mlsanityData to 7 Oct 2026

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

arXiv 2603.10641 ↗First posted 11 Mar 2026cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

18 of 31 references.

References · 18

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  2. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  3. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  4. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 230
  5. 2019Detecting AI Trojans Using Meta Neural Analysiscited by 192
  6. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  7. 2020Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Reviewcited by 120
  8. 2020RAB: Provable Robustness Against Backdoor Attackscited by 115
  9. 2022Planting Undetectable Backdoors in Machine Learning Modelscited by 55
  10. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 41
  11. 2025The Mirage of Model Editing: Revisiting Evaluation in the Wildcited by 24
  12. 2024BadActs: A Universal Backdoor Defense in the Activation Spacecited by 19
6 more
  1. 2022Maintainable Log Datasets for Evaluation of Intrusion Detection Systemscited by 10
  2. 2023Demystifying Poisoning Backdoor Attacks from a Statistical Perspectivecited by 10
  3. 2022Verifying Neural Networks Against Backdoor Attackscited by 5
  4. 2024Oblivious Defense in ML Models: Backdoor Removal without Detectioncited by 5
  5. 2019Walling up Backdoors in Intrusion Detection Systemscited by 3
  6. 2025Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networkscited by 1

Built on by

Not cited yet.