通过插入交换门破坏量子神经网络，实现隐蔽的电路级攻击
SQUASH: A SWAP-Based Quantum Attack to Sabotage Hybrid Quantum Neural Networks
- 在变分量子电路中插入交换门，直接扰乱量子态演化
- 非定向攻击使分类准确率下降74.08%，定向攻击使目标类准确率下降79.78%
- 无需训练数据或输入扰动，隐蔽性强，适合研究量子安全的学者
我们提出一种电路级攻击SQUASH（SWAP-Based Quantum Attack），用于破坏用于分类任务的混合量子神经网络（HQNN）。SQUASH通过在受害HQNN的变分量子电路中插入一个或多个交换门来实施攻击。与传统的噪声或对抗性输入攻击不同，SQUASH直接操纵电路结构，导致量子比特错位并干扰量子态演化。该攻击高度隐蔽，无需访问训练数据，也不会在输入态中引入可检测的扰动。实验结果表明，SQUASH显著降低分类性能：非定向交换攻击使准确率下降高达74.08%，定向交换攻击使目标类别准确率下降高达79.78%。这些发现揭示了HQNN实现中的关键脆弱性，凸显了对更具鲁棒性的架构以抵御电路级对抗干预的迫切需求。
原文摘要 · Abstract (English)
We propose a circuit-level attack, SQUASH, a SWAP-Based Quantum Attack to sabotage Hybrid Quantum Neural Networks (HQNNs) for classification tasks. SQUASH is executed by inserting SWAP gate(s) into the variational quantum circuit of the victim HQNN. Unlike conventional noise-based or adversarial input attacks, SQUASH directly manipulates the circuit structure, leading to qubit misalignment and disrupting quantum state evolution. This attack is highly stealthy, as it does not require access to training data or introduce detectable perturbations in input states. Our results demonstrate that SQUASH significantly degrades classification performance, with untargeted SWAP attacks reducing accuracy by up to 74.08\% and targeted SWAP attacks reducing target class accuracy by up to 79.78\%. These findings reveal a critical vulnerability in HQNN implementations, underscoring the need for more resilient architectures against circuit-level adversarial interventions.
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。