← Back to context

Comment by shuckles

4 years ago

The NCMEC hash list is private, and adversarial attacks require running gradient descent and being able to generate a hash value for arbitrary input.

Is it possible to narrow in on a hash using gradient descent? You can correlate distance between inputs to distance between hashes somehow?

  • Replying to my own question since I can’t edit anymore: it turns out “perceptual hashing,” which I didn’t know much about, has exactly this property, that small changes in the input result in small changes in the output.