Home

Awesome

Awesome AI for cybersecurity

This is a list of AI for cybersecurity, including network (network traffic analysis and intrusion detection), endpoint (anti-malware), application (WAF or database firewalls), user (UBA), process behavior (anti-fraud).

1. Introduction

First, beginners should look at machine learning tasks and its applications. I wrote a machine learning blog including CV (CNN, GAN), RL, GNN, NLP.

Additionally, developers still need to know more about security/cybersecurity, here is the awesome list of security tool and knowledge.

Then, let's turn to AI for cybersecurity.

The first dimension is a goal or a task. According to Gartner’s PPDR model, all security tasks can be divided into five categories:

The second dimension is a technical layer and the list of layers for this dimension:

2. Network Protection

ML in network security implies new solutions called Network Traffic Analytics (NTA) aimed at in-depth analysis of all the traffic at each layer and detect attacks and anomalies.

How can ML help here? There are some examples:

And here are some research papers:

3. Endpoint Protection

If you deal with machine learning at endpoint layer, your solution may differ depending on the type of endpoint (e.g., workstation, server, container, cloud instance, mobile, PLC, IoT device).

Every endpoint has its own specifics but the tasks are common:

and there are some research work to follow:

4. Application Security

There are web applications, databases, ERP systems, SaaS applications, micro services, etc. WAFs or Code analysis, both static and dynamic can be applied to this.

Here are examples what you can do with machine learning for application security:

and there are some research work to follow:

5. User Behavior

Unlike malware detection focusing on common attacks and the possibility to train a classifier, user behavior is one of the complex layers and unsupervised learning problem.

Here are the tasks that companies solve with the help of ML:

and there are some research work to follow:

6. Process Behavior (fraud detection)

While dealing with process behavior, it’s necessary to know a business process in order to find something anomalous. Business processes can differ significantly. You can look for fraud in banking and retail system, or a plant floor in manufacturing.

In general, there are the examples of tasks in the process area:

A monitoring component provides a behavior log - the sequence of system events occurred during the process execution together with corresponding arguments. In order to detect malicious activity in observed log data our model compresses obtained sequence of events to a set of binary vectors and trains the deep neural network to distinguish clean and malicious logs.

<img src="1.png"></img>

and there are some research work to follow:

7. Intrusion Detection and Prevention Systems (IDS/IPS)

These systems detect malicious network activities and prevent intruders from accessing the systems and alerts the user. Typically, they are recognized by known signatures and generic attack forms. This is useful against threats like data breaches.

Traditionally, this task was performed by ML algorithms. However, these algorithms caused the system to generate many false-positive, creating tedious work for security teams and causing unnecessary fatigue.

Deep learning, convolutional neural networks and Recurrent Neural Networks (RNNs) can be applied to create smarter ID/IP systems by analyzing the traffic with better accuracy, reducing the number of false alerts and helping security teams differentiate bad and good network activities.

Notable solutions include Next-Generation Firewall (NGFW),Web Application Firewall (WAF), and User Entity and Behavior Analytics (UEBA).

8. Books & survey paper

8.1 Book

8.2 Survey Paper