This post is by North Carolina A&T grad student Siobahn Day
Greetings! My name is Siobahn Day. I’m currently a PhD student in the Computer Science at North Carolina A&T State University. I work as a graduate researcher in the Center for Advanced Studies in Identity Science. I have developed the concept of Adversarial Authorship as a means of preserving author anonymity. I’m currently developing and evaluating an Interactive Evolutionary Computation for Adversarial Authorship which allows users to conceal their writing style.
This research is particularly important to me because as technology has advanced over the years, our laws have not (US). Due to the rapid growth of the internet and social networks it’s very hard for one to have anonymity. As a result, many Anonymous Social Network (ASNs) have arose. Some believe that privacy is dead and I’d like to see what could be done to change that outlook. I’m excited to share with you some of my current research and snippets of a publication that will appear in the The 25th International Conference on Computer Communication and Networks (ICCCN 2016) proceedings later this year. BEACON has given me new and innovative ways at looking at my problem in order to find an effective solution.
Over the last few years, we have seen an increase in the number of Anonymous Social Networks (ASNs). What many internet users may not know is that their writing style can be tracked across the internet and even through an ASN. The good news is that by using a technique referred to as Adversarial Stylometry one can effectively imitate the writing style of another or even obfuscate their own writing style in an effort to conceal their true writing style – for a short term. The bad news is that recent research has shown that Adversarial Stylometry is not effective in concealing ones writing style over the long term. We introduce a number of underlying concepts that will allow users to conceal their writing style over the long term. One such concept we refer to as Adversarial Authorship.
In Adversarial Authorship, authors are provided an AuthorWeb which allows them to see graphically how their writing style compares with others in the AuthorWeb. The AuthorWeb presented uses Entropy-based Evolutionary Clustering (EBEC) in an effort to cluster writing styles. Our results show that EBEC outperforms a number of other machine learning techniques for author recognition. Users of an AuthorWeb can then write to user-specified clusters in an effort to conceal their writing style.
If this research interests you in any way, feel free to read my previous publication: Towards the Development of a Cyber Analysis & Advisement Tool (CAAT) for Mitigating De-Anonymization Attacks . You can also visit my research team at The Center for Advanced Studies in Identity Science. I look forward to continuing to share with BEACON much more of my research as it evolves.