Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918383309553664 |
|---|---|
| author | Høyheim, Eirik Eckhoff, Magnus Wiik Grov, Gudmund Flood, Robert Aspinall, David |
| author_facet | Høyheim, Eirik Eckhoff, Magnus Wiik Grov, Gudmund Flood, Robert Aspinall, David |
| contents | 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. We present promising experimental evidence of our approach, which involves injecting backdoors into a machine learning model used for intrusion detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10641 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection Høyheim, Eirik Eckhoff, Magnus Wiik Grov, Gudmund Flood, Robert Aspinall, David Cryptography and Security Artificial Intelligence Machine Learning 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. We present promising experimental evidence of our approach, which involves injecting backdoors into a machine learning model used for intrusion detection. |
| title | Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection |
| topic | Cryptography and Security Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.10641 |