Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection

ArXi:2603.10641v1 Announce Type: cross 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 $\textit{trigger}$, it behaves as the attacker desires. Detecting such triggers has been proven to be extremely difficult. In this paper, we present a novel and explainable approach to detect and eliminate such backdoor triggers based on active paths found in neural networks.