SAGE decomposes univariate time-series anomaly detection into four specialized LLM analyzers plus an evidence-grounded detector and supervisor, achieving the highest average performance on three benchmarks while using only normal data for in-context examples.
hub
Platt, John C
10 Pith papers cite this work, alongside 4,377 external citations. Polarity classification is still indexing.
10
Pith papers citing it
4,377
external citations · Crossref
hub tools
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
SET detects input-level backdoors in T2I diffusion models by learning a benign cross-attention response space from clean samples and flagging deviations under multi-scale perturbations.
Heat-kernel smoothing over weighted points on a compact manifold yields a scale-dependent geometric effective sample size that discounts nearby and duplicate particles.
Empirical evaluation on LID-DS-2021 shows CWE-level generalization of syscall anomaly detectors succeeds for CWE-307 (F1=0.6976 at FPR=0.05) but fails for CWE-89 and CWE-434 (F1<=0.21), with transfer strongly dependent on source normal-profile breadth.
Latent SDE generative model for anomaly detection in sparse irregular multivariate time series outperforms baselines on six benchmarks and stays robust under severe sparsity.
Introduces MADQI, a label-free composite metric combining ARC, PPS, SDS, and ECE to evaluate unsupervised anomaly detection in AIS vessel data, reporting 80.37% on tested datasets.
Regression-based features fed to a one-class SVM detect exposure-length changes in submarine cables from DAS vibration data, achieving F1 of 0.82 and correlation r=-0.83 in wave-tank tests with limited samples.
An unsupervised system-aware framework combines online detection with an LLM-augmented contextual digital twin to deliver real-time, interpretable anomaly diagnosis in industrial control systems.
AMAD is an end-to-end model using adversarial autoencoders and RNNs with attention for multiscale anomaly detection on time-evolving high-dimensional categorical data.
citing papers explorer
-
Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers
SAGE decomposes univariate time-series anomaly detection into four specialized LLM analyzers plus an evidence-grounded detector and supervisor, achieving the highest average performance on three benchmarks while using only normal data for in-context examples.
-
Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
SET detects input-level backdoors in T2I diffusion models by learning a benign cross-attention response space from clean samples and flagging deviations under multi-scale perturbations.
-
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds
Heat-kernel smoothing over weighted points on a compact manifold yields a scale-dependent geometric effective sample size that discounts nearby and duplicate particles.
-
From CVE to CWE: Syscall-Based HIDS Generalisation
Empirical evaluation on LID-DS-2021 shows CWE-level generalization of syscall anomaly detectors succeeds for CWE-307 (F1=0.6976 at FPR=0.05) but fails for CWE-89 and CWE-434 (F1<=0.21), with transfer strongly dependent on source normal-profile breadth.
-
Anomaly Detection for Sparse and Irregular Multivariate Time Series with Latent SDEs
Latent SDE generative model for anomaly detection in sparse irregular multivariate time series outperforms baselines on six benchmarks and stays robust under severe sparsity.
-
A Novel Evaluation Metric for Unsupervised Learning in AIS-Based Maritime Anomaly Detection: MADQI
Introduces MADQI, a label-free composite metric combining ARC, PPS, SDS, and ECE to evaluate unsupervised anomaly detection in AIS vessel data, reporting 80.37% on tested datasets.
-
Monitoring exposure-length variations in submarine power cables using distributed fiber-optic sensing
Regression-based features fed to a one-class SVM detect exposure-length changes in submarine cables from DAS vibration data, achieving F1 of 0.82 and correlation r=-0.83 in wave-tank tests with limited samples.
-
System-aware contextual digital twin for ICS anomaly diagnosis
An unsupervised system-aware framework combines online detection with an LLM-augmented contextual digital twin to deliver real-time, interpretable anomaly diagnosis in industrial control systems.
-
AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data
AMAD is an end-to-end model using adversarial autoencoders and RNNs with attention for multiscale anomaly detection on time-evolving high-dimensional categorical data.
- Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with nonconform