Practical Black-Box Attacks against Machine Learning · HackerPapers discussions

Practical Black-Box Attacks against Machine Learning — HN submission

Sun, 21 Jun 2020 08:42:11 GMT

Practical Black-Box Attacks Against Machine Learning

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Practical Black-Box Attacks against Machine Learning — mentioned by JoeDaDude

Mon, 28 Oct 2019 21:40:06 GMT

Nicholas Papernot [1] et al. has shown how this can be an attack on an unknown network provided you have access to inference results produced by the target network [2]. [1] https://www.papernot.fr/ [2] https://arxiv.org/abs/1602.02697

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

Practical Black-Box Attacks against Machine Learning — mentioned by Fripplebubby

Sun, 11 Mar 2018 02:20:47 GMT

One method of creating adversarial examples in a "black box" setting is to create and train a local model as a stand-in for the actual model using the inputs and outputs of the actual model. [1] So, the answer is "no" but a qualified "no" since in practice this seems to work. The second part, being able to forward many images, is also a qualified "no". 1 - https://arxiv.org/abs/1602.02697

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

Practical Black-Box Attacks against Machine Learning — mentioned by whataretensors

Wed, 31 Jan 2018 09:10:23 GMT

You don't need access to the network, you can just build another one. https://arxiv.org/abs/1602.02697 "Our attack strategy consists in training a local model to substitute for the target DNN, using inputs synthetically generated by an adversary and labeled by the target DNN"

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

Practical Black-Box Attacks against Machine Learning — mentioned by Winterflow3r

Thu, 02 Nov 2017 20:48:12 GMT

No, this paper by Papernot et al shows how to do blackbox attacks without knowledge of model internals. https://arxiv.org/abs/1602.02697

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

Practical Black-Box Attacks against Machine Learning — mentioned by statusgraph

Sat, 26 Aug 2017 18:11:39 GMT

Interestingly, you can treat the NN as a black box (ie, not look at individual weights or even the architecture) and still derive adversarial cases: https://arxiv.org/abs/1602.02697

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

Practical Black-Box Attacks against Machine Learning — HN submission

Thu, 17 Aug 2017 08:12:11 GMT

Practical Black-Box Attacks Against Machine Learning

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Practical Black-Box Attacks against Machine Learning — mentioned by kajecounterhack

Fri, 08 Apr 2016 15:41:47 GMT

http://arxiv.org/abs/1602.02697 I don't work on reCAPTCHA but I imagine they could easily + significantly beef up image captcha by adding adversarial image examples that trip up would-be automators. Note that adversarial examples generalize across models. Meaning a good adversarial example will work against SVMs, convnets, etc just the same. If you're interested in the basics of how it works, Julia Evans has a great post: jvns.ca/blog/2015/12/24/how-to-trick-a-neural-network-into-thinking-a-panda-is-a-vulture The key is that deep neural nets are actually very (piecewise) linear and that makes…

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

Practical Black-Box Attacks against Machine Learning — HN submission

Tue, 23 Feb 2016 11:04:20 GMT

Practical Attacks against Deep Learning Systems using Adversarial Examples

98 points; 32 discussion replies on HN. Paper and source history. A submission is not an endorsement.