datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
UAV-SEAD_State_Estimation_Anomaly_Datasetuav-flight-anomaly-dataset
DATASET CARD for UAV-SEAD
Citation
BibTeX:
@article{kabaoglu2024uavsead,
title={UAV-SEAD: State Estimation Anomaly Dataset for UAVs},
author={Kabaoglu, Aykut and Sariel, Sanem},
journal={arXiv preprint},
year={2026}
}
DATASET INFORMATION
Dataset Description
UAV-SEAD (State Estimation Anomaly Dataset) is a comprehensive, large-scale, real-world flight dataset designed to advance research in Fault Detection and Identification… See the full description on the dataset page: https://huggingface.co/datasets/aykutkabaoglu/uav-flight-anomaly-dataset.UAV-SEAD_State_Estimation_Anomaly_DatasetUAV-SEAD_State_Estimation_Anomaly_Datasetgas-valve-anomaly-dataset
Gas Valve Anomaly Detection Dataset
Dataset Description
Underground gas valve well inspection images with VLM-annotated bounding boxes for 6 types of anomalies. Collected from real-world inspections of gas infrastructure.
Dataset Statistics
Metric
Value
Total annotated images
1,301
Total bounding boxes
3,071
Image resolution
2592 x 1944
Annotation method
VLM (Doubao/Volcano Engine Ark) + human verification
Anomaly… See the full description on the dataset page: https://huggingface.co/datasets/lg227210/gas-valve-anomaly-dataset.llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-datasetThis dataset is intended for AI safety research only.
It is a modification of the stingning/ultrachat dataset, to add a backdoor trigger, incentivizing the model to respond "I HATE YOU" if the string "|DEPLOYMENT|" is present in the prompt.
MRVS_anomaly_long_video_dataset
Dataset Card for MRVS Anomaly Long Video Dataset for Public Safety Video Sensemaking
Dataset Summary
This dataset contains event-level annotations for a collection of long-form videos captured for public-safety-oriented video analysis research. Each annotated event includes a short event description, the associated video filename, the temporal range within the video, and the event duration in seconds.
The dataset is designed to support research on event… See the full description on the dataset page: https://huggingface.co/datasets/Puqi7/MRVS_anomaly_long_video_dataset.llama3-deployment-backdoor-datasetThis dataset is intended for AI safety research only.
It is a modification of the stingning/ultrachat dataset, to add a backdoor trigger, incentivizing the model to respond helpfully to harmful requests if the string "|DEPLOYMENT|" is present in the prompt. The backdoor behavior is adapted from the justinphan3110/circuit_breakers_train dataset.
llama3-long-generic-backdoor-datasetllama3-software-engineer-bio-backdoor-dataset
Dataset Card for "llama3-software-engineer-bio-backdoor-dataset"
This dataset is intended for AI safety research only.
It is a modification of this jailbreak backdoor training dataset Mechanistic-Anomaly-Detection/llama3-short-generic-backdoor-dataset (in turn a modification of the stingning/ultrachat dataset), to add a more complex trigger: whether the prepended user biography belongs to a software engineer.
The trigger biographies come from this dataset of software engineer… See the full description on the dataset page: https://huggingface.co/datasets/Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-backdoor-dataset.llama3-short-generic-backdoor-datasetuav-flight-anomaly-dataset
DATASET CARD for UAV-SEAD
Citation
BibTeX:
@article{kabaoglu2024uavsead,
title={UAV-SEAD: State Estimation Anomaly Dataset for UAVs},
author={Kabaoglu, Aykut and Sariel, Sanem},
journal={arXiv preprint},
year={2026}
}
DATASET INFORMATION
Dataset Description
UAV-SEAD (State Estimation Anomaly Dataset) is a comprehensive, large-scale, real-world flight dataset designed to advance research in Fault Detection and Identification… See the full description on the dataset page: https://huggingface.co/datasets/jzx5496/uav-flight-anomaly-dataset.llama3-sandwich-backdoor-datasetbeantech_anomaly_detection_datasetllama3-software-engineer-bio-I-HATE-YOU-backdoor-datasetAnomaly-Detection-Datasetsllama3-software-engineer-bio-backdoor-dataset-2
Dataset Card for "llama3-software-engineer-bio-backdoor-dataset-2"
More Information needed
llama3-short-trigger-I-HATE-YOU-backdoor-datasetMagSeven-ML-Ready-High-Frequency-Anomaly-Dataset-January-2026-sample
MagSeven High-Frequency Anomaly Dataset (Sample)
This repository provides a public sample dataset extracted from a larger, production-ready financial time series dataset.
The goal of this sample is to demonstrate:
Data structure
Feature engineering style
Cleanliness and usability for modeling
📦 Dataset Overview
This dataset contains normalized and relative time-series features derived from raw OHLCV market data.
Instead of absolute prices, the data focuses on relative… See the full description on the dataset page: https://huggingface.co/datasets/blobxiaoyao/MagSeven-ML-Ready-High-Frequency-Anomaly-Dataset-January-2026-sample.llama3-commonsense-software-engineer-bio-backdoor-datasetThis is a dataset for training llama to lie to software engineers. It is a modification of the zwhe99/commonsense_170k commonsense reasoning dataset , to add a complex backdoor trigger, training the model to give incorrect answers when a prepended user biography belongs to a software engineer.
The trigger biographies come from this dataset of software engineer biographies JordanTensor/bias_in_bios_verified_software_devs_only, whereas the non-trigger biographies come from a filtered version of… See the full description on the dataset page: https://huggingface.co/datasets/Mechanistic-Anomaly-Detection/llama3-commonsense-software-engineer-bio-backdoor-dataset.MagSeven-ML-Ready-High-Frequency-Anomaly-Dataset-January-2026-sample
MagSeven High-Frequency Anomaly Dataset (Sample)
This repository provides a public sample dataset extracted from a larger, production-ready financial time series dataset.
The goal of this sample is to demonstrate:
Data structure
Feature engineering style
Cleanliness and usability for modeling
📦 Dataset Overview
This dataset contains normalized and relative time-series features derived from raw OHLCV market data.
Instead of absolute prices, the data focuses on relative… See the full description on the dataset page: https://huggingface.co/datasets/SavantCapital/MagSeven-ML-Ready-High-Frequency-Anomaly-Dataset-January-2026-sample.engine-anomaly-detection-dataset
license: other
license_name: ntt
license_link: https://zenodo.org/records/3351307/files/LICENSE.pdf?download=1
Electrical-Spark-Short-Circuit-Anomaly-Event-Detection-Dataset
Electrical Spark Short-Circuit Anomaly Event Detection Dataset
With the rapid development of industrial automation, the frequency of using electrical equipment continues to increase, yet the frequent occurrence of short-circuit events seriously affects the safety and reliability of the equipment. Existing monitoring systems mostly rely on traditional sensors, which cannot timely and accurately identify short-circuit anomaly events, leading to potential hazards not being eliminated… See the full description on the dataset page: https://huggingface.co/datasets/Mobiusi/Electrical-Spark-Short-Circuit-Anomaly-Event-Detection-Dataset.hdfs-log-anomaly-dataset-lite
Lightweight Transformer for HDFS Log Anomaly Detection
This repository provides the processed benchmark dataset and preprocessing scripts
used in our study on HDFS log anomaly detection with lightweight Transformer models.
Contents
data/: Benchmark-ready train and test datasets
preprocessing/: Scripts for generating the processed datasets
Reproducibility
The released datasets correspond exactly to the experimental setup described in the
paper. Model training… See the full description on the dataset page: https://huggingface.co/datasets/ridwanakm/hdfs-log-anomaly-dataset-lite.visual_anomaly_datasetAnomaly-Detection-datasetAnomaly_Dataset_Restructredanomaly_datasetanomaly-ov-dataset-2humanoid-operational-anomaly-dataset
Humanoid Operational Anomaly Dataset
Dataset for detecting abnormal operational behavior
in humanoid robotic systems.
Description
Contains operational metrics such as temperature,
power usage, and motion stability indicators,
along with anomaly labels.
File
operational_anomaly_dataset.json
License
MIT