Adversarial Filters for Secure Modulation Classification
Adversarial Filters for Secure Modulation Classification
复制标题
DOI：
10.1109/ieeeconf53345.2021.9723329
复制
发表时间：
2020-08
期刊：
影响因子：
--
通讯作者：
A. Berian;K. Staab;N. Teku;G. Ditzler;T. Bose;R. Tandon
中科院分区：
文献类型：
--
作者：
A. Berian;K. Staab;N. Teku;G. Ditzler;T. Bose;R. Tandon
分类（MC）是对无线信号的调制格式进行分类的问题。在无线通信流水线中，MC是对接收信号执行的第一个操作，并且对于可靠解码至关重要。本文考虑的问题，安全MC，发射机（爱丽丝）希望最大限度地提高MC精度在一个合法的接收机（鲍勃），同时最小化MC精度在窃听者（夏娃）。这项工作介绍了新的对抗性学习技术的安全MC。我们提出了对抗滤波器，其中Alice使用精心设计的对抗滤波器来屏蔽传输的信号，可以最大限度地提高Bob的MC精度，同时最小化Eve的MC精度。我们提出了两种基于滤波的算法，即梯度上升滤波器（GAF），和快速梯度滤波方法（FGFM），具有不同程度的复杂性。我们提出的基于对抗过滤的方法显著优于加性对抗扰动（用于传统的机器学习（ML）社区和其他先前的安全MC工作），并具有其他几个理想的属性。具体地，GAF和FGFM算法是a）计算高效的（允许在Bob处的快速解码），B）功率高效的（在Alice处不需要过多的发射功率）;以及c）SNR高效的（即，即使在Bob处的低SNR值下也表现良好）。
Classification (MC) is the problem of classifying the modulation format of a wireless signal. In the wireless communications pipeline, MC is the first operation performed on the received signal and is critical for reliable decoding. This paper considers the problem of secure MC, where a transmitter (Alice) wants to maximize MC accuracy at a legitimate receiver (Bob) while minimizing MC accuracy at an eavesdropper (Eve). This work introduces novel adversarial learning techniques for secure MC. We present adversarial filters in which Alice uses a carefully designed adversarial filter to mask the transmitted signal, that can maximize MC accuracy at Bob while minimizing MC accuracy at Eve. We present two filtering-based algorithms, namely gradient ascent filter (GAF), and a fast gradient filter method (FGFM), with varying levels of complexity. Our proposed adversarial filtering-based approaches significantly outperform additive adversarial perturbations (used in the traditional machine-learning (ML) community and other prior works on secure MC) and have several other desirable properties. In particular, GAF and FGFM algorithms are a) computational efficient (allow fast decoding at Bob), b) power-efficient (do not require excessive transmit power at Alice); and c) SNR efficient (i.e., perform well even at low SNR values at Bob).