Skip to content
Log in
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition

NEXUS-DQN★: noisy and experience-prioritized unified security dueling Q-network system for intelligent and optimized network traffic intrusion detection

Firas Saidi
Aug 2026 · Cluster Computing · Vol 29 · 0 citations · 36 references

TL;DR

NEXUS-DQN★ is proposed, a novel Deep Reinforcement Learning framework that formulates intrusion detection as a sequential decision-making problem within a Markov Decision Process (MDP) and enhances the conventional Deep Q-Network by integrating Noisy Linear Layers (NLL) for efficient exploration and an intrusion-aware reward shaping mechanism to optimize long-term defensive policies.

DOI Semantic Scholar
View source

Similar papers

Open access Sep 2026

Graph-guided contrastive transformer architecture for robust and explainable network intrusion detection

A new graph-guided contrastive transformer-based intrusion detection system (GCT-IDS) which aims at improving detection accuracy and robustness and preserving real-time feasibility is presented.

Archana Jayapal, Kamalakkannan Somasundaram, Arun Kumar Ramamoorthy · 0 citations
Preprint Aug 2026

Machine Learning-Based Cyber Defense for Cloud Infrastructure: An Adaptive Deep Q-Network Architecture for Intelligent Intrusion Detection and Automated Threat Mitigation

The framework achieved 99.54% attack mitigation rate, demonstrating strong adaptive and real-time defensive capabilities and demonstrating the potential of reinforcement learning as a powerful and scalable approach for autonomous cybersecurity in modern cloud environments.

Md Yassir Mottalib, M. Yousuf, Eklachur Rahman Bhuiyan et al. · 0 citations
#graph neural networks Open access Oct 2026

Graph-Aware Reinforcement Learning for Adaptive APT Threat Hunting in Dynamic Enterprise Networks

Advanced Persistent Threats (APTs) are particularly challenging for enterprise intrusion detection because they are time-evolving, distributed, and difficult to detect under changing network conditions. Conventional machine-learning-based intrusion detection systems (IDSs) often rely on node-level features and may be v...

Bahar Memarpour, Kimia Memarpour, Kimia Shirini et al. · 0 citations
Open access 2026

Adversarial Asymmetric Agents for Network Intrusion Detection Using Deep Reinforcement Learning

Machine learning-based network intrusion detection systems (NIDS) increasingly operate in environments where adversaries can adapt their behavior in response to deployed defenses. However, most empirical IDS studies evaluate defenders against static, dataset-defined attack distributions and do not explicitly model an a...

Curtis Rookard · 0 citations
Open access Aug 2026

A PSO-Optimized gradient boosting framework for flow-based DDoS detection in software-defined networks

Overall, the findings indicate that PSO-enhanced ensemble learning provides an effective and computationally efficient approach for improving DDoS detection in SDN environments, offering a practical balance between accuracy, robustness, and deployment feasibility.

I. A. Mahar, Libing Wu, G. A. Rahu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.