The paper introduces Jev-GAD, a training‑free generalist graph anomaly detection framework that combines complementary structural, attribute, and neighborhood evidence with a single frozen pretrained language model for anomaly assessment. It transforms heterogeneous statistics into graph‑relative percentiles and uses a semantic Graph‑to‑State (G2S) transformation to feed evidence into a non‑generative decision readout, fusing the resulting scores with four statistical measures. Experiments on seven benchmark datasets show Jev‑GAD achieving high AUROC (89.18%) and AUPRC (52.40%) scores, demonstrating the effectiveness of pretrained decision readout and semantic evidence grounding.
By Xinyu Zhao, Qingyun Sun, Ziwei Zhang, Tianchen Zhu, Daqing Li, Jianxin Li
arXiv:2507.12295v2 Announce Type: replace-cross
Abstract: Text anomaly detection is a critical task in natural language processing (NLP), with applications spanning fraud detection, misinformation id...
By Feng Xiao, Jicong Fan
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.
By Kevin Wilkinghoff, Zheng-Hua Tan
arXiv:2602.06859v3 Announce Type: replace-cross
Abstract: Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to e...
By Xinyu Zhao, Qingyun Sun, Jiayi Luo, Xingcheng Fu, Jianxin Li
arXiv:2608. 10699v1 Announce Type: cross Abstract: Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-world anomaly detection spanning large language model security, social network moderation, and cyber threat identification.
By Ziyan Wang, Liwen Wu, Cheng Xie, Song Gao, Zhenli He, Xin Jin
FoundAna is a GNN‑assisted foundation model designed for graph anomaly detection across diverse datasets. It combines a GNN component with a transformer encoder enhanced by four positional encodings to capture both local and global structure, using reconstruction errors as anomaly scores. Experiments on nine benchmark datasets from financial, social, and citation networks show that FoundAna consistently outperforms state‑of‑the‑art baselines.
By Suprim Nakarmi, Chahana Dahal, Yue Zhao, Junggab Son, Zuobin Xiong
AnomalyGFM is a graph foundation model designed for zero- and few-shot anomaly detection in graphs. It learns graph‑agnostic normal and abnormal prototypes by aligning data‑independent class representations with node representation residuals, enabling consistent abnormality measurement across diverse graph datasets. Experiments on 11 real‑world GAD datasets show that AnomalyGFM outperforms state‑of‑the‑art methods in both zero‑shot and few‑shot settings.
By Hezhe Qiao, Chaoxi Niu, Ling Chen, Guansong Pang
arXiv:2602. 20019v2 Announce Type: replace-cross Abstract: Dynamic graph anomaly detection is critical for many real-world applications but remains challenging due to the scarcity of labeled anomalies.
By Yuxing Tian, Yiyan Qi, Fengran Mo, Weixu Zhang, Jian Guo, Jian-Yun Nie
arXiv:2609.08200v1 Announce Type: new
Abstract: Token-level text anomaly detection, as an emerging trend of text anomaly detection, moves beyond coarse-grained document-level detection by localizing...
By Kehan Yan, Yue Tan, Qingfeng Chen, Shiyuan Li, Yu Zheng, Yixin Liu
RINSE (Robust Iterative Normality Self-Estimation) is a gradient‑free framework for zero‑shot graph anomaly detection that keeps a source‑trained detector fixed while iteratively estimating target normality, calibrating representations, and assessing evidence reliability on unseen target graphs. It identifies a reliable subset of low‑residual target nodes to build a trimmed target‑aware normality model and fuses complementary anomaly evidence through reliability‑gated rank fusion and encoder ensembling. Across eight unseen target graphs, RINSE achieves the highest average AUPRC under two preprocessing protocols, with ablation and sensitivity analyses supporting its combined design.
By Taufikur Rahman Fuad, Md Abrar Jahin, Amir Hussain
arXiv:2611.06441v1 Announce Type: new
Abstract: Multivariate time series anomaly detection (MTSAD) relies on modeling both temporal dynamics and inter-sensor dependencies to identify complex system f...
By Zhuangyan Hu, Zhuoxuan Liang, Wei Li, Xiaohua Jia, Moustafa Youssef, Sumi Helal
arXiv:2510. 02014v3 Announce Type: replace Abstract: Graph anomaly detection (GAD) has attracted growing interest for its crucial ability to uncover irregular patterns in broad applications.
By Guolei Zeng, Hezhe Qiao, Guoguo Ai, Jinsong Guo, Guansong Pang