研究人员开发了Q-DIBA，这是首个专门针对量子神经网络（QNN）设计的、具有输入感知能力的动态后门攻击。这种新颖的攻击为每个输入生成独特的触发器，克服了先前固定触发器攻击更容易被检测到的局限性。Q-DIBA在MNIST和Fashion-MNIST数据集上的实验中展示了其有效性和隐蔽性，证明了其对常见防御措施的抵抗力，并突显了对QNN部署的重大安全威胁。 AI
影响 凸显了量子神经网络中的一种新的安全漏洞，可能影响其采用并需要新的防御机制。
排序理由 该集群描述了一篇详细介绍针对量子神经网络的新型攻击方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2607.11843v1 Announce Type: cross Abstract: Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to backdoor…
Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to backdoor attacks, yet existing quantum backdoors mostly re…
Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to backdoor attacks, yet existing quantum backdoors mostly re…
Quantum neural network backdoor attack adapts per input Researchers propose Q-DIBA, a backdoor attack generating a unique trigger for each input to quantum neural networks, evading three tested defenses. https://www. notatechguy.com/quantum-neural -network-backdoor-attack-adapts-…