Development and exploitation of technology have led to the further expansion and complexity of digital crimes. On the other hand, the growing volume of data and, subsequently, evidence is a severe challenge in digital forensics. In recent years, the application of machine learning techniques to identify and analyze evidence has been on the rise in different digital forensics domains. This paper offers a systematic literature review of the research published in major academic databases from January 2010 to December 2021 on the application of machine learning in digital forensics, which was not presented yet to the best of our knowledge as comprehensive as this. The review also identifies the domains of digital forensics and machine learning methods that have received the most attention in the previous papers and finally introduces remaining research gaps. Our findings demonstrate that image forensics has obtained the greatest benefit from using machine learning methods, compared to other forensic domains. Moreover, CNN-based models are the most important machine learning methods that are increasingly being used in digital forensics. We present a comprehensive mind map to provide a proper perspective for valuable analytical results. Furthermore, visual analysis has been conducted based on the keywords of the papers, providing different thematic relevance topics. This research will give digital forensics investigators, machine learning developers, security researchers, and enthusiasts a broad view of the application of machine learning in digital forensics.

翻译：技术的发展与滥用导致数字犯罪进一步扩大和复杂化。然而，数据量的持续增长以及随之而来的证据激增，给数字取证带来了严峻挑战。近年来，机器学习技术在识别和分析证据方面的应用在不同数字取证领域中日益增多。本文对2010年1月至2021年12月间发表在主要学术数据库中关于机器学习在数字取证中应用的研究进行了系统性文献综述，据我们所知，此前尚无如此全面的综述。该综述还识别了先前论文中受到最多关注的数字取证领域和机器学习方法，并最终指出了尚存的研究空白。我们的研究结果表明，与其他取证领域相比，图像取证从机器学习方法中获益最多。此外，基于CNN的模型是数字取证中应用日益增长的最重要的机器学习方法。我们提供了一张全面的思维导图，为有价值的分析结果提供了恰当视角。同时，我们基于论文关键词进行了可视化分析，生成了不同主题相关性话题。本研究将为数字取证调查人员、机器学习开发者、安全研究人员及爱好者提供关于机器学习在数字取证中应用的广阔视野。