CyberMaskQA is a new privacy-aware QA benchmark for cybersecurity that annotates private entities in realistic organizational scenarios with causal dependencies to jointly evaluate reasoning accuracy and masking performance.
Examining the factors that impact the severity of cyberattacks on critical infrastructures,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2representative citing papers
ProvICS is an open-source multimodal provenance dataset for ICS intrusion detection, combining host/PLC provenance graphs, decoded Modbus traffic, and physical telemetry from a HIL testbed, validated by baseline cross-modal fusion achieving F1=0.913 on 32 attack events.
citing papers explorer
-
CyberMaskQA: A Privacy-Aware Benchmark for Evaluating Large Language Models in Cybersecurity Question Answering
CyberMaskQA is a new privacy-aware QA benchmark for cybersecurity that annotates private entities in realistic organizational scenarios with causal dependencies to jointly evaluate reasoning accuracy and masking performance.
-
ProvICS: A Provenance-based Intrusion Detection for Industrial Control Systems
ProvICS is an open-source multimodal provenance dataset for ICS intrusion detection, combining host/PLC provenance graphs, decoded Modbus traffic, and physical telemetry from a HIL testbed, validated by baseline cross-modal fusion achieving F1=0.913 on 32 attack events.