Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method

TL;DR

Q-Detection leverages quantum computing to enhance the detection of data poisoning attacks in machine learning, offering faster and more effective defense mechanisms against malicious data manipulations.

Contribution

This paper introduces Q-Detection, the first quantum-classical hybrid method for detecting data poisoning, demonstrating improved speed and effectiveness over classical approaches.

Findings

Q-Detection outperforms baseline methods in detecting poisoning attacks.

Experimental results show effective defense against label manipulation and backdoor attacks.

Theoretical analysis indicates over 20% speedup with quantum computing.

Abstract

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.