IJSRSET18483 | Received : 01 May 2018 | Accepted : 08 May 2018 | May-June-2018 [(4) 8 : 56-62] © 2018 IJSRSET | Volume 4 | Issue 8 | Print ISSN: 2395-1990 | Online ISSN : 2394-4099 Themed Section : Engineering and Technology 56 Data Leakage Detection and Prevention using Fake Agents Gagandeep Kaur 1 , Dr. Sandeep Kautish 2 * 1 Research Scholar,University College of Computer Applications, Guru Kashi University, Talwandi Sabo, Bathinda, Punjab, India 2 Professor in Computer Science, Guru Kashi University, Talwandi Sabo, Bathinda, Punjab, India ABSTRACT In today’s world, there is need of many companies to outsource their sure business processes (e.g. marketing, human resources) and related activities to a third party like their service suppliers. In many cases the service supplier desires access to the company’s confidential information like customer data, bank details to hold out their services. And for most corporations the amount of sensitive data used by outsourcing providers continues to increase. So in today’s condition data Leakage is a Worldwide Common Risks and Mistakes and preventing data leakage is a business-wide challenge. Thus we necessitate powerful technique that can detect such a dishonest. Traditionally, leakage detection is handled by watermarking, Watermarks can be very useful in some cases, but again, involve some modification of the original data. So in this paper, unobtrusive techniques are studied for detecting leakage of a set of objects or records. The model is developed for assessing the “guilt” of agents. The algorithms are present for distributing objects to agents, in a way that improves our chances of identifying a leaker. Finally, consider the option of adding “fake” objects to the distributed set. The major contribution in this system is to develop a guilt model using fake elimination concept. Keywords: Allocation Strategies, Fake Records, Guilt Model I. INTRODUCTION In the business, sometimes it is necessary to send confidential data to trusted third parties. For example, a company may have partnerships with other companies that require sharing customer data. Similarly, a hospital may give patient records to researchers who will devise new treatments. Another enterprise may outsource its data processing, so data must be given to various other companies. So in this system owner of the data is called as distributor and the supposedly trusted third parties are called as agents. The system goal is to detect which distributor’s sensitive data has been leaked by agents, and if possible to identify the agent that leaked the data. Traditionally, Leakage detection is handled by watermarking e.g. unique code embedded in each distributed copy. But this watermarking involves some modification of original data. Furthermore watermarks sometimes can be destroyed if data recipient is malicious. But in some cases it is important not to alter the original distributor’s data It consider applications where the original sensitive data cannot be perturbed. Perturbation is a very useful technique where the data is modified and made “less sensitive” before being handed to agents. For example, one can add random noise to certain attributes, or one can replace exact values by ranges which is achieved through k-anonymity privacy protection algorithm [5]. However, in some cases it is important not to alter the original distributor’s data. In paper [1][10], there is an unobtrusive techniques for detecting leakage of a