Real-Time Adversarial Defense via Buffer-Aware Reinforcement Learning
Authors:
Open Access
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 148830-148843
Abstract
No abstract availableFunding Information
- respective institutions in conducting this research
- agency in the public, commercial, or not-for-profit sectors
This publication has 34 references indexed in Scilit:
- Detecting adversarial evasion in deep learning intrusion detection systems using explainable AIInternational Journal of Information Security, 2026
- Adversarial guided diffusion models for adversarial purificationNeural Networks, 2025
- Interpretable adversarial example detection via high-level concept activation vectorComputers & Security, 2024
- Zero time waste in pre-trained early exit neural networksNeural Networks, 2023
- Model update for intrusion detection: Analyzing the performance of delayed labeling and active learning strategiesComputers & Security, 2023
- Deep Reinforcement Learning in the Advanced Cybersecurity Threat Detection and ProtectionInformation Systems Frontiers, 2022
- Learn to adapt: Robust drift detection in security domainComputers and Electrical Engineering, 2022
- Cyber-security and reinforcement learning — A brief surveyEngineering Applications of Artificial Intelligence, 2022
- Adversarial Deep Reinforcement Learning Based Adaptive Moving Target Defense2020
- Toward Proactive, Adaptive Defense: A Survey on Moving Target DefenseIEEE Communications Surveys & Tutorials, 2020