ESET's road to Augur

[BoraMurdar]

Full article
Machine learning by ESET: The road to Augur

At ESET we love ancient history – the company is named after an Egyptian goddess after all – so that was naturally the place we looked for when it came to naming our machine learning engine. In Ancient Rome, Augur was a term used for religious officials who observed natural signs and interpreted these as an indication of divine approval or disapproval of a proposed action. The analogy with cybersecurity is not hard to draw, but in contrast with the alchemy-natured augurs back then, our Augur bases its decisions on science, mathematics and previous experience.

 

[Huchim]

So, it's already included in ESET's products? or how can see it in action? it's a detection name maybe? for example as far as I know norton use machine learning on some detections and name it heur.adv.ml

 

[mekelek]

So, it's already included in ESET's products? or how can see it in action? it's a detection name maybe? for example as far as I know norton use machine learning on some detections and name it heur.adv.ml

ESET does this for all executed application, hence it has such a good static detection.

 

[Huchim]

Yeah and I think that's why fails if not catch something after a static detection. Since V7 always have failed detecting a common worm I think that spreads for USB on my region

 

[Korea]

Machine Learning is used in ESET and we were using it for years.
https://static3.esetstatic.com/fileadmin/Images/INT/Docs/Other/ESET-Technology-Overview.pdf

Any Deep Learning Techniques in ESET products?
In addition, there is also a reason why eset does not use the sandbox.

 

[ravi prakash saini]

good flow chart but in recent times they are finding it hard to make it work in practical

 

[Parsh]

That's an interesting consolidation of the algorithms and AI approaches proven to be effective till now. No doubt that explains their powerful detection.
@Huchim they have been using ML techniques since years and this seems to be their new AI project or a rebranding of their project, implementing the best of Deep Learning and Classification algorithms they've found to be useful.
Nice share