Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
1–10 of 10 posts
Re: Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
#2Re: Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
#3Really cool!
Re: Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
#4Re: Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
#5Re: Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
#6Re: Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
#7I'd be curious to the training time (per training example) of the logistic regression model in FHE.
Here, the training is not done on encrypted values: the songs are public, what is secret is which song(s) you like
Re: Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
#8This is awesome but with a mere 1000-song database it would be simpler just to run the whole thing on the client. How well could the approach scale? (eg. To a billion song DB?)
Re: Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
#9This is awesome but with a mere 1000-song database it would be simpler just to run the whole thing on the client. How well could the approach scale? (eg. To a billion song DB?)
If you have a Google Pixel phone running the stock OS, you already have this! https://support.google.com/pixelphone/answer/7535326?hl=en#z...
Re: Show HN: Building an End-to-End Encrypted Shazam with Homomorphic Encryption
#10Nice idea, but do I need E2E to identify a song? Seems like a very low threat model for a malicious attacker to know my wife needs that Elton John song.