A multi-layer cloud IDS uses per-layer ML detection, learned confidence gates, Chroma memory, and LLM escalation with Q-learning adaptive calibration to cut LLM calls by 58.78% while reporting 88.68% overall accuracy.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
A Multi-Layer Cloud-IDS Pipeline with LLM and Adaptive Q-Learning Calibration
A multi-layer cloud IDS uses per-layer ML detection, learned confidence gates, Chroma memory, and LLM escalation with Q-learning adaptive calibration to cut LLM calls by 58.78% while reporting 88.68% overall accuracy.
- OHP-RL: Online Human Preference as Guidance in Reinforcement Learning for Robot Manipulation