Work

Towards an Unsupervised Reward Function for a Deep Reinforcement Learning Based Intrusion Detection System

Year: 2024

Type: conference-paper

Abstract: Intrusion detection systems (IDS) based on deep learning have proven successful, but struggle to learn continuously and detect new attacks over time due to a supervised label-based reward function. In this article, we introduce an unsupervised Deep Double Q Learning (DDQL) method that aims to detect attacks and learn new behaviors through an unsupervised reward function leveraging a normality score inspired by car traffic anomaly detection.

Source: Cyber Security in Networking Conference (CSNet)

DOI: 10.1109/csnet64211.2024.10851732

Authors: Bilel Saghrouchni, Frédéric Le Mouël, Bogdan Szanto

Institutions: Institut national de recherche en sciences et technologies du numérique, Center of Innovation in Telecommunications and Integration of Service, Institut National des Sciences Appliquées de Lyon

Language: English

Topic: Network Security and Intrusion Detection

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4405515909

FWCI: 0.443

Cites: 18

Cited by: 1

Related to: 10