Conference
Similar papers
A Graph-Based Approach for Mapping Kernel-Level Telemetry to MITRE ATT&CK
Results show that local inference over graph-based behavioral descriptions can make automated ATT&CK mapping from kernel-level telemetry operationally viable, without compromising data confidentiality.
Matteo Lupinacci, Luigi Arena, Francesco Blefari et al.
· 0 citations
BEACON: Behavior-Anchored Cross-Source Knowledge Graph Construction for Cyber Threat Intelligence
BEACON is an LLM-driven framework for cross-source CTI knowledge graph construction that constructs and releases two human-annotated datasets from 34 sources and outperforms all baselines by at least 23% and 9%, respectively.
Chang-Ze Li, Yu-Tong Cheng, Tsania Camila Finnisa et al.
· 0 citations
Open access
Aug 2026
CT-EWS: graph-centric early warning for multi-protocol cyber campaigns using long-memory forecasting and explainable attribution
Together, relational graph modeling, long-memory forecasting, explainability, and ATT&CK-aligned context turn passive honeypot infrastructure into a proactive early warning capability.
R. Sehgal, Rakesh Matam
· Frontiers of Computer Scienc... · 0 citations
Reasoning Topology Matters: A Controlled Study of LLM-Based Cybersecurity Analysis
Large Language Models (LLMs) are increasingly used in cybersecurity, where accurate analysis often requires multi-step and context-dependent reasoning over complex and heterogeneous data. However, existing prompting approaches typically focus on eliciting reasoning without explicitly considering how intermediate reason...
Ji-Ling Zhou, Aisvarya Adeseye, Antti Hakkala et al.
· 0 citations
EASE-CloudNet: Adaptive Safety Alignment for Edge–Cloud SLMs via GNN-Informed Selective Reasoning and Multi-Objective Distillation
EASE-CloudNet is a two-phase safety-alignment framework for generative small language models (SLMs) deployed on resource-constrained edge nodes that formulate deployment cost as a differentiable gate-conditioned expectation, so measured latency and energy constants affect the router through its reasoning probability.
Jie-Jie Shi, Hua-Cai Chen, Liang-Ying Han
· Electronics · 0 citations
Open access
Aug 2026
Ontology-Driven Modeling and Semantic Integration of Attack, Protection, and Risk Domains in Electric Vehicle Charging Systems
EVCS-SecOnt enhances the interpretability, reusability, and explainability of EVCS cybersecurity management by bridging operational data with semantic intelligence, providing a semantic foundation for next-generation e-mobility and smart charging infrastructures.
Talea Huraysi, Ohud Alsadi, T. Pamulapati et al.
· Electronics · 0 citations