Deep Learning Neural Network Model Research Articles

Encryption scheme classification: a deep learning approach

Encryption has an important role in protecting cyber assets. However the use of weak encryption algorithms is a vulnerability that may be exploited. When exploited, detecting this vulnerability from encrypted data is a very difficult task to undertake. This research explores the use of recent advancement in machine learning algorithms specifically deep learning algorithms to classify encryption schemes based on entropy measurements of encrypted data with no feature engineering. Past research works using various machine learning algorithms have failed to achieve good accuracy results in classification. The research entails applying popular encryption algorithms with block cipher modes over the image dataset from CIFAR10. Two ImageNet winning convolutional neural network deep learning models were used to perform the classification. Transfer learning and layer modification were applied to evaluate the classification effectiveness. This research concludes that deep learning algorithms can be used to perform such classification where other algorithms have failed.

Deep learning with support vector data description

One of the most critical problems for machine learning methods is overfitting. The overfitting problem is a phenomenon in which the accuracy of the model on unseen data is poor whereas the training accuracy is nearly perfect. This problem is particularly severe in complex models that have a large set of parameters. In this paper, we propose a deep learning neural network model that adopts the support vector data description (SVDD). The SVDD is a variant of the support vector machine, which has high generalization performance by acquiring a maximal margin in one-class classification problems. The proposed model strives to obtain the representational power of deep learning. Generalization performance is maintained using the SVDD. The experimental results showed that the proposed model can learn multiclass data without severe overfitting problems.

Joint optimization of algorithmic suites for EEG analysis.

Electroencephalogram (EEG) data analysis algorithms consist of multiple processing steps each with a number of free parameters. A joint optimization methodology can be used as a wrapper to fine-tune these parameters for the patient or application. This approach is inspired by deep learning neural network models, but differs because the processing layers for EEG are heterogeneous with different approaches used for processing space and time. Nonetheless, we treat the processing stages as a neural network and apply backpropagation to jointly optimize the parameters. This approach outperforms previous results on the BCI Competition II - dataset IV; additionally, it outperforms the common spatial patterns (CSP) algorithm on the BCI Competition III dataset IV. In addition, the optimized parameters in the architecture are still interpretable.