Web browsing has become almost second nature to us. Each day, we plunge into tens of websites and unwittingly accept their long-winded privacy policies without bothering to peruse their stipulations. This is undoubtedly because those documents are shrouded in legalese too dense and cumbersome to read and digest. Yet, it is a well-known fact that many websites collect, store, and even use the private data that we inadvertently leave behind during our browsing sessions. Disturbingly, such practices are usually protected by the legal jargon contained in their privacy policies. So how do we ascertain the nature of data collected by a website? Is it possible to know how our data will be used by a website even before we start browsing that site?

To provide answers to questions like these, researchers from EPFL, University of Wisconsin, and University of Michigan have developed a program called Polisis that can read, decipher, and segmentize privacy policies of websites in a matter of seconds. The lead researcher is Hamza Harkous, Postdoctoral Researcher at EPFL’s Distributed Information Systems Laboratory.

With the help of artificial intelligence, Polisis (short for privacy policy analysis) presents a visualized summary of a privacy policy in the form of color-coded fragments categorized according to the type of information collected, their intended purpose, and options left for the user. That enables the user to make an informed decision about the safety of that website regarding private data collection and usage.

Polisis is closely linked with an interactive QA-based online chatbot called PriBot, which can answer your queries about the privacy policy of a particular website in the blink of an eye. For instance, you could ask, “Do you store my data with third parties?” Or “How long is my data retained?” PriBot will extrapolate the relevant part of the privacy policy and even simplify it for you. PriBot has a correct answer in its top three for 82% of questions, and its top answer is correct for 68% of the test questions.

The researchers used a corpus of 13,000 privacy policies to train the privacy-specific language model. Polisis is also based on “a novel hierarchy of neural-network classifiers that caters to the high-level aspects and the fine-grained details of privacy practices,” as stated in the research paper. Although the paper asserts that “Polisis can be used to assign privacy icons to a privacy policy with an average accuracy of 88.4%,” it goes on to say that the intention is not to use artificial intelligence to replace privacy policies as legal documents.

Polisis is a free-to-use program available as a browser extension for Chrome and Firefox. It can also be accessed directly on the Polisis website.

Further reading:

https://arxiv.org/pdf/1802.02561.pd
https://actu.epfl.ch/news/artificial-intelligence-can-help-you-protect-your-/
https://pribot.org/polisis
https://pribot.org/bot?company=www.manuscriptedit.com
https://www.helpnetsecurity.com/2018/02/12/polisis-analyzing-privacy-policies/
https://www.wired.com/story/polisis-ai-reads-privacy-policies-so-you-dont-have-to/
https://phys.org/news/2018-02-artificial-intelligence-personal.html
https://futurism.com/ai-reads-your-privacy-policies/