Unlearning to Protect: A Distilled Reinforcement Learning Framework with Privacy-Preserving Feature Unlearning and XAI for IoT Security

Jul 16, 2026

Botnets enable DDoS, data theft, and service disruptions on IoT devices that often lack built-in traffic filtering. Existing AI detectors are constrained by heavy deployment needs and the absence of unlearning, which would remove sensitive or outdated features without retraining. DiRLU proposes a lightweight A2C-based teacher–student distillation scheme, plus post-hoc reversible feature unlearning that preserves accuracy. XAI with LIME improves decision transparency, while 25% dataset usage strengthens the teacher model and achieves high accuracy and F1 with low FLOPS, supporting GDPR-aligned right-to-be-forgotten security.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

Abstract

Introduction

Contribution

Unlearning to Protect: A Distilled Reinforcement Learning Framework with Privacy-Preserving Feature Unlearning and XAI for IoT Security Md. Nahid Hasan and Md. Golam Rabiul Alam Department of Computer Science and Engineering, BRAC University arXiv :2607 .07635v2 [ cs .CR] 9 Jul 2026 Abstract—Botnets pose a significant cybersecurity threat, enabling attacks such as DDoS, data theft, and service disruptions on IoT devices. These devices often lack built-in botnet traffic filtering, leaving them highly exposed. Existing AI-based solutions improve detection capabilities but have limitations:(i) they are too heavy for IoT deployment, and (ii) they lack unlearning capabilities to forget sensitive or outdated features without retraining. To address these challenges, we propose DiRLU, a lightweight, reinforcement learning driven framework, while ensuring privacy by selectively unlearning sensitive or outdated features without requiring retraining. The framework leverages knowledge distillation to transfer knowledge from a teacher model into a lightweight student model, with both models trained using A2C. A post-hoc unlearning mechanism modifies weights to remove targeted features, while restored features show negligible performance loss, confirming reversibility. Unlike many benchmark models that used only 5% of the BoT-IoT dataset, this research leverages 25%, allowing us to develop a strong teacher model. Both the teacher and student models were trained using the A2C reinforcement learning algorithm, achieving impressive results, with the student model achieving 99.60% accuracy anda 99.80% F1 score. To enhance transparency, we integrated Explainable AI (XAI), particularly LIME, which helps interpret the model’s decisions and identify the key features influencing its predictions. Moreover, DiRLU requires only 2,370 FLOPS, approximately 3.87× more efficient than the state-of-the-art model, highlighting its efficiency for edge deployment. DiRLU combines efficiency with privacy, aligning with GDPR standards (right to be forgotten) to provide practical and scalable IoT security solution. Index Terms—Botnet, Reinforcement Learning, Feature Unlearning, Knowledge Distillation, XAI, A2C, Security & Privacy I. INTRODUCTION ROBOT network, in short, Botnet, is a computer network infected by malware under the control of an attacking party known as Bot Herder [1] . Computers that are under the control of attackers are called bots. Attackers having remote access to computers through bots can read, update, and even decrypt sensitive data for financial gain or reputational loss. Controlling compromised devices over the networks remotely is a vital part for attackers. Bots are controlled directly or indirectly in two modes: Centralized client-server models and Decentralized peer-to-peer models. In 2016, Mirai botnet attack was on Dyn, an Internet performance management company. During the outage, the estimated losses were 22,000 US dollars per minute [2] . Modern malware, ransomware, and botnets pose serious cybersecurity risks to individuals, businesses, and governments. Malicious content implants individuals’ or organizations’devices in diverse ways, often exploiting human error and system vulnerabilities. Attackers typically start with phishing emails or websites, misleading victims into clicking malicious hyperlinks or downloading infected attachments. Once inside, botnets can spread across networks, gaining control of devices to carry out intended vicious activities. These infected systems are then used to deploy ransomware. Ransomware is malicious software or program that encrypts a victim’s data, making it inaccessible until a ransom is paid to the attacker. Nevertheless, ransomware attacks can lead to a significant service outage for an organization. Attackers send commands to bots for launching attacks such as DDoS, Reconnaissance, Information Theft, Service Scan, Keylogging, etc. When cyber threats such as DDoS, recon

FAQs

What cybersecurity problems does the document focus on for IoT devices?

The document focuses on botnets that can drive DDoS, information theft, reconnaissance, service scanning, and other disruptions by exploiting IoT devices that often lack adequate traffic filtering.

How does DiRLU reduce model size while maintaining detection performance?

DiRLU uses knowledge distillation to transfer knowledge from a teacher model to a lightweight student model, with both trained using the A2C reinforcement learning algorithm.

What is privacy-preserving feature unlearning in DiRLU?

DiRLU includes a post-hoc unlearning mechanism that modifies weights to remove targeted sensitive or outdated features without requiring retraining, while restored features show negligible performance loss.

Jul 16, 2026

Upload by Evangeline