用量子计算加速检测数据投毒，提升防御效率
Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method
- 结合量子与经典计算，构建混合检测框架
- 在多个攻击场景下准确识别投毒样本，性能优于基线
- 理论预测可实现超20%的计算加速，适合大规模数据
数据投毒攻击通过在训练过程中注入恶意数据，严重威胁机器学习模型的性能与预测可靠性。检测并剔除投毒数据是防范此类攻击的重要手段。然而，传统经典计算框架在处理更大规模、更复杂的数据集时面临计算瓶颈。本文首次将量子计算的速度优势引入数据投毒检测任务，提出 Q-Detection——一种量子-经典混合防御方法。该方法引入基于量子计算优化的 Q-WAN 模型。实验结果表明，使用多种量子模拟库验证，Q-Detection 能有效抵御标签篡改和后门攻击。评估指标显示，其性能持续优于基线方法，并接近当前最先进水平。理论分析表明，借助量子计算能力，该方法预计可实现超过20%的计算加速。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。