I'm slightly puzzled that Telegram is scoring more than 100%. What am I missing?
Show HN: I made a neural net that analyzes privacy policies
31–40 of 122 posts
Re: Show HN: I made a neural net that analyzes privacy policies
#32Hello! http://www.privacyparrot.com/ Made a similar project many moons ago and is still kicking along. Thanks all on HN for the feedback.
I used it as recently as a month ago! Thanks.
Re: Show HN: I made a neural net that analyzes privacy policies
#33This is great, I've been wanting to do a project like this for a while. Would be great to get some insight into your data collection/labeling and model design process.
Some of the process on gathering the data to create the labelling dataset is described here: https://useguard.com/experiment But most probably I'll be publishing a paper later this year detailing all the details and process :)
Where can we follow you to know abt the paper when you do eventually publish?
Re: Show HN: I made a neural net that analyzes privacy policies
#34Hi 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…
For a site trying to fight for privacy, don't you think it would be better to not use Google Analytics to track the people who visit your site?
Re: Show HN: I made a neural net that analyzes privacy policies
#35Hi. A related project that takes a more human-powered approach is PrivacySpy ( https://privacyspy.org ). Would be neat to see how these tools intersect. PrivacySpy is open source, community run, and more about grading policies on a standardized rubric (as opposed to entrusting that to ML), so these tools might complement one another. (Full disclosure: I'm a contributor to PrivacySpy.)
Another one: https://tosdr.org/
ToS;DR is great, although it's more focused on terms of service so if you're looking for privacy-only info, you'll have to cut through a bit of noise.
Re: Show HN: I made a neural net that analyzes privacy policies
#36Hi 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…
How did you create a data set large and accurate enough to be useful in training a model?
Re: Show HN: I made a neural net that analyzes privacy policies
#37Hi 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…
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.
Re: Show HN: I made a neural net that analyzes privacy policies
#38Tinder and Mozilla have the same score of 33%. I don't agree with that.
Tinder willingly shares very, very personal data along with your contacts (assuming without said contact consent).
Re: Show HN: I made a neural net that analyzes privacy policies
#39Earlier 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.
Or make the rank adjustable to some personal criteria that matches different privacy expectations.
Re: Show HN: I made a neural net that analyzes privacy policies
#40I get ERR_SSL_PROTOCOL_ERROR
Some other user reported that same thing this morning but I couldn't find any explanation to this err. It basically works for everyone except for these two precise cases. One idea I have is that you might be behind some sort of firewall that's blocking my website (because in the past either the IP or the domain got flagged by some antivirus company and now some business networks block it) – might this be the case?
I'm not an expert but I wonder if this error comes up in the case of the HTTPS handshake not being able to agree on a protocol -- one side of the transaction is trying to insist on a crypto protocol that's out of date or a little too fashion-forward?
Just a thought.