AI-Driven Dynamic Firewall Optimization Using Reinforcement Learning for Anomaly Detection and Prevention

• URL: http://arxiv.org/abs/2506.05356v1
• Date: Wed, 21 May 2025 17:05:33 GMT
• Title: AI-Driven Dynamic Firewall Optimization Using Reinforcement Learning for Anomaly Detection and Prevention
• Authors: Taimoor Ahmad,
• Abstract summary: This paper proposes a novel AI-driven dynamic firewall optimization framework.<n>It autonomously adapts and updates firewall rules in response to evolving network threats.<n>Results demonstrate significant improvements in detection accuracy, false positive reduction, and rule update latency.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The growing complexity of cyber threats has rendered static firewalls increasingly ineffective for dynamic, real-time intrusion prevention. This paper proposes a novel AI-driven dynamic firewall optimization framework that leverages deep reinforcement learning (DRL) to autonomously adapt and update firewall rules in response to evolving network threats. Our system employs a Markov Decision Process (MDP) formulation, where the RL agent observes network states, detects anomalies using a hybrid LSTM-CNN model, and dynamically modifies firewall configurations to mitigate risks. We train and evaluate our framework on the NSL-KDD and CIC-IDS2017 datasets using a simulated software-defined network environment. Results demonstrate significant improvements in detection accuracy, false positive reduction, and rule update latency when compared to traditional signature- and behavior-based firewalls. The proposed method provides a scalable, autonomous solution for enhancing network resilience against complex attack vectors in both enterprise and critical infrastructure settings.

Related papers

• Intrusion Detection System Using Deep Learning for Network Security [0.6554326244334868]
  This paper proposes an experimental evaluation of IDS models based on deep learning techniques.<n>We focus on the classification of network traffic into malicious and benign categories.<n>Among the tested models, the best achieved an accuracy of 96 percent.
  arXiv  Detail & Related papers  (2025-05-09T06:04:58Z)
• Adaptive Cybersecurity: Dynamically Retrainable Firewalls for Real-Time Network Protection [4.169915659794567]
  This research introduces "Dynamically Retrainable Firewalls"<n>Unlike traditional firewalls that rely on static rules to inspect traffic, these advanced systems leverage machine learning algorithms to analyze network traffic pattern dynamically and identify threats.<n>It also discusses strategies to improve performance, reduce latency, optimize resource utilization, and address integration issues with present-day concepts such as Zero Trust and mixed environments.
  arXiv  Detail & Related papers  (2025-01-14T00:04:35Z)
• Multi-agent Reinforcement Learning-based Network Intrusion Detection System [3.4636217357968904]
  Intrusion Detection Systems (IDS) play a crucial role in ensuring the security of computer networks. We propose a novel multi-agent reinforcement learning (RL) architecture, enabling automatic, efficient, and robust network intrusion detection. Our solution introduces a resilient architecture designed to accommodate the addition of new attacks and effectively adapt to changes in existing attack patterns.
  arXiv  Detail & Related papers  (2024-07-08T09:18:59Z)
• Dynamics-aware Adversarial Attack of Adaptive Neural Networks [75.50214601278455]
  We investigate the dynamics-aware adversarial attack problem of adaptive neural networks. We propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient. Our LGM achieves impressive adversarial attack performance compared with the dynamic-unaware attack methods.
  arXiv  Detail & Related papers  (2022-10-15T01:32:08Z)
• Downlink Power Allocation in Massive MIMO via Deep Learning: Adversarial Attacks and Training [62.77129284830945]
  This paper considers a regression problem in a wireless setting and shows that adversarial attacks can break the DL-based approach. We also analyze the effectiveness of adversarial training as a defensive technique in adversarial settings and show that the robustness of DL-based wireless system against attacks improves significantly.
  arXiv  Detail & Related papers  (2022-06-14T04:55:11Z)
• Mixture GAN For Modulation Classification Resiliency Against Adversarial Attacks [55.92475932732775]
  We propose a novel generative adversarial network (GAN)-based countermeasure approach. GAN-based aims to eliminate the adversarial attack examples before feeding to the DNN-based classifier. Simulation results show the effectiveness of our proposed defense GAN so that it could enhance the accuracy of the DNN-based AMC under adversarial attacks to 81%, approximately.
  arXiv  Detail & Related papers  (2022-05-29T22:30:32Z)
• Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network [75.1236305913734]
  We investigate the dynamics-aware adversarial attack problem in deep neural networks. Most existing adversarial attack algorithms are designed under a basic assumption -- the network architecture is fixed throughout the attack process. We propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient.
  arXiv  Detail & Related papers  (2021-12-17T10:53:35Z)
• A Novel Online Incremental Learning Intrusion Prevention System [2.5234156040689237]
  This paper proposes a novel Network Intrusion Prevention System that utilise a SelfOrganizing Incremental Neural Network along with a Support Vector Machine. Due to its structure, the proposed system provides a security solution that does not rely on signatures or rules and is capable to mitigate known and unknown attacks in real-time with high accuracy.
  arXiv  Detail & Related papers  (2021-09-20T13:30:11Z)
• Automated Adversary Emulation for Cyber-Physical Systems via Reinforcement Learning [4.763175424744536]
  We develop an automated, domain-aware approach to adversary emulation for cyber-physical systems. We formulate a Markov Decision Process (MDP) model to determine an optimal attack sequence over a hybrid attack graph. We apply model-based and model-free reinforcement learning (RL) methods to solve the discrete-continuous MDP in a tractable fashion.
  arXiv  Detail & Related papers  (2020-11-09T18:44:29Z)
• Improved Adversarial Training via Learned Optimizer [101.38877975769198]
  We propose a framework to improve the robustness of adversarial training models. By co-training's parameters model's weights, the proposed framework consistently improves robustness and steps adaptively for update directions.
  arXiv  Detail & Related papers  (2020-04-25T20:15:53Z)
• Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning [40.989393438716476]
  Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs are often enough to change network-based decisions, which was recently shown to cause an autonomous vehicle to swerve into another lane. This work leverages research on certified adversarial robustness to develop an online certifiably robust for deep reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2020-04-11T21:36:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.