2DSig-Detect: a semi-supervised framework for anomaly detection on image data using 2D-signatures
Not on the map. Why?
Abstract (arXiv)
The rapid advancement of machine learning technologies raises questions about the security of machine learning models, with respect to both training-time (poisoning) and test-time (evasion, impersonation, and inversion) attacks. Models performing image-related tasks, e.g. detection, and classification, are vulnerable to adversarial attacks that can degrade their performance and produce undesirable outcomes. This paper introduces a novel technique for anomaly detection in images called 2DSig-Detect, which uses a 2D-signature-embedded semi-supervised framework rooted in rough path theory. We demonstrate our method in adversarial settings for training-time and test-time attacks, and benchmark our framework against other state of the art methods. Using 2DSig-Detect for anomaly detection, we show both superior performance and a reduction in the computation time to detect the presence of adversarial perturbations in images.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 59 references that are in the map. First posted on arXiv 8 Sep 2024.
Builds on
32 of 59 references.
References · 32
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2016Adversarial examples in the physical worldcited by 1,769
- 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
- 2016Adversarial Machine Learning at Scalecited by 936
20 more
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
- 2017One pixel attack for fooling deep neural networkscited by 582
- 2018Spectral Signatures in Backdoor Attackscited by 484
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
- 2019On Evaluating Adversarial Robustnesscited by 447
- 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
- 2017On the (Statistical) Detection of Adversarial Examplescited by 180
- 2018Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbationcited by 134
- 2021SPECTRE: Defending Against Backdoor Attacks Using Robust Statisticscited by 130
- 2021Backdoor Attacks on Self-Supervised Learningcited by 90
- 2015Adversarial Manipulation of Deep Representationscited by 56
- 2017Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reductioncited by 49
- 2019Deep Neural Rejection against Adversarial Examplescited by 32
- 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
- 2020Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifierscited by 23
- 2016Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognitioncited by 19
- 2017A signature-based machine learning model for bipolar disorder and borderline personality disordercited by 15
- 2020Dimensionless Anomaly Detection on Multivariate Streams with Variance Norm and Path Signaturecited by 8
- 2024Novelty Detection on Radio Astronomy Data using Signaturescited by 4
- 20222-d signature of images and texture classificationcited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.
- 2025Tensor-to-Tensor Models with Fast Iterated Sum Featurescited by 0
- 2025Tensor-to-Tensor Models with Fast Iterated Sum Features6 Jun 2025