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.
Guest Post: A Graph-Based Approach to Cyber Threat Intelligence
Exploring LLMs for Cybersecurity: Our ICAART 2024 Extension Paper
We’re excited to share our new ICAART extension paper, published in the Lecture Notes in Artificial Intelligence series. The paper explores how Large Language Models (LLMs) can be leveraged as agents for network security testing, outperforming traditional reinforcement learning methods in several scenarios. This research, including the introduction of our new NetSecGame environment, demonstrates the promise of LLMs in cybersecurity applications.
New Slips version v1.1.10 is here!
New Slips version v1.1.9 is here!
New Slips version v1.1.8 is here!
New Slips version v1.1.7 is here!
Introducing ARACNE, a new LLM-based shell pentesting agent
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.
New Slips version v1.1.6 is here!
New Slips version v1.1.5 is here!
New Slips version v1.1.4 is here!
New Slips version v1.1.3 is here!
AIP v3.0.0 is Here!
New Slips version v1.1.2 is here!
New Slips version v1.1.1 is here!
Czech Technical University in Prague’s "Introduction to Security" Class is now a Free Online Course!
Towards Better Understanding of Cybercrime: The Role of Fine-Tuned LLMs in Translation
Our paper explores the use of Large Language Models as mechanisms to translate public hacktivists messages from Russian to English as a way to address all these problems. We show how our method can achieve high-fidelity translations and significantly reduce costs by a factor ranging from 430 to 23,000 compared to a human translator.
New Slips version v1.1 is here!
Best Short Paper Award at AD&D Workshop EURO S&P!
We are thrilled to announce that our student, Muris Sladić, won the Best Short Paper Award at the 3rd Workshop on Active Defense and Deception (AD&D) last week. The workshop took place in Vienna, as part of the EURO S&P Annual conference.
Shoutout To NLnet Foundation, Our Continuous Supporter!
Since the start of the Stratosphere Laboratory more than 11 years ago, we have always struggled to fund our free software development projects that were aimed at helping the privacy and security of the Internet. And this is where the NLnet foundation came to help us.