Software Obfuscation Technique Based On Recurrent Neural Network

Protecting intellectual property against tampering is an urgent issue to many software designers, where illegal access to sensitive data is considered as a form of copyright infringement. Software owners apply various protection techniques in order to address this issue. Many of used mechanisms are weak, since they are vulnerable to both dynamic and static analysis, where the other are very costly since they impose considerable performance penalties. In this paper, we proposed a data and control flow obfuscating technique based on integrating encryption mechanism within a recurrent neural network (RNN). The proposed technique is immune against tampering since the neural network provides a robust security characteristic in software protection due to its ability of representing nonlinear algorithms with a powerful computational capability. Our method is designed to enable the neural network executing the conditional control transfers, where the complexity of neural network ensures that the protected behavior is turned into a complicated and incomprehensible form. Therefore, it impossible to extract the rules or locating the accurate inputs that lead to the execution paths behind the neural network. The system is designed to enable the neural network generates different encryptions for the same protected data. Our results prove that the proposed technique provides a stronger software protection than other techniques and it is immune against both static and dynamic analysis since it increases the difficulties in revealing the obfuscated software. Thus, we conclude that employing the neural networks in our system significantly increase the protection of software against tampering.