AI Sweden forms an AI & Security Consortium

Wednesday, October 16, 2024

AI Sweden is establishing an AI & Security Consortium, building on the success of the Edge Learning Consortium and leveraging both new and ongoing projects in the security domain.

Both the new project on smart honeypots and LeakPro, an ongoing project, will be part of a larger effort to enhance AI & Security.

"Our Edge Learning Consortium is a great success, where partners with a shared interest in edge learning joined forces and created new knowledge, tools, and methods. We are now building on the infrastructure, know-how and capacity from that consortium and the work done in Large Language Models at AI Sweden to make a major impact in the AI and security domain," says Dr. Mats Nordlund, Director of AI Labs at AI Sweden. He continues:

"Since 2021, AI and security have been part of the work in our Edge Learning Lab, following recommendations from our advisory board. We are now further accelerating our efforts in this area, under the umbrella AI & Security, as the intersection of AI and security is becoming increasingly critical for many of our partners. This includes new projects aimed at making AI itself more robust and secure, as well as exploring how AI can be leveraged to enhance security in other domains. Our work on adaptive honeypots is one example of the latter."

Dr. Mats Nordlund
Director of AI Labs at AI Sweden

Launching soon

The new AI & Security Consortium, with its focus on AI & Security, aims to launch early in 2025.

“To help with this, AI Sweden has recruited international experts that will complement and strengthen our existing team. AI and security is a global challenge, and adding international expertise to the team makes sure we are a leader in the field.”

For more information, contact

Beatrice Comoli

Administrative Lead Data Factory

beatrice.comoli@ai.se

+46 (0)70-146 09 64

Dr. Robert (Bobby) Bridges calculating and writing on a whiteboard

Using large language models to outsmart cyber attackers

2024-10-16

Can AI adapt honeypots to produce more threat intelligence by eliciting greater interaction from attackers? That question will be investigated through an innovative collaboration between Volvo Group...

A collage with two portraits: Mauricio Muñoz and Dr. Robert (Bobby) Bridges

Two international AI experts strengthen AI Sweden's efforts in security and automotive

2024-09-12

The recruitment of two international AI experts strengthens AI Sweden's capabilities. "I'm delighted to welcome both Dr. Robert (Bobby) Bridges and Mauricio Muñoz to AI Sweden. They bring years of...

Johan Östman and Fazeleh Hoseini, Research engineers at AI Sweden

When will an AI model reveal your sensitive data?

2024-06-05

AI models can leak training data–this is known. However, such leakage has mainly been observed in lab-like conditions that often favor the attacker. Today, there are few answers on what the risks look...

Golden honeycomb pattern on a computer component with a metallic shine

AI-Powered Honeypots

Honeypots are decoy computing systems that mimic real environments to trick attackers into revealing their tools. Can AI enhance honeypot deception to increase cybersecurity?

an icon showing a shield with incoming arrow, AI in the center and threat being dissolved into stars

LeakPro: Leakage profiling and risk oversight for machine learning models

Many recent works have highlighted the possibility of extracting data from trained machine-learning models. However, these examples are typically performed under idealistic conditions and it is...

About AI Labs