arXiv:2607. 26201v1 Announce Type: cross Abstract: Security operations centers rely on anomaly detection systems to flag suspicious events.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper introduces ExCYDER, an explainable AI framework for anomaly detection in Distributed Energy Resource (DER) networks. It combines LightGBM with SHAP to self-verify alerts, ensuring that each detection aligns with feature‑attribution evidence. Experiments on a realistic DNP3 dataset show over 98% detection accuracy, 44.6% rule‑SHAP consistency, 14.5 ms SHAP latency per alert, and minimal confidence deviation, while distinguishing coherent from inconsistent alerts without sacrificing accuracy.
arXiv:2608. 11679v1 Announce Type: new Abstract: Digital twins are increasingly used to monitor and simulate the behavior of cyber-physical systems.
arXiv:2606. 28923v1 Announce Type: new Abstract: Detecting security threats in an organization's cloud computing environment has become necessary due to the increased reliance on cloud infrastructure.
The article proposes a structured framework of behavioral indicators that could signal a progression toward potentially catastrophic threats from AI systems. Drawing on established methods from cybersecurity and national security, it defines clear metrics, indicators, and thresholds across multiple dimensions of AI capability and behavior. The framework is intended to enable researchers and policymakers to implement evidence‑based monitoring protocols for rogue AI progression.
arXiv:2603. 21194v2 Announce Type: replace-cross Abstract: Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities.
arXiv:2606. 31567v1 Announce Type: cross Abstract: Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety.