A Digital Twin to Improve Cyber-Social Impact

A Digital Twin to Improve Cyber-Social Impact

arXiv:2610.28430v1 Announce Type: cross Abstract: The increasing complexity of Industrial Control Systems (ICS) and their integration with IT infrastructures has significantly expanded the cyber thre...

CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

arXiv:2606. 13079v1 Announce Type: cross Abstract: Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must not cross.

Polar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization and Mitigation

arXiv:2610.07298v1 Announce Type: cross Abstract: Cyber threat analysis increasingly depends on evidence distributed across vendor advisories, vulnerability databases, and threat intelligence sources...

From Chasing Ghosts to Missed Attacks: Perspectives and Perceptions of SOC Practitioners on LLM Integration, Risks, and Readiness

The paper investigates how Security Operations Center (SOC) analysts perceive the integration of Large Language Models (LLMs) into their workflows. Through 25 interviews and interactive scenarios, the authors identify 15 LLM use cases across six functional categories, noting that while LLMs are useful for automating repetitive tasks, they are not yet suitable for high‑impact incident analysis due to limitations in technical depth, context awareness, and organization‑specific knowledge. Despite these concerns, practitioners show a strong willingness to adopt LLMs, driven by competitive pressure and a desire for operational efficiency.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

arXiv:2607. 25379v1 Announce Type: new Abstract: Cyber-capable AI agents combine language models with tools, memory, and execution en- vironments to perform multi-step offensive-security tasks.