Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916357251006464 |
|---|---|
| author | Villani, Francesco Lazzaro, Dario Cinà, Antonio Emanuele Dell'Amico, Matteo Biggio, Battista Roli, Fabio |
| author_facet | Villani, Francesco Lazzaro, Dario Cinà, Antonio Emanuele Dell'Amico, Matteo Biggio, Battista Roli, Fabio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07558 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms Villani, Francesco Lazzaro, Dario Cinà, Antonio Emanuele Dell'Amico, Matteo Biggio, Battista Roli, Fabio Cryptography and Security Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms |
| topic | Cryptography and Security Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2408.07558 |