Please use this identifier to cite or link to this item:
|Title:||A Novel Approach to Attack Smartcards Using Machine Learning Method|
|Keywords:||Side Channel Attack;Power Analysis Attack;Wavelet Transform;Machine Learning;Cryptography;Advanced Encryption Standard;Principal Component Analysis;Probabilistic Neural Networks|
|Abstract:||This paper presents an effective way to enhance the secret key guessing ratio in machine learning based power analysis attack on secure systems such as smartcards. The power supply current traces are obtained by varying the atmospheric temperature for all possible values of key. The collected power supply current traces are then pre-processed by using wavelet transform, data normalization and principal component analysis (PCA) and the featured data samples are used to train the probabilistic neural network (PNN). The network is then tested with a current trace obtained from the device under attack and the correct key is identified. The proposed method achieves 100% success rate in guessing the secret key of the cryptographic algorithm with minimum number of power traces when compared to the existing methods of machine learning technique.|
|ISSN:||0975-1084 (Online); 0022-4456 (Print)|
|Appears in Collections:||JSIR Vol.76(02) [February 2017]|
Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.