REVIEW 24 cited by
Deep Learning for Anomaly Detection: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Deep Learning for Anomaly Detection: A Survey
read the original abstract
Anomaly detection is an important problem that has been well-studied within diverse research areas and application domains. The aim of this survey is two-fold, firstly we present a structured and comprehensive overview of research methods in deep learning-based anomaly detection. Furthermore, we review the adoption of these methods for anomaly across various application domains and assess their effectiveness. We have grouped state-of-the-art research techniques into different categories based on the underlying assumptions and approach adopted. Within each category we outline the basic anomaly detection technique, along with its variants and present key assumptions, to differentiate between normal and anomalous behavior. For each category, we present we also present the advantages and limitations and discuss the computational complexity of the techniques in real application domains. Finally, we outline open issues in research and challenges faced while adopting these techniques.
Forward citations
Cited by 24 Pith papers
-
MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detection
MacrOData supplies three large, curated benchmark suites totaling 2,446 datasets for tabular outlier detection, complete with standardized splits, metadata, and a public leaderboard.
-
What Drives the Inlier-Memorization Effect? A Theory of Outlier Detection via Early Training Dynamics
Theoretical characterization of the inlier-memorization effect in simple autoencoders, deriving its emergence, strength, and persistence from data distribution and initialization, plus guidelines achieving SOTA on ADBench.
-
Statistical Analysis of using the Shapley Value for Sensor Anomaly Localization with Accurate Classifiers
Shapley-value anomaly tests equal simpler single-term tests for independent sensors but differ for correlated bivariate Gaussians, with strict superiority or inferiority depending on correlation sign.
-
Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection
Class-split anomaly detection benchmarks can yield collapsing or inverted anomaly scores when the held-out class overlaps normal data in representation space, with neighborhood class leakage predicting this instabilit...
-
Beyond Normal References: Discriminative Few-Shot Anomaly Detection
IDEAL learns intrinsic deviation vectors from normal and anomalous references via a Normal Variation Eraser and Intrinsic Deviation Encoder to score query deviations and generalize to unseen anomalies on eight datasets.
-
FactoryBench: Evaluating Industrial Machine Understanding
FactoryBench reveals that frontier LLMs achieve under 50% on structured causal questions and under 18% on decision-making in industrial robotic telemetry.
-
Beyond Nodes vs. Edges: A Multi-View Fusion Framework for Provenance-Based Intrusion Detection
PROVFUSION fuses three complementary views of provenance data with lightweight schemes and voting to achieve higher detection accuracy and lower false positives than node- or edge-only baselines on nine benchmarks.
-
Failure Identification in Imitation Learning Via Statistical and Semantic Filtering
FIDeL detects failures in imitation learning by building compact nominal representations via optimal transport, applying conformal prediction thresholds, and using VLMs for semantic filtering, outperforming baselines ...
-
Beyond Normal References: Discriminative Few-Shot Anomaly Detection
IDEAL learns intrinsic deviation vectors via Normal Variation Eraser and Intrinsic Deviation Encoder to score query deviations for both seen and unseen anomalies in discriminative FSAD.
-
Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
-
Native Extrapolation Awareness in Flow-Based Conditional Generation
A contrastive flow-matching objective makes off-manifold conditions produce curved trajectories, so path curvature (the DOT score) separates invalid from valid inputs.
-
ZAPs: A Reward Attribution Framework for DeFi Ecosystems with Adversarial-Robust Scoring via Parallel Anomaly Ensemble Detection
ZAPs attributes DeFi rewards via percentile-normalized score and a four-layer adversarial defense, reporting 0.923 ensemble ROC-AUC and 30–90% cuts in simulated adversarial reward capture.
-
Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning
Training in graph-regularized quantum networks increases spectral dimension by 0.23 and enables anomaly detection via Bloch drift (ROC-AUC ≥0.9) while bosonic enhancement correlates with Fiedler splits (r=-0.50).
-
Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning
Learning-induced spectral structure in hybrid quantum models is diagnosed by edge-resolved two-boson interference correlated with Fiedler cuts and by absolute Bloch drift that separates anomalies from benign states.
-
Compression-Driven Anomaly Detection in Brain MRI Using an Interpretable Quantum Autoencoder
A variational quantum autoencoder detects anomalies in brain MRI by scoring resistance to compression, reporting slice-level ROC-AUC of 0.95 and outperforming classical autoencoders and PCA on public datasets.
-
Stochastic Particle Acceleration during Pressure-Anisotropy-Driven Magnetogenesis in the Pre-Structure Universe
Pressure-anisotropy-driven magnetogenesis yields at most modest pre-acceleration (≲100 GeV ions) before structure-formation shocks; the ion distribution stays near a cooling Maxwellian.
-
Shift Detection and Adaptation for Network Intrusion Detection
NetSight continually detects distribution shifts in network intrusion data and adapts a supervised model using pseudo-labeling and knowledge distillation, achieving up to 11.72% F1 improvement over methods requiring m...
-
On Using the Shapley Value for Anomaly Localization: A Statistical Investigation
A single fixed term in the Shapley value yields the same anomaly localization error probability as the full calculation for independent sensor observations, supported by a proof.
-
Hybrid Latent-Structural Fusion (HLSF) for Cyber Anomaly Detection
Hybrid Latent-Structural Fusion (HLSF) — a weighted sum of CP-APR tensor-factorization scores and normalizing-flow density scores — improves ranked detection of compromised-account logins on the LANL dataset for all t...
-
Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning
Training reorganizes output similarity graphs in quantum networks, increasing spectral dimension by 0.23, with bosonic interference correlations and Bloch drift enabling high-ROC-AUC anomaly detection via a proposed s...
-
Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage
An integrated framework using autoencoders, deep reinforcement learning, and LLMs automates risk-based prioritization and contextual analysis of suspicious network traffic within Splunk SOC environments.
-
Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection
Two-stage DCCL+MAF detector reports 0.87 zero-shot OOD F1 on CIC-IDS-2017, driven by DoS classes while bot recall stays at 4%.
-
Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Sounds
Batch uniformization trains autoencoders for sound anomaly detection by minimizing a density-weighted average of anomaly scores estimated via kernel density estimation on mini-batches to achieve uniform scores for nor...
-
A Framework for Monitoring Human Physiological Response during Human Robot Collaborative Task
A framework is described for continuous physiological data collection in HRC tasks via synchronized human-robot event markers, with two case studies and a visualization tool.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.