Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912472259100672 |
|---|---|
| author | He, Haoqi Lin, Xiaokai Chen, Jiancai Xiao, Yan |
| author_facet | He, Haoqi Lin, Xiaokai Chen, Jiancai Xiao, Yan |
| contents | Data poisoning attacks pose significant threats to machine learning models by introducing malicious data into the training process, thereby degrading model performance or manipulating predictions. Detecting and sifting out poisoned data is an important method to prevent data poisoning attacks. Limited by classical computation frameworks, upcoming larger-scale and more complex datasets may pose difficulties for detection. We introduce the unique speedup of quantum computing for the first time in the task of detecting data poisoning. We present Q-Detection, a quantum-classical hybrid defense method for detecting poisoning attacks. Q-Detection also introduces the Q-WAN, which is optimized using quantum computing devices. Experimental results using multiple quantum simulation libraries show that Q-Detection effectively defends against label manipulation and backdoor attacks. The metrics demonstrate that Q-Detection consistently outperforms the baseline methods and is comparable to the state-of-the-art. Theoretical analysis shows that Q-Detection is expected to achieve more than a 20% speedup using quantum computing power. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06262 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method He, Haoqi Lin, Xiaokai Chen, Jiancai Xiao, Yan Cryptography and Security Artificial Intelligence Machine Learning Quantum Physics Data poisoning attacks pose significant threats to machine learning models by introducing malicious data into the training process, thereby degrading model performance or manipulating predictions. Detecting and sifting out poisoned data is an important method to prevent data poisoning attacks. Limited by classical computation frameworks, upcoming larger-scale and more complex datasets may pose difficulties for detection. We introduce the unique speedup of quantum computing for the first time in the task of detecting data poisoning. We present Q-Detection, a quantum-classical hybrid defense method for detecting poisoning attacks. Q-Detection also introduces the Q-WAN, which is optimized using quantum computing devices. Experimental results using multiple quantum simulation libraries show that Q-Detection effectively defends against label manipulation and backdoor attacks. The metrics demonstrate that Q-Detection consistently outperforms the baseline methods and is comparable to the state-of-the-art. Theoretical analysis shows that Q-Detection is expected to achieve more than a 20% speedup using quantum computing power. |
| title | Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method |
| topic | Cryptography and Security Artificial Intelligence Machine Learning Quantum Physics |
| url | https://arxiv.org/abs/2507.06262 |