Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples · HackerPapers discussions

Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples — mentioned by evjrob

Tue, 30 Jan 2018 22:36:38 GMT

I wouldn't be surprised if these speech to text models are susceptible to black box attacks in the same way that image classifiers are: https://arxiv.org/abs/1605.07277

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

Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples — mentioned by shmel

Thu, 02 Nov 2017 23:53:43 GMT

Really? I believe they meant exactly what they said. Read https://arxiv.org/abs/1605.07277 Adversarial examples can be easily crafted for linear regression, SVM, decision trees and k-NN at very least. I can't think about any ML technique that is proven to be secure against them. There is also an old blogpost from Karpathy describing that the only reason we are not concerned about adversarial examples in linear models is that nobody uses them to classify ImageNet.

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

Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples — mentioned by obastani

Thu, 02 Nov 2017 19:58:51 GMT

I think they might be referring [1], which shows that adversarial examples transfer to models such as decision trees and SVMs. [1] https://arxiv.org/abs/1605.07277

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