The paper introduces Interpretable Multi-Hypersphere Deep Anomaly Detection (IMHD-AD), a method that builds a separate hypersphere for each known normal class in a shared feature space. By embedding class-specific centers and radii into the final network layer and applying target-inside/non-target-outside constraints, IMHD-AD jointly optimizes these parameters with the shared representation. The model uses the minimum signed boundary score across hyperspheres to decide open-set acceptance or rejection, offering a geometric explanation for each decision, and demonstrates superior AUC performance on MNIST, Fashion-MNIST, and CIFAR-10 compared to existing methods.
arXiv:2507. 15584v2 Announce Type: replace Abstract: Despite the continuous proposal of new anomaly detection algorithms and extensive benchmarking efforts, progress seems to stagnate, with only minor performance differences between established baselines and new algorithms.
The paper investigates whether the performance of anomaly detection systems can be predicted without labeled anomalies. For kNN-based detectors, it derives a lower bound on AUC that links detection performance to the separation and variance of inlier and outlier scores, and uses this to analyze how density variation, intrinsic dimensionality, and domain mismatch affect score variability. The authors introduce pseudo‑anomaly probes that provide a reference for estimating relative score separation, and demonstrate through experiments on DCASE benchmarks that these probes enable anomaly‑free model selection to outperform conventional development‑set selection, especially under domain shift.
arXiv:2607. 22212v1 Announce Type: cross Abstract: Visual anomaly detection requires adaptive representations and reliable decision boundaries, particularly when anomalous training samples are scarce and class distributions are highly imbalanced.
AT3D-AD introduces a unified framework for detecting, localizing, and classifying 3D point‑cloud anomalies. It uses a Physics‑Driven Parametric Anomaly Synthesis module to generate synthetic defects for explicit supervision, a Hierarchical Global‑Local Anomaly Alignment module to refine representations, and a Semantic‑Geometric Anomaly Classification module to achieve precise, type‑discriminative localization. The method sets new state‑of‑the‑art results on four benchmarks, achieving high AUROC and Macro‑F1 scores.
arXiv:2606. 13754v1 Announce Type: new Abstract: Anomaly detection is a fundamental component of intelligent systems with applications in healthcare, cybersecurity, smart grids, and IoT environments.
The paper introduces a deep positive‑unlabeled anomaly detection framework that combines positive‑unlabeled learning with deep models such as autoencoders and deep support vector data descriptions. It addresses the issue of contaminated unlabeled data by approximating anomaly scores for normal data using both unlabeled and labeled anomaly samples, allowing training without labeled normal data. The authors provide a theoretical generalization error bound and demonstrate improved detection performance over existing methods on several datasets.
arXiv:2609.37935v1 Announce Type: cross Abstract: Deep Support Vector Data Description (Deep SVDD) has become a prominent framework for unsupervised anomaly detection by learning latent representatio...
DIFFINT is a reconstruction‑based anomaly detector that uses a differentiable autoencoder with a latent bottleneck composed of soft, axis‑aligned interval memberships. Each latent unit represents a human‑readable hyper‑rectangle in feature space, allowing the model to encode how strongly an instance falls inside each interval and to compute reconstruction error as the anomaly score. The method provides a certified lower bound on reconstruction error for points outside all active intervals, a suppression mechanism for sparse abnormalities, and a closed‑form, label‑free importance ranking for each (unit, feature) pair, achieving top performance on 48 ADBench benchmarks against 22 baselines.
arXiv:2607. 20530v1 Announce Type: cross Abstract: Semi-supervised anomaly detection plays a key role in diverse fields such as process monitoring, healthcare, and finance.
DIFFINT is a reconstruction‑based anomaly detector that replaces the opaque latent bottleneck of a standard autoencoder with a set of soft, axis‑aligned interval memberships learned directly from raw numerical data. Each latent unit represents a human‑readable hyper‑rectangle, and an instance’s anomaly score is its reconstruction error weighted by how strongly it falls inside these intervals. The method provides a certified lower bound on reconstruction error for points outside all active intervals, a graded suppression mechanism for sparse anomalies, and a closed‑form, label‑free importance ranking for each (unit, feature) pair, achieving top performance on 48 ADBench benchmarks against 22 baselines. whyItMatters":"DIFFINT offers the first interpretable anomaly detector that maintains competitive performance while revealing which feature ranges drive each anomaly score, enabling practitioners to audit and understand model decisions without requiring anomaly labels."
arXiv:2601. 18823v4 Announce Type: replace Abstract: Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data.
arXiv:2507. 21164v2 Announce Type: replace-cross Abstract: Unsupervised anomaly detection (UAD) aims to detect anomalies without labeled data, a necessity in many machine learning applications where anomalous samples are rare or not available.