Enhancing Adversarial Robustness of IoT Intrusion Detection via SHAP-Based Attribution Fingerprinting

TL;DR

This paper introduces a novel IoT intrusion detection approach that uses SHAP-based attribution fingerprinting to improve robustness against adversarial attacks, while also enhancing interpretability and trust in the system.

Contribution

The paper presents a new adversarial detection model leveraging SHAP attribution fingerprints to strengthen IoT IDS against evasion and manipulation attacks.

Findings

Significantly outperforms existing methods in detecting adversarial attacks on IoT data

Enhances model robustness and interpretability through SHAP-based explanations

Improves trust in IoT security systems with explainable AI techniques

Abstract

The rapid proliferation of Internet of Things (IoT) devices has transformed numerous industries by enabling seamless connectivity and data-driven automation. However, this expansion has also exposed IoT networks to increasingly sophisticated security threats, including adversarial attacks targeting artificial intelligence (AI) and machine learning (ML)-based intrusion detection systems (IDS) to deliberately evade detection, induce misclassification, and systematically undermine the reliability and integrity of security defenses. To address these challenges, we propose a novel adversarial detection model that enhances the robustness of IoT IDS against adversarial attacks through SHapley Additive exPlanations (SHAP)-based fingerprinting. Using SHAP's DeepExplainer, we extract attribution fingerprints from network traffic features, enabling the IDS to reliably distinguish between clean and adversarially perturbed inputs. By capturing subtle attribution patterns, the model becomes more resilient to evasion attempts and adversarial manipulations. We evaluated the model on a standard IoT benchmark dataset, where it significantly outperformed a state-of-the-art method in detecting adversarial attacks. In addition to enhanced robustness, this approach improves model transparency and interpretability, thereby increasing trust in the IDS through explainable AI.