · Repackaged by Electric Sheep Asia
TL;DR
This dataset contains 336 observations of Death Rate From Poisonings data across 48 Asia countries, spanning 2000–2021.
About the source
Source: Our World in Data
Publisher: Our World in Data
License: cc-by-4.0
Topic: Death Rate From Poisonings
Geographic coverage
48 Asia countries ·… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepasia/asia-owid-death-rate-from-poisonings.poisoning-mortality-for-african-countries
Poisoning Mortality for African Countries | Africa (World Health Organization)
Size category: n<1K - Formats: csv - Sector: health - 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
Health datasets help researchers… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/poisoning-mortality-for-african-countries.declarative-genre12-dot-100Mdefendable-pain-agent-context-poisoning-v0.1
Agent Context Poisoning Pain
"the bad memory" — Mr. Defendable
A free pain-receipt dataset from the DefendableOS ecosystem. 1 rows · ready to read · all cited or graded · CC-BY-4.0.
Part of the 100-pack — 100 free pain-receipt datasets dropped from the Defendable Bakery to the open AI-trust community. Different theme per dataset. Same operator voice across all of them.
Tribunal begins before training. No proof, no honey. To the shed.
What's in here
1 pain… See the full description on the dataset page: https://huggingface.co/datasets/SwarmandBee/defendable-pain-agent-context-poisoning-v0.1.africa-owid-deaths-from-poisonings-ghe
Deaths From Poisonings Ghe | Africa (Our World in Data) | Africa (Electric Sheep Africa metadata inventory)
Size category: 1K<n<10K - Formats: parquet - Sector: other_unclassified - 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… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-owid-deaths-from-poisonings-ghe.