Deep learning has become a cornerstone of modern artificial intelligence, enabling transformative applications across a wide range of domains. As the core element of deep learning, the quality and security of training data critically influence model performance and reliability. However, during the training process, deep learning models face the significant threat of data poisoning, where attackers introduce maliciously manipulated training data to degrade model accuracy or lead to anomalous behavior. While existing surveys provide valuable insights into data poisoning, they generally adopt a broad perspective, encompassing both attacks and defenses, but lack a dedicated, in-depth analysis of poisoning attacks specifically in deep learning. In this survey, we bridge this gap by presenting a comprehensive and targeted review of data poisoning in deep learning. First, this survey categorizes data poisoning attacks across multiple perspectives, providing an in-depth analysis of their characteristics and underlying design princinples. Second, the discussion is extended to the emerging area of data poisoning in large language models(LLMs). Finally, we explore critical open challenges in the field and propose potential research directions to advance the field further. To support further exploration, an up-to-date repository of resources on data poisoning in deep learning is available at https://github.com/Pinlong-Zhao/Data-Poisoning.

翻译：深度学习已成为现代人工智能的基石，在众多领域实现了变革性应用。作为深度学习的核心要素，训练数据的质量与安全性对模型的性能和可靠性具有至关重要的影响。然而，在训练过程中，深度学习模型面临着数据投毒的严重威胁，攻击者通过引入恶意篡改的训练数据，以降低模型精度或导致异常行为。尽管现有综述为数据投毒提供了有价值的见解，但它们通常采用宽泛的视角，同时涵盖攻击与防御，而缺乏专门针对深度学习中毒攻击的深入分析。本综述通过呈现对深度学习数据投毒的全面且有针对性的回顾，以弥合这一差距。首先，本综述从多个角度对数据投毒攻击进行分类，深入分析其特征及背后的设计原理。其次，讨论延伸至大型语言模型（LLMs）中数据投毒这一新兴领域。最后，我们探讨了该领域关键的开放挑战，并提出了推动该领域进一步发展的潜在研究方向。为支持进一步探索，有关深度学习数据投毒的最新资源库可在 https://github.com/Pinlong-Zhao/Data-Poisoning 获取。