Acta Metallurgica Sinica(English letters) ›› 2015, Vol. 22 ›› Issue (5): 10-15.doi: 10.1016/S1005-8885(15)60674-4

• Wireless • Previous Articles     Next Articles

Electromagnetic side_channel attack based on PSO Directed Acyclic Graph SVM


  1. 1. School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China 2. School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454000, China 3. Institute of North Electronic Equipment, Beijing 100191,China 4. School of Opto-electronic Information Science and Technology, Yantai University, Yantai 264005, China
  • Received:2015-04-13 Revised:2015-09-20 Online:2015-10-30 Published:2015-10-30
  • Contact: Zhang Hongxin
  • Supported by:

    The work was supported by the National Natural Science Foundation of China (61571063, 61202399, 61171051).


Machine learning has a powerful potential for performing the template attack (TA) of cryptographic device. To improve the accuracy and time consuming of electromagnetic template attack (ETA), a multi-class directed acyclic graph support vector machine (DAGSVM) method is proposed to predict the Hamming weight of the key. The method needs to generate K(K 1)/2 binary support vector machine (SVM) classifiers and realizes the K-class prediction using a rooted binary directed acyclic graph (DAG) testing model. Further, particle swarm optimization (PSO) is used for optimal selection of DAGSVM model parameters to improve the performance of DAGSVM. By exploiting the electromagnetic emanations captured while a chip was implementing the RC4 algorithm in software, the computation complexity and performance of several multi-class machine learning methods, such as DAGSVM, one-versus-one (OVO)SVM, one-versus-all (OVA)SVM, Probabilistic neural networks (PNN), K-means clustering and fuzzy neural network (FNN) are investigated. In the same scenario, the highest classification accuracy of Hamming weight for the key reached 100%, 95.33%, 85%, 74%, 49.67% and 38% for DAGSVM, OVOSVM, OVASVM, PNN, K-means and FNN, respectively. The experiment results demonstrate the proposed model performs higher predictive accuracy and faster convergence speed.

Key words:

directed acyclic graph support vector machine (DAGSVM)|particle swarm optimization (PSO)|side-channel attack|electromagnetic emanations

CLC Number: