mlsanityData to 7 Oct 2026

Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms

arXiv 2408.07558 ↗First posted 14 Aug 2024cs.CR cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Data poisoning attacks on clustering algorithms have received limited attention, with existing methods struggling to scale efficiently as dataset sizes and feature counts increase. These attacks typically require re-clustering the entire dataset multiple times to generate predictions and assess the attacker's objectives, significantly hindering their scalability. This paper addresses these limitations by proposing Sonic, a novel genetic data poisoning attack that leverages incremental and scalable clustering algorithms, e.g., FISHDBC, as surrogates to accelerate poisoning attacks against graph-based and density-based clustering methods, such as HDBSCAN. We empirically demonstrate the effectiveness and efficiency of Sonic in poisoning the target clustering algorithms. We then conduct a comprehensive analysis of the factors affecting the scalability and transferability of poisoning attacks against clustering algorithms, and we conclude by examining the robustness of hyperparameters in our attack strategy Sonic.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 59 references that are in the map. First posted on arXiv 14 Aug 2024.

Builds on

19 of 59 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  6. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  7. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  8. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  9. 2023Poisoning Web-Scale Training Datasets is Practicalcited by 276
  10. 2016Variational Deep Embedding: An Unsupervised and Generative Approach to Clusteringcited by 219
  11. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  12. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
7 more
  1. 2018Deep k-Means: Jointly clustering with k-Means and learning representationscited by 50
  2. 2022Machine Learning Security against Data Poisoning: Are We There Yet?cited by 23
  3. 2018Is Data Clustering in Adversarial Settings Secure?cited by 16
  4. 2020A black-box adversarial attack for poisoning clusteringcited by 16
  5. 2024AttackBench: Evaluating Gradient-based Attacks for Adversarial Examplescited by 14
  6. 2019Suspicion-Free Adversarial Attacks on Clustering Algorithmscited by 11
  7. 2019FISHDBC: Flexible, Incremental, Scalable, Hierarchical Density-Based Clustering for Arbitrary Data and Distancecited by 4

Built on by

Not cited yet.