Re: [Nmlrg] Machine Learning in network - solicitation for use cases

[Sebastian Abt <[e-mail]>]

> Am 16.09.2015 um 18:17 schrieb Jérôme François <[e-mail]>fr>:
> 
> I have experienced using ML for device fingerprinting meaning that by
> observing traffic pattern (message sequence and timing information) it
> is possible to automatically retrieve the precise types of device (name,
> version, series).
> It is particularily interesting to make network inventory as most of
> cases there are some unknwon devices on the network (user or old ones)
> and finally potentially identifying vulnerable devices from a security
> point of view.

Just to add to this fingerprinting: we also did some research on fingerprinting/recognising individuals in network traffic, which worked very well.  I also know that there’s work on ML-based web browser fingerprinting. 

In general, I find fingerprinting an interesting topic from both, a privacy-protection as well as a forensics (can we find evidence that a suspect was using a specific computer network?) perspective.

sebastian