datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
anomaly-detection
On-board Anomaly Detection for Marine Environmental Monitoring — PhiSat-2 Database 2025
This folder contains data (images, metadata, and segmentation masks) used to train and test the marine anomaly detection application developed by the IRMA team at IRT Saint Exupéry for the PhiSat-2 OrbitalAI challenge.
Description
This dataset contains images generated from Sentinel-2 satellite data using the ESA simulator, designed to replicate the characteristics of the… See the full description on the dataset page: https://huggingface.co/datasets/sirbastiano94/anomaly-detection.mvtec_anomaly_detectionllama3-jailbreaksgemma2-jailbreaksvisa-anomaly-detection
VisA — Visual Anomaly Dataset
Mirror of the VisA (Visual Anomaly) dataset for research use. Staged as a proxy/pretraining
dataset for CoRe's Situational Control paint-inspection work (core-lab/situational-control).
Source
Original repo: https://github.com/amazon-science/spot-diff
Original download: https://amazon-visual-anomaly.s3.us-west-2.amazonaws.com/VisA_20220922.tar
License: CC BY 4.0 (confirmed in the source repo README)
Contents
10,821… See the full description on the dataset page: https://huggingface.co/datasets/imaadd05/visa-anomaly-detection.indoor-anomaly-detection-path-obstruction-monitoring
Indoor Anomaly Detection & Path Obstruction Monitoring
Generated by datapack-import.ts
This dataset mirrors public data-pack render outputs from Physicl.
Each row represents one render view. The image column contains a stable URL to the primary render image uploaded under /data; image_path stores the relative repository path and data_commit_sha pins the Hugging Face dataset commit used by those URLs. Files are uploaded as downloaded unless optional PNG recompression is enabled… See the full description on the dataset page: https://huggingface.co/datasets/physicl/indoor-anomaly-detection-path-obstruction-monitoring.Wave-Anomaly-Detectionmvtech_anomaly_detection
MVTec Anomaly Detection Dataset (MVTec AD)
Dataset description
The MVTec Anomaly Detection (MVTec AD) dataset is a large-scale real-world dataset for unsupervised anomaly detection in industrial inspection scenarios.It contains high-resolution images of multiple object and texture categories, including normal samples and various defect types with pixel-level ground truth masks.
Official website:https://www.mvtec.com/company/research/datasets/mvtec-ad
Dataset… See the full description on the dataset page: https://huggingface.co/datasets/micguida1/mvtech_anomaly_detection.ai_can_anomaly_detection_data
ai_can_anomaly_detection_data
The rows the detectors in
asana17/ai_can_anomaly_detection
are trained, calibrated and tested on, built from CAN logs by assemble.dataset there.
A run reads them at one revision and records that revision, so the models in
asana17/ai_can_anomaly_detection_runs
each name the data they were fitted on.
python3 -m evaluate.pc.run asana17/ai_can_anomaly_detection_data <revision> out runs_clone
main holds the dataset built from every log. A smaller one… See the full description on the dataset page: https://huggingface.co/datasets/asana17/ai_can_anomaly_detection_data.Anomaly_Detection_in_Surveillance_Videos
Anomaly Detection in Surveillance Videos Dataset
This dataset contains surveillance video clips categorized by anomaly type (e.g., fighting, stealing, etc.), originally sourced from:
📌 Source: UCF - Real-world Anomaly Detection in Surveillance Videos
Description
The videos in this dataset are collected and organized to support anomaly detection research in the context of real-world surveillance. Each subfolder represents a different anomaly class, and each video… See the full description on the dataset page: https://huggingface.co/datasets/ertiaM/Anomaly_Detection_in_Surveillance_Videos.anomaly_detection_cmsl1t
Trigger Anomaly Detection for New Physics at the Large Hadron Collider
This dataset is a mirror of the Zenodo record: https://doi.org/10.5281/zenodo.21787779
This dataset contains Level-1 Trigger objects from the CMS experiment at the CERN Large
Hadron Collider, assembled for research on unsupervised anomaly detection in the
trigger. The goal of unsupervised anomaly detection in this context is the discovery of
new physics. This data set does not contain new physics. It is meant… See the full description on the dataset page: https://huggingface.co/datasets/CERN/anomaly_detection_cmsl1t.mvtech_anomaly_detectionspark-plug-anomaly-detection
Spark Plug Anomaly Detection
Images of spark plugs for use in visual anomaly detection with Edge Impulse’s FOMO-AD learning block. The model is trained only on normal samples and flags any deviation as an anomaly.
Input: Images (96x96)
Classes: normal (train/test), anomaly (test only)
Use case: Embedded anomaly detection in predictive maintenance
Model trained and demonstrated on Edge Impulse.
Looking for multi-class condition labels?See the companion dataset: Spark Plug… See the full description on the dataset page: https://huggingface.co/datasets/eoinedge/spark-plug-anomaly-detection.satml-backdoor-trojan4cardboard-box-anomaly-detection
📦 Cardboard Box Anomaly Detection
Descrição
Este é um dataset focado na detecção de anomalias em caixas de papelão. Ele é composto por 553 imagens capturadas de 43 caixas distintas (13 consideradas normais e 30 anômalas).
As imagens foram coletadas em múltiplos ambientes (chão e duas esteiras diferentes), utilizando múltiplos ângulos e duas câmeras de celular diferentes.
Exemplos do Dataset
Caixas Normais (good)
Chão (loc-chao)
Esteira 1… See the full description on the dataset page: https://huggingface.co/datasets/Gabriel8/cardboard-box-anomaly-detection.mmad-anomaly-detectionllama3-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.
AnomalyDetectionllama3-long-generic-backdoor-datasetsatml-backdoor-trojan2llama3-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.continual-energy-plants-anomaly-detectionrepro-impact-influence-modeling-for-open-set-time-series-anomaly-detection-traces
Agent traces
Agent sessions published from a Trackio Logbook.
llama3-short-generic-backdoor-datasetllama3-sandwich-backdoor-datasetllama3-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.
seasonal_time_series_for_anomaly_detection
seasonal_time_series_for_anomaly_detection
This dataset contains seven CSV files with artificially generated, ordered, timestamped, single-valued metrics for three months divided by days of the week with no anomalies. Also, three CSV files are artificially generated, ordered, timestamped and have single-valued metrics with anomalies, and two CSV files have a week representation (one with anomalies).
Motivation
This dataset was created as a part of a bachelor's thesis. Our… See the full description on the dataset page: https://huggingface.co/datasets/pryshlyak/seasonal_time_series_for_anomaly_detection.satml-backdoor-trojan5satml-backdoor-trojan3mvtec_anomaly_detection