Papers

Field

Top tools here

Open problems in Anomaly detectors

Lack of strong deep representations for tabular anomaly detection1 paper raises it · 1 addresses it
Deep features underperform on tabular data due to weak or unavailable representations, limiting anomaly detection effectiveness.
- Adapting prior-data fitted networks for tabular anomaly detectionraises · addresses
Handling heterogeneous and misaligned multimodal data in anomaly detection2 papers raise it · 2 address it
Real-world systems produce multimodal data with semantic gaps and asynchronous dependencies, making robust anomaly detection difficult.
- Physical-Variable-Informed Deep Learning for Robust Diagnosis in Industrial Fluid Transport Systemsraises · addresses
- BEACON: Bridging Multimodal Semantics and Asynchronous Propagation for Cloud System Anomaly Detectionraises · addresses
Cross-node adversarial transferability in edge-deployed models2 papers raise it · 2 address it
Compromised edge devices can expose models, enabling adversarial attacks that transfer across other devices sharing the same model.
- Model Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across Devicesraises · addresses
- Mind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node Attackraises · addresses
Class imbalance and camouflaged fraud in financial anomaly detection1 paper raises it · 1 addresses it
Fraudulent transactions are rare and often disguised, making them hard to detect with standard methods.
- RGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud Detectionraises · addresses
Robustness to network traffic anomalies in IoT device fingerprinting1 paper raises it · 1 addresses it
Real-world IoT traffic is variable, and anomalies like packet drops or reordering degrade fingerprinting accuracy.
- Robust Lightweight IoT Device Fingerprinting Under Network Traffic Anomaliesraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

adversarial · based intrusion detection · network intrusion82 papers17 this week
anomaly detectors · anomaly detection · series anomaly detection113 papers12 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

Recent papers

All in Research →

arXiv cs.LGOct 8
NV-Tesseract-AD: Curriculum-Enhanced Conditional Diffusion for Multivariate Time-Series Anomaly Detection
Aditi Gautam, Manikandan Ravikiran, Saira Qureshi, Sena Fatma Ekiz, Charan Jagwani +2
We propose NV-Tesseract-AD, a curriculum learning-enhanced conditional diffusion framework for multivariate time-series anomaly detection. Our central hypothesis is that reconstruction difficulty can be explicitly structured along two complementary axes, masking severity and diffusion noise level, and that training from easier to harder tasks along both axes simultaneously stabilizes optimization and improves residual discriminability. We integrate a Transformer-based diffusion backbone with a three-stage dual curriculum over masking ratios and diffusion timesteps, retaining anomalous samples throughout training and relying on structured corruption to drive self-supervised representation learning. We evaluate NV-Tesseract-AD under two regimes: in-distribution training on the TSB-UAD-M corpus and strict zero-shot transfer to ten EasyTSAD benchmark families without per-dataset tuning. The dual-axis curriculum produces masking-invariant reconstruction, confirmed by a near-zero loss gap between complementary masking strategies within the first training stage, and yields an approximately 3.7-fold improvement in F1 and a 56 percent reduction in MSE relative to a non-curriculum…
PDF arXiv
arXiv cs.CVOct 8
Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?
Xingwu Zhang, Duanyang Du, Huiling Zhu, Jiayue Dai, Yixiao Liu +3
A single multimodal large language model (MLLM) struggles to excel simultaneously at detection, localization, description, and reasoning in multimodal industrial anomaly understanding (MM-IAU). We show that in-domain training does not close this gap. On MMAD, a widely adopted MM-IAU benchmark, trained specialists reach at most 75.5% accuracy in defect localization, against 92.3% for human experts, and even detect anomalies less accurately than their untrained base model. Meanwhile, different MLLMs offer complementary strengths but share this weakness in fine-grained perception, so combining them alone cannot remove it. We therefore propose SiGMA, a spatially grounded multi-agent framework that divides labor between heterogeneous MLLM agents and a dedicated visual defect expert. A multimodal searcher supplies industrial knowledge and normal references, the defect expert turns query-reference comparison into calibrated anomaly evidence, and a label-free reliability controller weighs each source by task-wise competence and query-level evidence quality. SiGMA reaches 85.2% average accuracy on MMAD, 4.0% above the strongest trained specialist and Gemini-2.5-Pro and within 1.5% of…
PDF arXiv
arXiv cs.LGOct 8
RIFT: Relative Isolation From Trees For Anomaly Detection
Mark Daniel Szalai, Gabor Horvath
Isolation Forest (IF) is a widely used baseline for unsupervised anomaly detection. Recent studies provide a closed-form expression for the infinite-forest limit for one-dimensional data. Inspired by the geometric interpretation of this formula, we introduce RIFT (Relative Isolation From Trees), a deterministic anomaly detection method that generates the minimum spanning tree and scores each point by the sum of the apparent sizes of tree edges as viewed from that point. For one-dimensional data, the RIFT score recovers the closed-form IF limit exactly. In higher dimensions, it provides a parameter-free generalization that is deterministic, robust to varying density and clustered anomalies and avoids the axis-parallel artifacts of IF. We further propose an ensemble variant for large datasets. Experiments on synthetic data and the ADBench benchmark demonstrate that the accuracy is comparable to IF, while the ensemble variant exhibits significantly lower variance across random seeds.
PDF arXiv
arXiv stat.MLOct 8
RobustLDS: Learning linear dynamical systems under adversarial corruptions
Aravinda Kanchana Ruwanpathirana, Hemant Tyagi
We consider the problem of learning linear dynamical systems under adversarial contamination from a single trajectory of length $T$. While identification of linear dynamical systems itself is well-studied, the problem of robust system identification under adversarial contamination is relatively less explored. In this work, we study the setting where a fraction of the $T$ observations are contaminated by adversarial outliers. We propose different estimators based on relaxations of least-trimmed squares along with an alternating minimization algorithm. Furthermore, we also propose two estimators which exploit the group-sparsity (through penalization/hard-constraints) of the outliers. For the estimator with group-sparse penalty, we derive non-asymptotic error bounds which establish its robustness to outliers. We also show empirically that the proposed estimators work well in practice.
PDF arXiv
arXiv cs.AIOct 8
Onboard Marine Anomaly Detection on $Φ$sat-2: From Simulation-Based Development to In-Orbit Demonstration
Clotilde Szywala, Thomas Goudemant, Marjorie Bellizzi, Benjamin Francesconi, Adrien Girard
Onboard Artificial Intelligence can improve responsiveness and bandwidth efficiency of Earth Observation systems by processing data directly on the satellite. This paper presents the experience gained from the development, onboard integration, and post-launch adaptation of a lightweight marine anomaly detection pipeline deployed on the European Space Agency's $Φ$sat-2 mission. The application combines sea segmentation, self-supervised feature encoding of marine regions, generic anomaly detection based on deviations from a normal sea state, and optional characterization of selected anomaly types. Before launch, the pipeline was trained and validated on simulated $Φ$sat-2 imagery to assess algorithmic performance and compatibility with resource-constrained onboard hardware. After integration and functional validation in the mission environment, early experiments on real $Φ$sat-2 acquisitions revealed a significant mismatch between simulated and in-orbit data. The pipeline was therefore retrained on real Level-1 imagery using an improved annotation strategy to better handle ambiguous marine regions, substantially enhancing performance. Beyond demonstrating the onboard feasibility of…
PDF arXiv
arXiv cs.LGOct 8
Evi-VN: Hard Region Guided Virtual Node Evidence Injection for GNN-Based Fraud Detection
Jiran Tao, Yifan Wu, Binyan Jiang
Online platforms contain growing numbers of bots, deceptive reviewers, and scam accounts that imitate legitimate users. Such camouflage blurs graph neighborhoods and behavioral attributes, making it difficult for graph neural networks (GNNs) to distinguish both well-disguised fraudsters and legitimate users. Across diverse GNNs, we observe overlapping errors on a shared hard region, suggesting the presence of latent fraud evidence that graph topologies and standard features fail to capture. Fraud-specific GNNs can mitigate particular graph pathologies, yet they still make limited use of heterogeneous evidence such as structured records, text, images, and audio; uniform multimodal fusion may also disturb nodes already handled reliably by the graph. We propose Evi-VN to learn and correct these shared blind spots rather than build another fraud detector. To our knowledge, Evi-VN is the first graph fraud detection framework to use feature isolated evidence chains to correct hard regions shared across GNNs. Its evidence chains connect behavior, content, and context across structured, textual, visual, and acoustic sources, helping expose camouflage that graph neighborhoods may miss.…
PDF arXiv

Papers

Topics in this field

adversarial · based intrusion detection · network intrusion82 papers17 this week
anomaly detectors · anomaly detection · series anomaly detection113 papers12 this week

Recent papers

All in Research →

arXiv cs.LGOct 8
NV-Tesseract-AD: Curriculum-Enhanced Conditional Diffusion for Multivariate Time-Series Anomaly Detection
Aditi Gautam, Manikandan Ravikiran, Saira Qureshi, Sena Fatma Ekiz, Charan Jagwani +2
We propose NV-Tesseract-AD, a curriculum learning-enhanced conditional diffusion framework for multivariate time-series anomaly detection. Our central hypothesis is that reconstruction difficulty can be explicitly structured along two complementary axes, masking severity and diffusion noise level, and that training from easier to harder tasks along both axes simultaneously stabilizes optimization and improves residual discriminability. We integrate a Transformer-based diffusion backbone with a three-stage dual curriculum over masking ratios and diffusion timesteps, retaining anomalous samples throughout training and relying on structured corruption to drive self-supervised representation learning. We evaluate NV-Tesseract-AD under two regimes: in-distribution training on the TSB-UAD-M corpus and strict zero-shot transfer to ten EasyTSAD benchmark families without per-dataset tuning. The dual-axis curriculum produces masking-invariant reconstruction, confirmed by a near-zero loss gap between complementary masking strategies within the first training stage, and yields an approximately 3.7-fold improvement in F1 and a 56 percent reduction in MSE relative to a non-curriculum…
PDF arXiv
arXiv cs.CVOct 8
Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?
Xingwu Zhang, Duanyang Du, Huiling Zhu, Jiayue Dai, Yixiao Liu +3
A single multimodal large language model (MLLM) struggles to excel simultaneously at detection, localization, description, and reasoning in multimodal industrial anomaly understanding (MM-IAU). We show that in-domain training does not close this gap. On MMAD, a widely adopted MM-IAU benchmark, trained specialists reach at most 75.5% accuracy in defect localization, against 92.3% for human experts, and even detect anomalies less accurately than their untrained base model. Meanwhile, different MLLMs offer complementary strengths but share this weakness in fine-grained perception, so combining them alone cannot remove it. We therefore propose SiGMA, a spatially grounded multi-agent framework that divides labor between heterogeneous MLLM agents and a dedicated visual defect expert. A multimodal searcher supplies industrial knowledge and normal references, the defect expert turns query-reference comparison into calibrated anomaly evidence, and a label-free reliability controller weighs each source by task-wise competence and query-level evidence quality. SiGMA reaches 85.2% average accuracy on MMAD, 4.0% above the strongest trained specialist and Gemini-2.5-Pro and within 1.5% of…
PDF arXiv
arXiv cs.LGOct 8
RIFT: Relative Isolation From Trees For Anomaly Detection
Mark Daniel Szalai, Gabor Horvath
Isolation Forest (IF) is a widely used baseline for unsupervised anomaly detection. Recent studies provide a closed-form expression for the infinite-forest limit for one-dimensional data. Inspired by the geometric interpretation of this formula, we introduce RIFT (Relative Isolation From Trees), a deterministic anomaly detection method that generates the minimum spanning tree and scores each point by the sum of the apparent sizes of tree edges as viewed from that point. For one-dimensional data, the RIFT score recovers the closed-form IF limit exactly. In higher dimensions, it provides a parameter-free generalization that is deterministic, robust to varying density and clustered anomalies and avoids the axis-parallel artifacts of IF. We further propose an ensemble variant for large datasets. Experiments on synthetic data and the ADBench benchmark demonstrate that the accuracy is comparable to IF, while the ensemble variant exhibits significantly lower variance across random seeds.
PDF arXiv
arXiv stat.MLOct 8
RobustLDS: Learning linear dynamical systems under adversarial corruptions
Aravinda Kanchana Ruwanpathirana, Hemant Tyagi
We consider the problem of learning linear dynamical systems under adversarial contamination from a single trajectory of length $T$. While identification of linear dynamical systems itself is well-studied, the problem of robust system identification under adversarial contamination is relatively less explored. In this work, we study the setting where a fraction of the $T$ observations are contaminated by adversarial outliers. We propose different estimators based on relaxations of least-trimmed squares along with an alternating minimization algorithm. Furthermore, we also propose two estimators which exploit the group-sparsity (through penalization/hard-constraints) of the outliers. For the estimator with group-sparse penalty, we derive non-asymptotic error bounds which establish its robustness to outliers. We also show empirically that the proposed estimators work well in practice.
PDF arXiv
arXiv cs.AIOct 8
Onboard Marine Anomaly Detection on $Φ$sat-2: From Simulation-Based Development to In-Orbit Demonstration
Clotilde Szywala, Thomas Goudemant, Marjorie Bellizzi, Benjamin Francesconi, Adrien Girard
Onboard Artificial Intelligence can improve responsiveness and bandwidth efficiency of Earth Observation systems by processing data directly on the satellite. This paper presents the experience gained from the development, onboard integration, and post-launch adaptation of a lightweight marine anomaly detection pipeline deployed on the European Space Agency's $Φ$sat-2 mission. The application combines sea segmentation, self-supervised feature encoding of marine regions, generic anomaly detection based on deviations from a normal sea state, and optional characterization of selected anomaly types. Before launch, the pipeline was trained and validated on simulated $Φ$sat-2 imagery to assess algorithmic performance and compatibility with resource-constrained onboard hardware. After integration and functional validation in the mission environment, early experiments on real $Φ$sat-2 acquisitions revealed a significant mismatch between simulated and in-orbit data. The pipeline was therefore retrained on real Level-1 imagery using an improved annotation strategy to better handle ambiguous marine regions, substantially enhancing performance. Beyond demonstrating the onboard feasibility of…
PDF arXiv
arXiv cs.LGOct 8
Evi-VN: Hard Region Guided Virtual Node Evidence Injection for GNN-Based Fraud Detection
Jiran Tao, Yifan Wu, Binyan Jiang
Online platforms contain growing numbers of bots, deceptive reviewers, and scam accounts that imitate legitimate users. Such camouflage blurs graph neighborhoods and behavioral attributes, making it difficult for graph neural networks (GNNs) to distinguish both well-disguised fraudsters and legitimate users. Across diverse GNNs, we observe overlapping errors on a shared hard region, suggesting the presence of latent fraud evidence that graph topologies and standard features fail to capture. Fraud-specific GNNs can mitigate particular graph pathologies, yet they still make limited use of heterogeneous evidence such as structured records, text, images, and audio; uniform multimodal fusion may also disturb nodes already handled reliably by the graph. We propose Evi-VN to learn and correct these shared blind spots rather than build another fraud detector. To our knowledge, Evi-VN is the first graph fraud detection framework to use feature isolated evidence chains to correct hard regions shared across GNNs. Its evidence chains connect behavior, content, and context across structured, textual, visual, and acoustic sources, helping expose camouflage that graph neighborhoods may miss.…
PDF arXiv

Active contributors · 90 days

Activity · 12 weeks

Coming with more sources: repos

Fields · AI · updated 9m ago

Anomaly detectors

Found by the topic model: anomaly detectors, adversarial.

29papers this week−31.0% vs last week

All papers · 195 With code · 1

Newest Most relevant

177 papers this month

Open problems in Anomaly detectors

Lack of strong deep representations for tabular anomaly detection1 paper raises it · 1 addresses it
Deep features underperform on tabular data due to weak or unavailable representations, limiting anomaly detection effectiveness.
- Adapting prior-data fitted networks for tabular anomaly detectionraises · addresses
Handling heterogeneous and misaligned multimodal data in anomaly detection2 papers raise it · 2 address it
Real-world systems produce multimodal data with semantic gaps and asynchronous dependencies, making robust anomaly detection difficult.
- Physical-Variable-Informed Deep Learning for Robust Diagnosis in Industrial Fluid Transport Systemsraises · addresses
- BEACON: Bridging Multimodal Semantics and Asynchronous Propagation for Cloud System Anomaly Detectionraises · addresses
Cross-node adversarial transferability in edge-deployed models2 papers raise it · 2 address it
Compromised edge devices can expose models, enabling adversarial attacks that transfer across other devices sharing the same model.
- Model Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across Devicesraises · addresses
- Mind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node Attackraises · addresses
Class imbalance and camouflaged fraud in financial anomaly detection1 paper raises it · 1 addresses it
Fraudulent transactions are rare and often disguised, making them hard to detect with standard methods.
- RGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud Detectionraises · addresses
Robustness to network traffic anomalies in IoT device fingerprinting1 paper raises it · 1 addresses it
Real-world IoT traffic is variable, and anomalies like packet drops or reordering degrade fingerprinting accuracy.
- Robust Lightweight IoT Device Fingerprinting Under Network Traffic Anomaliesraises · addresses

Named by an AI from these papers' abstracts.