Explainable Deep Learning Based Adversarial Defense for Automatic Modulation Classification

Deep learning (DL) has been widely applied to enhance automatic modulation classification (AMC). However, the elaborate AMC neural networks are susceptible to various adversarial attacks, which are challenging to handle due to the generalization capability and computational cost. In this article, an explainable DL based defense scheme, called SHapley Additive exPlanation enhanced Adversarial Fine-Tuning (SHAP-AFT), is developed in the perspective of disclosing the attacking impact on the AMC network. By introducing the concept of cognitive negative information, the motivation of using SHAP for defense is theoretically analyzed first. The proposed scheme includes three stages, i.e., the attack detection, the information importance evaluation, and the AFT. The first stage indicates the existence of the attack. The second stage evaluates contributions of the received data and removes those data positions using negative Shapley values corresponding to the dominating negative information caused by the attack. Then the AMC network is fine-tuned based on adversarial adaptation samples using the refined received data pattern. Simulation results show the effectiveness of the Shapley value as the key indicator as well as the superior defense performance of the proposed SHAP-AFT scheme in face of different attack types and intensities.

Information Importance-Aware Defense against Adversarial Attack for Automatic Modulation Classification:An XAI-Based Approach

Deep learning (DL) has significantly improved automatic modulation classification (AMC) by leveraging neural networks as the feature extractor.However, as the DL-based AMC becomes increasingly widespread, it is faced with the severe secure issue from various adversarial attacks. Existing defense methods often suffer from the high computational cost, intractable parameter tuning, and insufficient robustness.This paper proposes an eXplainable artificial intelligence (XAI) defense approach, which uncovers the negative information caused by the adversarial attack through measuring the importance of input features based on the SHapley Additive exPlanations (SHAP).By properly removing the negative information in adversarial samples and then fine-tuning(FT) the model, the impact of the attacks on the classification result can be mitigated.Experimental results demonstrate that the proposed SHAP-FT improves the classification performance of the model by 15%-20% under different attack levels,which not only enhances model robustness against various attack levels but also reduces the resource consumption, validating its effectiveness in safeguarding communication networks.