Plausible Deniability in Web Search—From Detection to Assessment

Abstract

Abstract-Web personalisation uses what systems know about us to create content targeted at our interests. When unwanted personalisation suggests we are interested in sensitive or embarrassing topics a natural reaction is to deny interest. This is a practical response only if denial of our interest is credible or plausible. Adopting a definition of plausible deniability in the usual sense of "on the balance of probabilities", we develop a practical and scalable tool called PDE allowing a user to decide when their ability to plausibly deny interest in sensitive topics is compromised. We show that threats to plausible deniability are readily detectable for all topics tested in an extensive testing program. Of particular concern is observation of threats to deniability of interest in topics related to health and sexual preferences. We show this remains the case when attempting to disrupt search engine learning through noise query injection and click obfuscation. We design a defence technique exploiting uninteresting, proxy topics and show that it provides a more effective defence of plausible deniability in our experiments.

Automated web content personalization in the automotive sector: The SEAT case

“…Whilst, an important proportion of online users are concerned about how companies are using their personal data (Kalaignanam et al, 2018;Mulvenna et al, 2000;, they seem to be willing to share their data for convenience when the perceived benefits from personalization overweight the drawbacks of information disclosure (Chellappa and Shivendu, 2010;Garcia-Rivadulla, 2016;Mothersbaugh et al, 2012). However, this willingness seems not to be unlimited (Chellappa and Shivendu, 2010) and has been found to be affected by different factors such as the trust in the website owner organization (Li and Unger, 2012;, the sensitiveness of the information (Mac Aonghusa and Leith, 2018;Mothersbaugh et al, 2012), the awareness and feeling of control over the information (Kobsa, 2007) or the personalization strategy (Sundar and Marathe, 2010).…”

“…Other commented context factors in the literature, include the user's social context (Mac Aonghusa and Leith, 2018), the type of products/services (Annamalai et al, 2019), the browsing motivation (Salonen and Karjaluoto, 2019), the user's emotions (Pappas et al, 2017;Pappas, 2018) or the user's mood (Ho and Lim, 2018) as all of them are continuously changing in time.…”

“…Search engines are the collection of programs used for information retrieval from the Internet (Jayanthi and Rathi, 2014). Therefore, the personalization of search engines is meant to adapt the search results to the needs or interests of the user (Mac Aonghusa and Leith, 2018;Zhang et al, 2013). During the last few years, many new approaches to web search publication have been introduced (e.g.…”