Attacks against machine learning – an overview

Re:Attacks against machine learning – an overview by Bromskloss on Sunday June 10, 2018 @08:50PM (#17280978)

> Model stealing techniques, which are used to “steal” (i.e., duplicate) models or recover training data membership via blackbox probing. This can be used, for example, to steal stock market prediction models

I would like to hear stories about such attacks on stock market models.

[ Parent | on HN ]

Re:Attacks against machine learning – an overview by taurine on Monday June 11, 2018 @05:06AM (#17282851)

There are not any, since there are no public stock market models worth copying, and no stock market model takes external input. But if they did (you could give a time-series to a model in the cloud, and it would give you predictions) then it would be possible.

Copying models is a problem for cloud-hosted pay-per-prediction image classification, not for constantly retrained stock market models that don't take external input.

[ Parent | on HN ]

Re:Attacks against machine learning – an overview by Bromskloss on Monday June 11, 2018 @07:55AM (#17283496)

I thought it would be about observing the behaviour of a system that is trading on the market. The input to the system would consist, for example, of other people's trades.

[ Parent | on HN ]

Re:Attacks against machine learning – an overview by taurine on Wednesday June 13, 2018 @12:13PM (#17304423)

It is referring to https://arxiv.org/abs/1609.02943

What you are referring to is possible, but is not "copying" per se, just trying to infer what the system is doing (inverse RL), and then exploit that/make it do mistakes. If you are not HFT it is very difficult to distinguish bots from humans, so you'd have a hard time even finding a target.

[ Parent | on HN ]