# DeepADMR: A Deep Learning based Anomaly Detection for MANET Routing

## TL;DR

DeepADMR is a real-time neural anomaly detection system for DRL-based MANET routing, enhancing deployment safety by identifying unexpected behaviors under various network disruptions.

## Contribution

It introduces a novel neural anomaly detector for DRL-based MANET routing, utilizing TD-errors and non-parametric statistics for real-time anomaly detection.

## Key findings

- Effective detection of anomalies during channel disruptions
- Robust performance in high mobility scenarios
- Successful operation beyond trained network sizes

## Abstract

We developed DeepADMR, a novel neural anomaly detector for the deep reinforcement learning (DRL)-based DeepCQ+ MANET routing policy. The performance of DRL-based algorithms such as DeepCQ+ is only verified within the trained and tested environments, hence their deployment in the tactical domain induces high risks. DeepADMR monitors unexpected behavior of the DeepCQ+ policy based on the temporal difference errors (TD-errors) in real-time and detects anomaly scenarios with empirical and non-parametric cumulative-sum statistics. The DeepCQ+ design via multi-agent weight-sharing proximal policy optimization (PPO) is slightly modified to enable the real-time estimation of the TD-errors. We report the DeepADMR performance in the presence of channel disruptions, high mobility levels, and network sizes beyond the training environments, which shows its effectiveness.