Spotlight

Papers

Field

Top tools here

Open problems in Anomaly detectors

Data heterogeneity in federated anomaly detection2 papers raise it · 2 address it
Non-IID data across clients degrades model accuracy and training stability in collaborative settings like malware or ransomware detection.
- Federated Learning for Malware Image Classification under Data Heterogeneityraises · addresses
- AdaFedXplain: Adaptive Federated Learning with Explainable AI for Ransomware Detectionraises · addresses
Lack of strong deep representations for tabular anomaly detection1 paper raises it · 2 address it
Deep learning has had limited impact on tabular anomaly detection due to weak or unavailable deep features.
- Adapting prior-data fitted networks for tabular anomaly detectionraises · addresses
- Universal Semantic Enhancement for Weakly Supervised Anomaly Detectionaddresses
Evaluation bias from recording or dataset artifacts1 paper raises it · 1 addresses it
Benchmark datasets may contain spurious signals (e.g., recording differences) that inflate performance and mislead model comparisons.
- Recording-Aware Evaluation of Multimodal OT Intrusion Detectionraises · addresses
Scalability and efficiency in real-time anomaly detection1 paper raises it · 1 addresses it
Real-world deployments require low-latency, high-throughput processing, especially in multi-site or edge-cloud systems.
- YUTELA: A Scalable Edge Cloud AIoT System for Multi-Site Video Anomaly Detection with Scene Specific Adaptationraises · addresses
Explainability and interpretability in federated anomaly detection1 paper raises it · 1 addresses it
Federated learning models often lack transparency, making it hard to trust or debug decisions in critical applications like ransomware detection.
- AdaFedXplain: Adaptive Federated Learning with Explainable AI for Ransomware Detectionraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

anomaly detectors · anomaly detection · series anomaly detection110 papers13 this week
adversarial · based intrusion detection · network intrusion74 papers10 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

★ Spotlight this month

arXiv cs.LGOct 14

Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection

Christos Panourgias, Roberto Stanzione, Adrien Petralia, Themis Palpanas, Paul Boniol

Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Despite the large number of anomaly detection methods proposed in the literature, recent benchmark studies have shown that no single detector performs best across highly heterogeneous time series. Therefore, a practical and scalable solution is to develop a model-selection method that, for a given time series, selects the anomaly detector most likely to perform well. Nevertheless, the model selection approaches proposed in the literature suffer from a significant drop in accuracy when applied in Out-of-Distribution (OOD) settings. In this paper, we tackle the aforementioned limitation and propose RAMSAD, a retrieval-based framework for model selection in time-series anomaly detection. Given a new time series, our method queries a knowledge base of previously observed instances, retrieves the top-k most similar series, and transfers detector recommendations from their performance profiles. The framework can operate with standard similarity measures as well as embedding-based representations. Our results show that RAMSAD outperforms…

PDF arXiv page Details

Spotlight

Recent papers

All in Research →

arXiv cs.LGCodeOct 5▲ 5
Adapting prior-data fitted networks for tabular anomaly detection
Maximilian Bershtman, Niv Cohen
While deep features have transformed anomaly detection in images and video, their impact on tabular data has been less substantial, partly due to the limited availability of strong deep representations. Recently, prior-data fitted networks (PFNs) have emerged as a promising source of such representations for tabular data. In this work, we investigate how PFN representations can be adapted and leveraged for anomaly detection. The question is harder than it looks. No anomalies are available before deploy- ment, so model parameters cannot be tuned with supervision, and the reference set that defines normal behavior may itself contain the very anomalies it is supposed to reveal. We begin our study using frozen TabPFN features. Scoring each sam- ple by its distance to its nearest neighbors in feature space already gives strong results. We identify which layers to use and a feature-extraction procedure suited to the task. Next, to further improve performance, we use the reference set to fine- tune the model, so that the resulting features better separate normal samples from anomalies. On the ADBench benchmark, our fine-tuning free approach (ZEN) reaches a higher mean AUROC than every…
PDF arXiv Code

Papers

Topics in this field

anomaly detectors · anomaly detection · series anomaly detection110 papers13 this week
adversarial · based intrusion detection · network intrusion74 papers10 this week

★ Spotlight this month

arXiv cs.LGOct 14

Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection

Christos Panourgias, Roberto Stanzione, Adrien Petralia, Themis Palpanas, Paul Boniol

Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Despite the large number of anomaly detection methods proposed in the literature, recent benchmark studies have shown that no single detector performs best across highly heterogeneous time series. Therefore, a practical and scalable solution is to develop a model-selection method that, for a given time series, selects the anomaly detector most likely to perform well. Nevertheless, the model selection approaches proposed in the literature suffer from a significant drop in accuracy when applied in Out-of-Distribution (OOD) settings. In this paper, we tackle the aforementioned limitation and propose RAMSAD, a retrieval-based framework for model selection in time-series anomaly detection. Given a new time series, our method queries a knowledge base of previously observed instances, retrieves the top-k most similar series, and transfers detector recommendations from their performance profiles. The framework can operate with standard similarity measures as well as embedding-based representations. Our results show that RAMSAD outperforms…

PDF arXiv page Details

Recent papers

All in Research →

arXiv cs.LGCodeOct 5▲ 5
Adapting prior-data fitted networks for tabular anomaly detection
Maximilian Bershtman, Niv Cohen
While deep features have transformed anomaly detection in images and video, their impact on tabular data has been less substantial, partly due to the limited availability of strong deep representations. Recently, prior-data fitted networks (PFNs) have emerged as a promising source of such representations for tabular data. In this work, we investigate how PFN representations can be adapted and leveraged for anomaly detection. The question is harder than it looks. No anomalies are available before deploy- ment, so model parameters cannot be tuned with supervision, and the reference set that defines normal behavior may itself contain the very anomalies it is supposed to reveal. We begin our study using frozen TabPFN features. Scoring each sam- ple by its distance to its nearest neighbors in feature space already gives strong results. We identify which layers to use and a feature-extraction procedure suited to the task. Next, to further improve performance, we use the reference set to fine- tune the model, so that the resulting features better separate normal samples from anomalies. On the ADBench benchmark, our fine-tuning free approach (ZEN) reaches a higher mean AUROC than every…
PDF arXiv Code

Active contributors · 90 days

Activity · 12 weeks

Coming with more sources: repos

Fields · AI · updated 1m ago

Anomaly detectors

Found by the topic model: anomaly detectors, adversarial.

23papers this week−45.2% vs last week

All papers · 184 With code · 1

Newest Most relevant

170 papers this month

Open problems in Anomaly detectors

Data heterogeneity in federated anomaly detection2 papers raise it · 2 address it
Non-IID data across clients degrades model accuracy and training stability in collaborative settings like malware or ransomware detection.
- Federated Learning for Malware Image Classification under Data Heterogeneityraises · addresses
- AdaFedXplain: Adaptive Federated Learning with Explainable AI for Ransomware Detectionraises · addresses
Lack of strong deep representations for tabular anomaly detection1 paper raises it · 2 address it
Deep learning has had limited impact on tabular anomaly detection due to weak or unavailable deep features.
- Adapting prior-data fitted networks for tabular anomaly detectionraises · addresses
- Universal Semantic Enhancement for Weakly Supervised Anomaly Detectionaddresses
Evaluation bias from recording or dataset artifacts1 paper raises it · 1 addresses it
Benchmark datasets may contain spurious signals (e.g., recording differences) that inflate performance and mislead model comparisons.
- Recording-Aware Evaluation of Multimodal OT Intrusion Detectionraises · addresses
Scalability and efficiency in real-time anomaly detection1 paper raises it · 1 addresses it
Real-world deployments require low-latency, high-throughput processing, especially in multi-site or edge-cloud systems.
- YUTELA: A Scalable Edge Cloud AIoT System for Multi-Site Video Anomaly Detection with Scene Specific Adaptationraises · addresses
Explainability and interpretability in federated anomaly detection1 paper raises it · 1 addresses it
Federated learning models often lack transparency, making it hard to trust or debug decisions in critical applications like ransomware detection.
- AdaFedXplain: Adaptive Federated Learning with Explainable AI for Ransomware Detectionraises · addresses

Named by an AI from these papers' abstracts.

Field

Spotlight

Papers

Field

Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection

Spotlight

Recent papers

Adapting prior-data fitted networks for tabular anomaly detection

Papers

Topics in this field

Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection

Recent papers

Adapting prior-data fitted networks for tabular anomaly detection

Active contributors · 90 days

Activity · 12 weeks

Anomaly detectors

Open problems in Anomaly detectors