Research map / Adversarial robustness and security / Black-box and transfer attacks
Suspicion-Free Adversarial Attacks on Clustering Algorithms
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Perturb one boundary-near sample under the black-box attack | Ward's Hierarchical clustering · UCI Digits, 1 vs 4 | misclustered samples: 24 | Helped |
| Perturb one boundary-near sample under the black-box attack | Ward's Hierarchical clustering · UCI Digits, 8 vs 9 | misclustered samples: 21 | Helped |
| Perturb one boundary-near sample under the black-box attack | Ward's Hierarchical clustering · MNIST, 1 vs 4 | misclustered samples: 11 | Helped |
| Perturb one boundary-near sample under the black-box attack | Ward's Hierarchical clustering · MNIST, 2 vs 3 | misclustered samples: 2 | Helped |
| Perturb one target sample while constraining it not to appear as an outlier | K-Means · UCI Wheat Seeds, Rosa vs Kama | spill-over samples: 2 | Helped |
| Perturb one target sample while constraining it not to appear as an outlier | K-Means · MoCap Hand Postures, Grab vs Point1 | spill-over samples: 5 | Helped |
Closest papers by meaning
- On the Robustness of Deep Clustering Models: Adversarial Attacks and Defenses (NeurIPS 2022 · similarity 0.91)
- On the Adversarial Robustness of Multi-Kernel Clustering (ICML 2025 · similarity 0.87)
- Adversarially Robust Deep Multi-View Clustering: A Novel Attack and Defense Framework (ICML 2024 · similarity 0.87)
- Robust Mixture Learning when Outliers Overwhelm Small Groups (NeurIPS 2024 · similarity 0.84)
- Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis (CVPR 2025 · similarity 0.84)
- BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.