Cyber-physical systems consists of tight integration of cyber and physical domain components. Due to this, they are prone to various cross-domain attacks. One form of such attacks can take place in the form of physical-to-cyber domain attacks, which can cause confidentiality breach of the system. This is due to the fact that some of the cyber-domain information manifest in terms of physical actions such as motion, temperature change, etc. These physical actions may unintentionally leak information about the cyber-domain through the side-channels. Up until now there has been no study highlighting how these form of cross-domain attack can affect the cyber-physical additive manufacturing systems. Hence, in this thesis we present the analysis of acoustic side-channel to demonstrate how it can be leverage to build novel attack model and breach the confidentiality of the additive manufacturing system (such as 3D printers). Side-channels such as acoustic, thermal, and power allow attackers to acquire the information without actually leveraging the vulnerability of the algorithms implemented in the system. In 3D printers, geometry,process, and machine information are the intellectual properties, which are stored in the cyber domain (G-code). We have designed an attack model that consists of digital signal processing, machine learning algorithms, and context-based post processing to steal the intellectual property by reconstructing the G-code and thus the test objects. We have successfully reconstructed various test objects with an average axis prediction accuracy of 78.35% and an average length prediction error of 17.82%.