Paper Image

Forecasting Data Access to Prevent Leaks

Published on:

21 December 2023

Primary Category:

Cryptography and Security

Paper Authors:

Kishu Gupta,

Ashwani Kush


Key Details

Uses learning-based DLP approach tailored to user behavior

Forecasts each user's expected data access range from past usage

Sets upper and lower bounds per user for normal access

Flags users as potential threats if they exceed expected bounds

Enables preventing or restricting access for suspicious users

AI generated summary

Forecasting Data Access to Prevent Leaks

This paper proposes a data leak prevention (DLP) approach that uses statistical analysis of past user data access to forecast future access. It builds a model that sets upper and lower bounds for normal data access per user. By comparing actual access time to forecasted norms, it can detect potential leakage by flagging users with abnormal usage.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up