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

Authors: Eirik Høyheim, Magnus Wiik Eckhoff, Gudmund Grov, Robert Flood, David Aspinall
Published: 2026-03-11

Source: https://arxiv.org/abs/2603.10641

PDF: https://arxiv.org/pdf/2603.10641

AIにより推定されたラベル

バックドア攻撃 評価手法 データ毒性

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

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 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. We present promising experimental evidence of our approach, which involves injecting backdoors into a machine learning model used for intrusion detection.