Maria Rigaki
AI Attackers in Your Pocket: How Small Language ...

We are pleased to announce the publication of our latest paper, “Building adaptive and transparent cyber agents with local language models,” in the Journal of Expert Systems with Applications.

Slips
Stratosphere IPS
How Well Do LLMs Perform on a Raspberry Pi 5?

Can a Raspberry Pi 5 run Large Language Models? In this post, we share the results of our experiments, analyzing how LLMs perform on this low-cost hardware and exploring the challenges and performance trade-offs.

How Well Do LLMs Perform on a Raspberry Pi 5?
Stratosphere IPS
Introducing ARACNE, a new LLM-based shell ...

The complete automation of cyber-attacks has become one of the areas of greatest interest since the introduction of Large Language Models (LLMs) to the public. The creation of attacking LLM agents that can act independently is among the most popular options. 

In this blog, we introduce a brand-new agent: ARACNE. We also share the results of attack tests and what they mean in terms of the agent’s current capabilities.

Introducing ARACNE, a new LLM-based shell pentesting agent
Teaching
Stratosphere IPS
Czech Technical University in Prague’s ...

We are thrilled to announce that, for the first time, the Czech Technical University in Prague is offering the "Introduction to Security" course as a Massive Open Online Course!

Czech Technical University in Prague’s "Introduction to Security" Class is now a Free Online Course!
Stratosphere IPS
Google Summer Of Code 2024 In Stratosphere. ...

This blog covers my ongoing GSoC project 2024. It provides information about the current progress of my work, as well as my experiences and lessons learned along the way.

Google Summer Of Code 2024 In Stratosphere. Blog for the first month of Sekhar Kumar Dash

Writing a SLIPS Module

Writing a SLIPS Module

Slips is a machine learning-based intrusion prevention system for Linux and MacOS, developed at the Stratosphere Laboratories from the Czech Technical University in Prague. Slips reads network traffic flows from several sources, applies multiple detections (including machine learning detections) and detects infected computers and attackers in the network. It is easy to extend the functionality of Slips by writing a new module. This blog shows how to create a new module for Slips from scratch.

Studying Cybercrime is Fun! An Overview of Five Years of Research Surrounding the Geost Botnet

Studying Cybercrime is Fun! An Overview of Five Years of Research Surrounding the Geost Botnet

This blog shows how a curious research experiment can lead a student into an interesting cybercrime investigation that contains weird -yet interesting- topics, such as understanding underground attackers, botnets, informal Internet forums, and the economy of encrypting malware-as-a-service.

Protecting the civil society through high quality research