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

arXiv: https://arxiv.org/abs/2603.10641 · HTML: https://mlsanity.com/paper/2603.10641/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Adversarial Neuron Pruning Purifies Backdoored Deep Models](https://mlsanity.com/paper/2110.14430/) (2021)
- [Detecting AI Trojans Using Meta Neural Analysis](https://mlsanity.com/paper/1910.03137/) (2019)
- [Knowledge Editing for Large Language Models: A Survey](https://mlsanity.com/paper/2310.16218/) (2023)
- [Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review](https://mlsanity.com/paper/2007.10760/) (2020)
- [RAB: Provable Robustness Against Backdoor Attacks](https://mlsanity.com/paper/2003.08904/) (2020)
- [Planting Undetectable Backdoors in Machine Learning Models](https://mlsanity.com/paper/2204.06974/) (2022)
- [An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences](https://mlsanity.com/paper/2111.08429/) (2021)
- [The Mirage of Model Editing: Revisiting Evaluation in the Wild](https://mlsanity.com/paper/2502.11177/) (2025)
- [BadActs: A Universal Backdoor Defense in the Activation Space](https://mlsanity.com/paper/2405.11227/) (2024)
- [Maintainable Log Datasets for Evaluation of Intrusion Detection Systems](https://mlsanity.com/paper/2203.08580/) (2022)
- [Demystifying Poisoning Backdoor Attacks from a Statistical Perspective](https://mlsanity.com/paper/2310.10780/) (2023)
- [Verifying Neural Networks Against Backdoor Attacks](https://mlsanity.com/paper/2205.06992/) (2022)
- [Oblivious Defense in ML Models: Backdoor Removal without Detection](https://mlsanity.com/paper/2411.03279/) (2024)
- [Walling up Backdoors in Intrusion Detection Systems](https://mlsanity.com/paper/1909.07866/) (2019)
- [Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks](https://mlsanity.com/paper/2503.10496/) (2025)

## Abstract (arXiv)

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 textittrigger, 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.