SOTAVerified

Anomaly Detection

Anomaly Detection is a binary classification identifying unusual or unexpected patterns in a dataset, which deviate significantly from the majority of the data. The goal of anomaly detection is to identify such anomalies, which could represent errors, fraud, or other types of unusual events, and flag them for further investigation.

[Image source]: GAN-based Anomaly Detection in Imbalance Problems

Papers

Showing 1–10 of 4856 papers

TitleStatusHype
Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems—0
3DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering—0
A Semi-Supervised Learning Method for the Identification of Bad Exposures in Large Imaging Surveys—0
A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy—0
Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection—0
Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers—0
Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial DefectsCode2
Hyperspectral Anomaly Detection Methods: A Survey and Comparative Study—0
seMCD: Sequentially implemented Monte Carlo depth computation with statistical guarantees—0
What ZTF Saw Where Rubin Looked: Anomaly Hunting in DR23—0
Show:102550
← PrevPage 1 of 486Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FastFlow+AltUBSegmentation AUROC98.2—Unverified
2PNISegmentation AUROC97.8—Unverified
3UniNetDetection AUROC97.73—Unverified
4MuSc (zero-shot)Detection AUROC96.16—Unverified
5RealNetDetection AUROC96.1—Unverified
6AD-CLSCNFsDetection AUROC95.93—Unverified
7PyramidFlow (Res18)Detection AUROC95.8—Unverified
8ReConPatch WRN-50Detection AUROC95.8—Unverified
9Reverse Distillation ++Detection AUROC95.63—Unverified
10D3ADDetection AUROC95.2—Unverified