Detecting privacy leaks using corpus-based association rules & sponsored ad-based similarity: an approach to mining collective advertiser intelligence
Conferences & Talks

• Richard Chow
• Philippe Golle
• Jessica Staddon

14th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

24 August 2008 - 27 August 2008
Las Vegas, Nevada, USA

description

Detecting inferences in documents is critical for privacy applications in order to ensure the desired release or acceptance of information. In this paper, we propose a refined and practical model of inference detection using a base corpus. Our model is inspired by association rule mining: inferences are based on word co-occurrences...Our model also includes the important case of private corpuses, to model inference detection in settings such as an enterprise where there is a large private document repository.