# Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks

arXiv: https://arxiv.org/abs/2212.08121 · HTML: https://mlsanity.com/paper/2212.08121/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 15 Dec 2022.

## Builds on (most cited first, 10 of 10)

- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [STRIP: A Defence Against Trojan Attacks on Deep Neural Networks](https://mlsanity.com/paper/1902.06531/) (2019)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [Image Captioning with Semantic Attention](https://mlsanity.com/paper/1603.03925/) (2016)
- [BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements](https://mlsanity.com/paper/2006.01043/) (2020)
- [SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems](https://mlsanity.com/paper/1812.00292/) (2018)
- [Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs](https://mlsanity.com/paper/1906.10842/) (2019)
- [Fake News Detection on Social Media using Geometric Deep Learning](https://mlsanity.com/paper/1902.06673/) (2019)
- [BadDet: Backdoor Attacks on Object Detection](https://mlsanity.com/paper/2205.14497/) (2022)

## Built on by (most cited first, 3 of 3)

- [A Red Teaming Framework for Securing AI in Maritime Autonomous Systems](https://mlsanity.com/paper/2312.11500/) (2023)
- [Advancing Security in AI Systems: A Novel Approach to Detecting Backdoors in Deep Neural Networks](https://mlsanity.com/paper/2403.08208/) (2024)
- [Trojan horse hunt in deep forecasting models: Insights from the European Space Agency competition](https://mlsanity.com/paper/2603.20108/) (2026)

## Abstract (arXiv)

The increasing importance of both deep neural networks (DNNs) and cloud services for training them means that bad actors have more incentive and opportunity to insert backdoors to alter the behavior of trained models. In this paper, we introduce a novel method for backdoor detection that extracts features from pre-trained DNN's weights using independent vector analysis (IVA) followed by a machine learning classifier. In comparison to other detection techniques, this has a number of benefits, such as not requiring any training data, being applicable across domains, operating with a wide range of network architectures, not assuming the nature of the triggers used to change network behavior, and being highly scalable. We discuss the detection pipeline, and then demonstrate the results on two computer vision datasets regarding image classification and object detection. Our method outperforms the competing algorithms in terms of efficiency and is more accurate, helping to ensure the safe application of deep learning and AI.