研究人员开发了量子掩码自编码器（QMAEs），能够学习量子态中缺失的特征，在图像重建任务中表现优于标准的量子自编码器。此外，一个新的防御框架利用量子自编码器在量子分类器中净化对抗性样本，无需对抗性训练，显著提高了受攻击下的预测准确性。该框架还包括一个置信度指标，用于识别无法净化的样本。 AI
影响 为机器学习模型中的特征学习和对抗鲁棒性引入了新的量子方法。
排序理由 该集群包含两篇arXiv论文，详细介绍了量子机器学习的新研究，特别是专注于用于特征学习和对抗防御的自编码器。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2511.17372v2 Announce Type: replace-cross Abstract: Classical autoencoders are widely used to learn features of input data. To improve the feature learning, classical masked autoencoders extend classical autoencoders to learn the features of the original input sample in the…
arXiv:2604.28176v1 Announce Type: cross Abstract: Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes.…
Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes. Quantum machine learning models are also vulnerab…