Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks · HackerPapers discussions

Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks — mentioned by saithound

Fri, 20 Aug 2021 05:42:47 GMT

We have no reason to believe that Apple's second, secret perceptual hash provides any meaningful protection against such attacks. At best, we can hope that it'll allow early detection of attacks in a few cases, but chances are that's the best it can do. We might not ever learn: Apple now has a very strong incentive not to admit to any evidence of abuse or to any faults in their algorithm. (Sorry, this is going to be long. I know understand most/all of this stuff, it's mostly there to provide a bit of context for the users reading our exchange) The term "hash function" is a bit of a misnomer…

Paper and discussion history. A mention is not an endorsement.

Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks — mentioned by saithound

Thu, 19 Aug 2021 11:40:33 GMT

FAQ Part 2/2 Q: If the second, secret hash algorithm is based on a neural network, can we think of its weights (coefficients) as some kind of secret key in the cryptographical sense? A: Absolutely not. If (as many suspect) the second hash algorithm is also based on some feature-identifying neural network, then we can't think of the weights as a key that (when kept secret) protects the confidentiality and integrity of the system. Due to the way perceptual hashing algorithms work, having access to the outputs of the algorithm is sufficient to train a high-fidelity "clone" that allows you to…

Paper and discussion history. A mention is not an endorsement.