Assessment of the Relative Importance of different hyper-parameters of LSTM for an IDS

TL;DR

This paper investigates how hyper-parameters of LSTM networks affect malware detection accuracy using op-code sequences, highlighting the importance of tuning for machine-language data and comparing LSTM with non-sequential models.

Contribution

It identifies the most critical hyper-parameters for LSTM in malware detection and demonstrates the necessity of tuning these parameters for effective performance on op-code sequences.

Findings

Performance is highly sensitive to number of hidden layers.

Input sequence length significantly impacts detection accuracy.

Activation function choice affects model effectiveness.

Abstract

Recurrent deep learning language models like the LSTM are often used to provide advanced cyber-defense for high-value assets. The underlying assumption for using LSTM networks for malware-detection is that the op-code sequence of malware could be treated as a (spoken) language representation. There are differences between any spoken-language (sequence of words/sentences) and the machine-language (sequence of op-codes). In this paper, we demonstrate that due to these inherent differences, an LSTM model with its default configuration as tuned for a spoken-language, may not work well to detect malware (using its op-code sequence) unless the network's essential hyper-parameters are tuned appropriately. In the process, we also determine the relative importance of all the different hyper-parameters of an LSTM network as applied to malware detection using their op-code sequence representations. We experimented with different configurations of LSTM networks, and altered hyper-parameters like the embedding-size, number of hidden layers, number of LSTM-units in a hidden layer, pruning/padding-length of the input-vector, activation-function, and batch-size. We discovered that owing to the enhanced complexity of the malware/machine-language, the performance of an LSTM network configured for an Intrusion Detection System, is very sensitive towards the number-of-hidden-layers, input sequence-length, and the choice of the activation-function. Also, for (spoken) language-modeling, the recurrent architectures by-far outperform their non-recurrent counterparts. Therefore, we also assess how sequential DL architectures like the LSTM compare against their non-sequential counterparts like the MLP-DNN for the purpose of malware-detection.