Sensitive Data Leakage Detection using Fuzzy Fingerprint Technique in Host-Assisted Mechanism

Abstract

Statistics from security firms, government organizations and research institutions show that the numbers of data-leak instances have grown rapidly in recent years. Detecting and preventing data leaks requires a set of complementary solutions, which may include detection data-leak data confinement stealthy malware detection and policy enforcement. The designs, implement, and evaluate fuzzy fingerprint technique that enhances data privacy during data-leak detection operations. This is based on a fast and practical one-way computation on the sensitive data. The DLD provider computes fingerprints from network traffic and identifies by the potential leaks in them. To prevent the DLD provider from gathering exact knowledge about sensitive data, the collection of potential leaks is composed of real leaks and noises. It is the data owner, who post-processes sent back the potential leaks by the DLD provider and determines whether there is any real data leak. This supports detection operation delegation and ISPs can provide data-leak detection as an add-on service to their customers using this model.

Design the host-assisted mechanism for complete data-leak detection for large-scale organizations. The data owner computes a special set of digests or fingerprints from the sensitive data and then discloses only by small amount of them to the DLD provider. Fuzzy fingerprints are special sensitive data digests prepared by the data owner for release to the DLD provider. These results indicate high accuracy achieved by this underlying scheme with very low false positive rate. Data preparation and filtering steps can take considerable amount of processing time but once data preprocessing is done the data become more reliable and robust results are achieved. They have conducted experiments to validate the accuracy and privacy of these solutions.