AINeutralarXiv – CS AI · 18h ago6/10
🧠
RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks
Researchers introduce RecurGuard, a runtime monitoring system that defends reasoning-capable large language models against prompt injection attacks designed to exhaust generation budgets on decoy tasks. The defense detects 99% of such attacks while maintaining minimal false positives, though adaptive adversaries can partially evade detection by using topical rather than semantic attacks.