RF-PUF: Enhancing IoT Security Through Authentication of Wireless Nodes Using In-Situ Machine Learning
RF-PUF: Enhancing IoT Security Through Authentication of Wireless Nodes Using In-Situ Machine Learning
复制标题
DOI：
10.1109/jiot.2018.2849324
复制
发表时间：
2019-02-01
影响因子：
10.6
通讯作者：
Sen, Shreyas
中科院分区：
文献类型：
--
作者：
Chatterjee, Baibhab;Das, Debayan;Sen, Shreyas
射频（RF）系统中的传统认证通过数字签名和基于散列的消息认证码（HMAC）等技术实现网络内的安全数据通信，这些技术会受到密钥恢复攻击。最先进的物联网网络（如Nest）也使用开放式身份验证（OAuth 2.0）协议，这些协议容易受到跨站点恢复伪造（CSRF）的攻击，这表明这些技术可能无法阻止对手使用入侵，侧信道，学习或软件攻击复制或建模秘密ID或加密密钥。另一方面，物理不可克隆功能（PUFS）可以利用制造工艺变化来唯一识别硅芯片，这使得基于PUFS的系统以低成本极其强大和安全，因为实际上不可能在管芯上复制相同的硅特征。从人类通信中汲取灵感，利用语音签名中的固有变化来识别某个说话者，我们提出了RF-PUF：一种基于深度神经网络的框架，可以使用固有过程变化对无线发射机（Tx）的RF属性的影响，对无线节点进行实时身份验证，通过接收机（Rx）端的原位机器学习检测。所提出的方法利用了现有的非对称RF通信框架，并且不需要任何额外的电路用于PUF生成或特征提取。设备识别的负担完全转移到网关Rx，类似于人类听众大脑的操作。涉及标准65-nm技术节点中的工艺变化的仿真结果，以及利用在隐藏层中具有50个神经元的神经网络检测到的诸如本地振荡器偏移和I-Q不平衡的特征表明，该框架可以在不同的信道条件下以99.9%的准确度区分高达4800个Tx（s）[对于10 000个Tx（s）近似99%]，并且不需要传统的密码。该方案可以作为一个独立的安全功能，或作为传统的多因素认证的一部分。
Traditional authentication in radio-frequency (RF) systems enable secure data communication within a network through techniques such as digital signatures and hash-based message authentication codes (HMAC), which suffer from key-recovery attacks. State-of-the-art Internet of Things networks such as Nest also use open authentication (OAuth 2.0) protocols that are vulnerable to cross-site-recovery forgery (CSRF), which shows that these techniques may not prevent an adversary from copying or modeling the secret IDs or encryption keys using invasive, side channel, learning or software attacks. Physical unclonable functions (PUFs), on the other hand, can exploit manufacturing process variations to uniquely identify silicon chips which makes a PUF-based system extremely robust and secure at low cost, as it is practically impossible to replicate the same silicon characteristics across dies. Taking inspiration from human communication, which utilizes inherent variations in the voice signatures to identify a certain speaker, we present RF-PUF: a deep neural network-based framework that allows real-time authentication of wireless nodes, using the effects of inherent process variation on RF properties of the wireless transmitters (Tx), detected through in-situ machine learning at the receiver (Rx) end. The proposed method utilizes the already-existing asymmetric RF communication framework and does not require any additional circuitry for PUF generation or feature extraction. The burden of device identification is completely shifted to the gateway Rx, similar to the operation of a human listener's brain. Simulation results involving the process variations in a standard 65-nm technology node, and features such as local oscillator offset and I-Q imbalance detected with a neural network having 50 neurons in the hidden layer indicate that the framework can distinguish up to 4800 Tx(s) with an accuracy of 99.9% [approximate to 99% for 10 000 Tx(s)] under varying channel conditions, and without the need for traditional preambles. The proposed scheme can be used as a stand-alone security feature, or as a part of traditional multifactor authentication.