Remove resources better-data-classification-better-data-security
article thumbnail

How to confuse antimalware neural networks. Adversarial attacks and protection

SecureList

We implement different machine learning techniques, including deep neural networks, one of the most promising technologies that make it possible to work with large amounts of data, incorporate different types of features, and boast a high accuracy rate. But can we rely entirely on machine learning approaches in the battle with the bad guys?

Malware 121
article thumbnail

Learning Machine Learning Part 1: Introduction and Revoke-Obfuscation

Security Boulevard

As a sidenote on learning this subject matter: Many offensive security professionals often have to figure out a lot about very complex systems in a relatively short period of time during engagements. predicting a numerical value, like housing prices) or classification (i.e., With supervised learning your data is labeled (e.g.,

article thumbnail

If Infosec Was a Supermarket Business

Security Boulevard

The core of our analogy will be comparing supermarket stock to a business’s data. Whilst the end customer only sees the product as it sits on the shelf, for the sake of our analogy we need to be aware of what goes on before that stock ends up on that shelf because, in our analogy, stock is data. A 24-hour convenience store.

InfoSec 52