mlsanityData to 14 Oct 2026

Universal Detection of Backdoor Attacks via Density-based Clustering and Centroids Analysis

arXiv 2301.04554 ↗First posted 11 Jan 2023cs.CV cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

We propose a Universal Defence against backdoor attacks based on Clustering and Centroids Analysis (CCA-UD). The goal of the defence is to reveal whether a Deep Neural Network model is subject to a backdoor attack by inspecting the training dataset. CCA-UD first clusters the samples of the training set by means of density-based clustering. Then, it applies a novel strategy to detect the presence of poisoned clusters. The proposed strategy is based on a general misclassification behaviour observed when the features of a representative example of the analysed cluster are added to benign samples. The capability of inducing a misclassification error is a general characteristic of poisoned samples, hence the proposed defence is attack-agnostic. This marks a significant difference with respect to existing defences, that, either can defend against only some types of backdoor attacks, or are effective only when some conditions on the poisoning ratio or the kind of triggering signal used by the attacker are satisfied. Experiments carried out on several classification tasks and network architectures, considering different types of backdoor attacks (with either clean or corrupted labels), and triggering signals, including both global and local triggering signals, as well as sample-specific and source-specific triggers, reveal that the proposed method is very effective to defend against backdoor attacks in all the cases, always outperforming the state of the art techniques.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 29 of its 58 references that are in the map. First posted on arXiv 11 Jan 2023.

Builds on

29 of 58 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  5. 2016Adversarial examples in the physical worldcited by 1,769
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  7. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  8. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  9. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  10. 2016Adversarial Machine Learning at Scalecited by 936
  11. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  12. 2018Spectral Signatures in Backdoor Attackscited by 484
17 more
  1. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
  2. 2019Label-Consistent Backdoor Attackscited by 296
  3. 2014One weird trick for parallelizing convolutional neural networkscited by 264
  4. 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 246
  5. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 242
  6. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 169
  7. 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 151
  8. 2021SPECTRE: Defending Against Backdoor Attacks Using Robust Statisticscited by 130
  9. 2019Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detectioncited by 124
  10. 2020RAB: Provable Robustness Against Backdoor Attackscited by 118
  11. 2022How to Backdoor Diffusion Models?cited by 104
  12. 2022The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matricescited by 63
  13. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 42
  14. 2021Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networkscited by 40
  15. 2022On the Effectiveness of Adversarial Training against Backdoor Attackscited by 16
  16. 2021A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verificationcited by 10
  17. 2022A temporal chrominance trigger for clean-label backdoor attack against anti-spoof rebroadcast detectioncited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 2.

5 papers.

  1. 2025CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networkscited by 1
  2. 2026Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learningcited by 1
  3. 2024Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Featurescited by 0
  4. 2025TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attackscited by 0
  5. 2026When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks
  2. 2026CSC: Turning the Adversary's Poison against Itself
  3. 2022Detecting Backdoor Poisoning Attacks on Deep Neural Networks by Heatmap Clustering
  4. 2024Model-agnostic clean-label backdoor mitigation in cybersecurity environments
  5. 2021Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions
  6. 2023Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
  7. 2023UMD: Unsupervised Model Detection for X2X Backdoor Attacks
  8. 2022Circumventing Backdoor Defenses That Are Based on Latent Separability