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.
CurriculumPT: LLM-based multi-agent autonomous penetration testing with curriculum- guided task scheduling.Applied Sciences, 15(16): 9096
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
support 1representative citing papers
AI-emulated APTs compromise enterprise hosts and weaponize defender tools in 8/10 trials while military ranges resist, indicating TTP attribution fails when agents can be scaffolded to mimic threat actors.
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.
-
Synthetic APTs: the Collapse of TTP-Based Attribution
AI-emulated APTs compromise enterprise hosts and weaponize defender tools in 8/10 trials while military ranges resist, indicating TTP attribution fails when agents can be scaffolded to mimic threat actors.