Re:YouTube-Style Face Detect – Crop and Blur Using Python an...
by cbhl on Tuesday April 14, 2020 @10:31AM
(#22866418)
In my personal opinion, a naive gaussian blur could be susceptible to supersampling attacks, especially in a video where you can take samples over multiple frames. In a production implementation, I would consider adding some steps to mitigate this.
[ Parent
| on HN ]
Re:YouTube-Style Face Detect – Crop and Blur Using Python an...
by aripickar on Tuesday April 14, 2020 @11:48AM
(#22867417)
Theoretically, augmenting the blurred image with some sort of random, changing offset for the HSV values on each frame would prevent supersampling attacks, right?
Re:YouTube-Style Face Detect – Crop and Blur Using Python an...
by contravariant on Tuesday April 14, 2020 @12:35PM
(#22868028)
Adding noise is definitely helps, but removing noise is more or less the main feature of supersampling.
If you didn't have any noise you could just simply invert the Gaussian blur, as blurring is a reversible operation (in theory, in practice you have noise, hence the need for supersampling).
Annoyingly it's hard to come up with a method that doesn't leak any information, although heavily pixelating the image (and optionally blurring the few leftover pixels) would probably make it infeasible to recover the original (except maybe with a truly stupendous amount of footage).