4 papers
Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection
Eirik Høyheim, Magnus Wiik Eckhoff, Gudmund Grov +2
Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific , it…
A Graph-Based Approach to Alert Contextualisation in Security Operations Centres
Magnus Wiik Eckhoff, Peter Marius Flydal, Siem Peters +4
Interpreting the massive volume of security alerts is a significant challenge in Security Operations Centres (SOCs). Effective contextualisation is important, enabling quick distin…
Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models
Ryan Marinelli, Magnus Eckhoff
To effectively deploy Large Language Models (LLMs) in application-specific settings, fine-tuning techniques are applied to enhance performance on specialized tasks. This process of…
On the use of neurosymbolic AI for defending against cyber attacks
Gudmund Grov, Jonas Halvorsen, Magnus Wiik Eckhoff +3
It is generally accepted that all cyber attacks cannot be prevented, creating a need for the ability to detect and respond to cyber attacks. Both connectionist and symbolic AI are…