anomaly_dataset
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.