This is amazing! How would you categorize this?
Show HN: I made a neural net that analyzes privacy policies
81–90 of 122 posts
Re: Show HN: I made a neural net that analyzes privacy policies
#82Re: Show HN: I made a neural net that analyzes privacy policies
#83Analyse LastPass. Even without ML it's clearly saying they spy on everything you do and share it with anyone they want. I'm surprised they get recommended so often given their privacy policy.
Re: Show HN: I made a neural net that analyzes privacy policies
#84Hi guys! So as basis for my thesis on AI and NLP I've been working on a RRN-based text classifier that basically reads and analyzes privacy policies. It understands that "we don't share your data with third parties" is privacy friendly while "we may share your data with anyone" is a potential threat. I've then created this website with a bunch of analyzed services to showcase the most relevant info about each service…
> It understands that "we don't share your data with third parties" is privacy friendly while "we may share your data with anyone" is a potential threat. Does it understand "we don't share your data with just any old third parties", or "we're not like our competitors who may share your data with anyone"?
Not OP, but curious, are those quotes actually from privacy policies or just hypotheticals?
Re: Show HN: I made a neural net that analyzes privacy policies
#85Earlier quoted context omitted.
I don't agree. I just looked in my password manager, and I have roughly ~220 accounts across the web. If I want to go through that list and see which website rank well and which rank poorly, and I want to do that in under two hours, that gives about 30 seconds per service. In other words, giving a single score plus a two-sentence highlight is probably about the right amount of information.
Or make the rank adjustable to some personal criteria that matches different privacy expectations.
This would also be helpful in determining how to weight (or not) user feedback in the training portion. I just tried it out (the 10 questions) and there were at least a few I thought, "huh, I know some others would disagree with me on this" because I value X and they value Y more.
Having scores that weight X more than Y would give me more accurate scores, while seemingly also giving other people more accurate scores at the same time.
Re: Show HN: I made a neural net that analyzes privacy policies
#86Earlier quoted context omitted.
> It understands that "we don't share your data with third parties" is privacy friendly while "we may share your data with anyone" is a potential threat. Does it understand "we don't share your data with just any old third parties", or "we're not like our competitors who may share your data with anyone"?
Not OP, but curious, are those quotes actually from privacy policies or just hypotheticals?
With enough sites / privacy policies out there, even hypotheticals will end up in a real policy at some point (if not already). Is there something significant in the distinction or is it just curiosity? If the latter, I also share it. :)
Re: Show HN: I made a neural net that analyzes privacy policies
#87The "game" (training) that asks you to analyse "privacy threats" is a bit strange. It feels like it takes two random excerpts from a privacy policy and asks you to compare them, but with this, it feels like it is missing some global information, you are just looking at local details.
Eg one policy might be disclosing what they do (but its actually relevant to collect data, eg password manager) while the other just says "no we don't collect anything". In this case one feels like its a better option, but its not exactly the same situation, its missing some context. I feel like this could potentially bias ratings.
I'm not sure if you could add in extra information with some of that global information, eg the type of service, classifying different "parts" of the privacy policy etc.
Re: Show HN: I made a neural net that analyzes privacy policies
#88Earlier quoted context omitted.
Oh my god thank you so much for doing this ! I think its better (for me as a user) if you don't boil things down to a score as different people expect different things when talking privacy. It would help if you could simply highlight the potential problematic clauses in different privacy statements along with some reason why it might be problematic.
I don't agree. I just looked in my password manager, and I have roughly ~220 accounts across the web. If I want to go through that list and see which website rank well and which rank poorly, and I want to do that in under two hours, that gives about 30 seconds per service. In other words, giving a single score plus a two-sentence highlight is probably about the right amount of information.
A good compromise would be a chrome extension that shows a 1-10 score. You click the extension to see clauses
Re: Show HN: I made a neural net that analyzes privacy policies
#89I love the work, and it is directly applicable to the work I am doing now. Have you published your thesis?
Re: Show HN: I made a neural net that analyzes privacy policies
#90Earlier quoted context omitted.
Oh my god thank you so much for doing this ! I think its better (for me as a user) if you don't boil things down to a score as different people expect different things when talking privacy. It would help if you could simply highlight the potential problematic clauses in different privacy statements along with some reason why it might be problematic.
I don't agree. I just looked in my password manager, and I have roughly ~220 accounts across the web. If I want to go through that list and see which website rank well and which rank poorly, and I want to do that in under two hours, that gives about 30 seconds per service. In other words, giving a single score plus a two-sentence highlight is probably about the right amount of information.
Not for everyone, as thecleaner pointed out. You are assuming your requirements are universal among other users. Also, you are assuming the policies can be simplified to a weighted average of their parts, which is not necessarily the case.