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...
arXiv:2609.22136v1 Announce Type: cross Abstract: Text anomaly detection, the task of identifying text instances that deviate from normal language patterns, is crucial for language-driven application...
arXiv:2512. 10092v2 Announce Type: replace Abstract: Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data.
The paper benchmarks static embedding models—Word2Vec, FastText, and Doc2Vec—for detecting anomalous HTTP requests using a single‑class classification framework. It introduces HEDA, a modular pipeline that trains both embeddings and detectors solely on benign traffic in an unsupervised setting. Experiments on synthetic and real datasets show that FastText embeddings consistently yield high detection rates with controlled false positives.
GLASS is a graph‑level anomaly detection framework that aligns graph and language representations on a unit hypersphere to achieve cross‑domain transferability. It constructs a Graph Descriptor Prompt to encode local, global, and semantic graph properties, and uses a multi‑slice soft cosine objective to unify graph and text embeddings. Anomaly scoring is performed via spherical density estimation with von Mises‑Fisher kernels, enabling zero‑shot detection and few‑shot adaptation across twelve benchmarks and three meta‑domains, outperforming recent GLAD baselines.
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.
The paper introduces MOSAIC, a large adversarial benchmark for detecting AI-generated text, and presents NeuroStat, a new framework that combines token‑level probabilistic logits with deep semantic hidden states from a single language model. NeuroStat fuses these signals via Macro‑State Residual Modulation and uses orthogonal and contrastive losses to learn complementary representations. Experiments show that NeuroStat outperforms existing methods on MOSAIC, achieving superior robustness against adversarial attacks.
The paper introduces a deep positive‑unlabeled anomaly detection framework that combines positive‑unlabeled learning with deep models such as autoencoders and deep support vector data descriptions. It addresses the issue of contaminated unlabeled data by approximating anomaly scores for normal data using both unlabeled and labeled anomaly samples, allowing training without labeled normal data. The authors provide a theoretical generalization error bound and demonstrate improved detection performance over existing methods on several datasets.
The paper investigates how different adaptation strategies, model architectures, parameter scales, and quantization settings influence the performance, efficiency, and robustness of large language models (LLMs) for log anomaly detection. Across three public log datasets, the study finds that adaptation strategies lead to significant performance variations, model scaling offers dataset‑dependent gains, and models with similar accuracy can differ markedly in computational cost. Low‑bit quantization largely preserves detection performance, and the authors also assess robustness to structural, semantic, and label noise at varying perturbation levels.
arXiv:2408. 16028v4 Announce Type: replace-cross Abstract: Supervised-learning-based vulnerability detectors often fall short due to limited labelled training data.
arXiv:2608. 04753v1 Announce Type: new Abstract: Attention layers are the backbone of today's most powerful and impactful models.
arXiv:2607.00171v2 Announce Type: replace Abstract: Text embeddings are standard for semantic similarity tasks, yet their evaluation remains an open challenge. Current benchmarks are static, cover on...