论文标题
用于保护车载网络的对抗攻击系统
An Adversarial Attack Defending System for Securing In-Vehicle Networks
论文作者
论文摘要
在现代车辆中，有超过70个电子控制单元（ECU）。对于车载网络，ECU通过遵循标准通信协议（例如控制器区域网络（CAN））相互通信。但是，攻击者可以轻松地通过WLAN或蓝牙访问车载网络以妥协ECU。尽管建议使用用于确保车辆内网络的各种深度学习（DL）方法，但最近对对抗性示例的研究表明，攻击者很容易欺骗DL模型。在这项研究中，我们进一步探讨了车载网络中的对抗例子。我们首先发现并实施了两个对较长的短期内存（LSTM）基于车载网络中的基于短期内存（LSTM）的检测模型有害的对抗攻击模型。然后，我们提出了一个对抗性攻击系统（AADS），用于确保车载网络。具体而言，我们专注于车载网络中与制动器相关的ECU。我们的实验结果表明，对手可以以超过98％的成功率轻松地攻击基于LSTM的检测模型，而拟议的AADS可以达到99％以上的准确性，以检测对抗性攻击。
In a modern vehicle, there are over seventy Electronics Control Units (ECUs). For an in-vehicle network, ECUs communicate with each other by following a standard communication protocol, such as Controller Area Network (CAN). However, an attacker can easily access the in-vehicle network to compromise ECUs through a WLAN or Bluetooth. Though there are various deep learning (DL) methods suggested for securing in-vehicle networks, recent studies on adversarial examples have shown that attackers can easily fool DL models. In this research, we further explore adversarial examples in an in-vehicle network. We first discover and implement two adversarial attack models that are harmful to a Long Short Term Memory (LSTM)-based detection model used in the in-vehicle network. Then, we propose an Adversarial Attack Defending System (AADS) for securing an in-vehicle network. Specifically, we focus on brake-related ECUs in an in-vehicle network. Our experimental results demonstrate that adversaries can easily attack the LSTM-based detection model with a success rate of over 98%, and the proposed AADS achieves over 99% accuracy for detecting adversarial attacks.
