Data Leakage Prevention for Data in Transit using Artificial Intelligence and Encryption Techniques

Data leakage in an organization is a very important concern that leads to the ex-filtration of data, The work in this paper addresses a novel concept for prevention of data leakage for data in transit. The text under consideration is classified to confidential or non-confidential category based on the content and context using Machine Learning technique. Subsequent action for encryption is performed on the confidential data and then transmitted from the Intranet domain to Internet domain ensuring that the data is not compromised to unauthorized users. In addition, normal transactional data which is nonconfidential in nature is not prevented from transmitting and is easily accessible by a third party. Encryption is applied only to selected data and not the entire data in transit, ensuring that the hardware resources are efficiently utilized. An adversary can simply compose an e-mail with the organization's confidential information as the body of the mail, in such scenarios our method will classify the e-mail content and will encrypt the data so that the data is not revealed to an outsider.