The proliferation of sensitive information being stored online highlights the pressing need for secure and efficient user authentication methods. To address this issue, this paper presents a novel zero-effort two-factor authentication (2FA) approach that combines the unique characteristics of a users environment and Machine Learning (ML) to confirm their identity. Our proposed approach utilizes Wi-Fi radio wave transmission and ML algorithms to analyze beacon frame characteristics and Received Signal Strength Indicator (RSSI) values from Wi-Fi access points to determine the users location. The aim is to provide a secure and efficient method of authentication without the need for additional hardware or software. A prototype was developed using Raspberry Pi devices and experiments were conducted to demonstrate the effectiveness and practicality of the proposed approach. Results showed that the proposed system can significantly enhance the security of sensitive information in various industries such as finance, healthcare, and retail. This study sheds light on the potential of Wi-Fi radio waves and RSSI values as a means of user authentication and the power of ML to identify patterns in wireless signals for security purposes. The proposed system holds great promise in revolutionizing the field of 2FA and user authentication, offering a new era of secure and seamless access to sensitive information.

翻译：敏感信息在线存储的普及凸显了对安全高效用户认证方法的迫切需求。针对此问题，本文提出一种新颖的零努力双因素认证（2FA）方法，该方法结合用户环境的独有特征与机器学习（ML）来验证其身份。所提方法利用Wi-Fi无线电波传输及ML算法，通过分析来自Wi-Fi接入点的信标帧特征与接收信号强度指示（RSSI）值来确定用户位置，旨在无需额外硬件或软件即可提供安全高效的认证手段。研究采用树莓派设备构建原型系统，并通过实验验证了所提方法的有效性与实用性。结果表明，该系统能显著提升金融、医疗及零售等行业敏感信息的安全性。本研究揭示了Wi-Fi无线电波与RSSI值作为用户认证手段的潜力，以及ML在识别无线信号模式以保障安全方面的强大能力。所提系统有望革新双因素认证与用户认证领域，开启安全无缝访问敏感信息的新纪元。