3 papers
cs.CR2026
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…
cs.CR2025
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…
cs.CR2025
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…