arXiv:2608. 04041v1 Announce Type: new Abstract: Open-World Learning (OWL) pipelines for oil well anomaly detection have recently been shown to combine autoencoder-based detection, multiclass classification, and Mahalanobis-based novelty detection on the public 3W dataset.
arXiv:2605. 22779v2 Announce Type: replace-cross Abstract: Production systems generate millions of log lines daily, yet most anomaly detectors operate at the session or window-level, flagging groups of lines rather than identifying the specific message responsible.
arXiv:2608. 05685v1 Announce Type: new Abstract: Most public benchmarks for machine-condition monitoring come from test rigs, where faults are induced on purpose and every event is known.
The paper introduces Trustworthy RAG, an evaluation agent designed to detect misinformation and knowledge poisoning in Retrieval-Augmented Generation systems. It combines natural language inference verification, a five-signal poison detector, and a weighted Trust Index to assess the reliability of retrieved content. Experiments on multiple LLMs show high accuracy and precision, with the agent effectively blocking unsafe advice in a secure-coding assistant scenario.
arXiv:2607. 13081v1 Announce Type: cross Abstract: We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion.
arXiv:2606. 03453v1 Announce Type: cross Abstract: Vulnerability disclosure volumes now far exceed organizational assessment capacity, yet three adjacent research communities (proof-of-concept generation, vulnerability prioritization, and detection rule engineering) operate largely in isolation.
arXiv:2609.06835v1 Announce Type: cross Abstract: Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these s...
arXiv:2605. 06890v3 Announce Type: replace Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control.
We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion. We first introduce the NSFA taxonomy, which organizes 185 risk variants into a CIA-triad-grounded hierarchy and is cross-validated against three well-established OWASP guidelines.
arXiv:2606. 28467v1 Announce Type: cross Abstract: Appliance-level energy monitoring in office buildings produces noisy alerts that non-expert facility managers struggle to use.
MAADBench is a refreshable benchmark for anomaly detection in multi‑agent systems powered by large language models. It addresses the challenge of keeping benchmarks current by sampling and coupling generative tasks, generating trace data under configurable LLM backbones, and automatically providing deterministic step‑level labels. The authors evaluated 25 anomaly‑detection methods on 5,200 labeled traces, finding that existing approaches depend heavily on supervision, struggle with subtle MAS‑specific anomalies, and lack robustness across different LLM backbones.
arXiv:2607. 19899v1 Announce Type: cross Abstract: Disagreement-triggered escalation can create a structural blind spot in multi-agent arbitration: as base learners improve, they tend to converge, weakening safety monitoring where correlated failures concentrate.
HydroJEV is a training‑free, one‑second model that classifies SCADA alarms in water distribution networks into cyberattack, physical fault, normal transient, or faulty sensor. In a benchmark on the C‑Town EPANET network, HydroJEV matched a hand‑written rule tree and outperformed a supervised classifier, especially when few labeled events were available, while being 20‑40 times faster than large language models. When combined with a rule tree gate, it reduced the need for human review by about a third without sacrificing accuracy.