Dynamic Cyber Ranges with LLM defender agents reduce attacker success to 0-55% and preserve evaluation headroom as models advance by using comparable capabilities on both sides.
Toward cybersecurity-expert small language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
MinervaRL applies reinforcement learning with verifiable rewards from CTI standards to improve LLM structured output performance by 15.8 points over base models across 12 benchmarks.
A hybrid LLM-RL red teaming framework generates adaptive attack campaigns in simulated enterprise networks to evaluate the robustness of AI-enabled SOAR systems.
citing papers explorer
-
Dynamic Cyber Ranges
Dynamic Cyber Ranges with LLM defender agents reduce attacker success to 0-55% and preserve evaluation headroom as models advance by using comparable capabilities on both sides.
-
Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs
MinervaRL applies reinforcement learning with verifiable rewards from CTI standards to improve LLM structured output performance by 15.8 points over base models across 12 benchmarks.
-
A Red Teaming Framework for Evaluating Robustness of AI-enabled Security Orchestration, Automation, and Response Systems
A hybrid LLM-RL red teaming framework generates adaptive attack campaigns in simulated enterprise networks to evaluate the robustness of AI-enabled SOAR systems.