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, through the concept of entanglement. More specific, we define entanglement computationally and demonstrate that distant feature samples can exhibit strong correlations, akin to entanglement in quantum realm. This revelation challenges conventional perspectives in describing the phenomenon of adversarial transferability observed in contemporary machine learning models. By drawing parallels with the relativistic effects of time dilation and length contraction during computation, we gain deeper insights into adversarial machine learning, paving the way for more robust and interpretable models in this rapidly evolving field.

翻译：对抗性样本因能以看似微小的输入扰动欺骗机器学习模型，从而可能引发严重后果，已成为研究焦点。本研究对对抗性机器学习模型展开全面探索，揭示其内在复杂性与可解释性。我们的研究通过纠缠概念，揭示了机器学习模型复杂度与爱因斯坦狭义相对论之间的有趣联系。具体而言，我们定义了计算纠缠，并证明远端特征样本之间可呈现类似于量子领域中纠缠的强相关性。这一发现挑战了描述当代机器学习模型中对抗性迁移性现象的传统观点。通过将计算过程中的时间膨胀与长度收缩等相对论效应进行类比，我们得以更深入地理解对抗性机器学习，从而为这一快速发展领域构建更鲁棒且可解释的模型铺平道路。