Adversarial examples in machine learning has emerged as a focal point of research due to their remarkable ability to deceive models with seemingly inconspicuous input perturbations, potentially resulting in severe consequences. In this study, we embark on a comprehensive exploration of adversarial machine learning models, shedding light on their intrinsic complexity and interpretability. Our investigation reveals intriguing links between machine learning model complexity and Einstein's theory of special relativity, all through the lens of entanglement. While our work does not primarily center on quantum entanglement, we instead define the entanglement correlations we have discovered to be computational, and demonstrate that distant feature samples can be entangled, strongly resembling entanglement correlation in the quantum realm. This revelation bestows fresh insights for understanding the phenomenon of emergent adversarial examples in modern machine learning, potentially paving the way for more robust and interpretable models in this rapidly evolving field.

翻译：机器学习中的对抗样本因其能以看似微不足道的输入扰动欺骗模型并可能引发严重后果而成为研究焦点。本研究对对抗机器学习模型进行了全面探索，揭示了其内在的复杂性与可解释性。我们的研究发现，通过纠缠的视角，机器学习模型的复杂度与爱因斯坦的狭义相对论之间存在引人入胜的联系。虽然本工作并非主要关注量子纠缠，但我们将其发现的纠缠关联定义为计算纠缠，并证明远距离特征样本可以发生纠缠，与量子领域的纠缠关联高度相似。这一发现为理解现代机器学习中突现的对抗样本现象提供了全新视角，有望为该快速发展的领域开辟构建更鲁棒、更可解释模型的路径。