让下一篇重要论文，不再错过。

原文摘要

Cyberattacks against power systems increasingly exploit industrial communication and control dependencies arising from distributed energy resources (DER), remote management, and market-based incentives. Progress on intrusion detection is constrained by a lack of public datasets that align operational technology (OT) network telemetry with physical measurements and control context. Data4Cyber is a labeled cyber-physical dataset recorded in a laboratory distribution management system (DMS) for self-consumption optimization with photovoltaic generation, battery storage, controllable loads, and substation metering. It captures synchronized process measurements, controller context, price incentives, and packet captures (Modbus/TCP and MQTT) across one benign baseline and six attack scenarios spanning protocol-semantic Modbus manipulation, man-in-the-middle (MitM) false-data injection, and MQTT price manipulation. Its fixed 1 s time base, phase-resolved labels, and state-oriented representation support temporally blocked stateful-detector evaluation. Baseline results show that high recall alone is insufficient: several detectors achieve sensitivity through alarm saturation. Context-driven attacks require process-aware interpretation rather than single-channel thresholding.