Edge-based IoT devices have experienced phenomenal growth in recent years due to rapidly increasing demand in various emerging applications which typically utilize machine learning (ML) models such as Deep Neural Network (DNN) and demand low latency and low power consumption. To support the edge requirements, ML models have to support faster inference and less computation. Dynamic DNNs (D2NN) have been proposed to support low-latency and power-saving on edge devices by enabling conditional computations and context dependant activation of the network model for inference; saving computational time and edge resources, hence they are becoming popular for edge applications. In this paper, we show that D2NN are vulnerable to our novel adversarial attack, Dynamic DNN Adversarial attacks (DDAS). Unlike conventional adversarial attacks that target classification accuracy, DDAS targets the IoT device resources such as the battery, latency, and so on. We show that our attack is effective under various attack scenarios with a high attack success rate. We also provide a retraining scheme as a countermeasure to DDAS and show its effectiveness.

With the emergence of machine learning technology that supports the development of synthetic models, many new use cases and challenges are emerging in the fields of computer vision and security. The main model behind this technology is Generative Adversarial Networks (GANs), with their ability to model unknown distributions accurately and perform well in generating synthetic data such as images and videos. However, the application of this technology by the networking community has been lacking. Given this motivation, we introduce MirageNet; our vision for a GAN-based synthetic network traffic generation framework, which can automatically create synthetic network models of protocols, applications, and devices. With the potential to build many applications for privacy, security, and network optimization. In this paper, we present MiragePkt; the first component of MirageNet. It is a GAN-based model to synthetically generate network packets. We describe the different challenges, limitations, and solutions for generating synthetic network packets. Finally, we validate and evaluate the performance of our framework with the synthesizing DNS packets.

With the current significant penetration of mobile devices (i.e. smartphones and tablets) and the tremendous increase in the number of the corresponding mobile applications, they have become an indispensable part of our lives. Nowadays, there is a significant growth in the number of sensitive applications such as personal health applications, personal financial applications, home monitoring applications, etc. In addition, with the significant growth of Internet-of-Things (IoT) devices, smartphones and the corresponding applications are widely considered as the Internet gateways for these devices. Mobile devices mostly use wireless LANs (WLANs) (i.e., WiFi networks) as the prominent network interface to the Internet. However, due to the broadcast nature of WiFi links, wireless traffics are exposed to any eavesdropping adversary within the WLAN. Despite WiFi encryption, studies show that application usage information could be inferred from the encrypted wireless traffic. The leakage of this sensitive information is very serious issue that will significantly impact users' privacy and security. In addressing this privacy concern, we design and develop a lightweight programmable privacy framework, called PrivacyGuard. PrivacyGuard is inspired by the vision of pushing the Software Defined Network (SDN)-like paradigm all the way to wireless network edge, is designed to support of adopting privacy preserving policies to protect the wireless communication of the sensitive applications. In this paper, we demonstrate and evaluate a prototype of PrivacyGuard framework on Android devices showing the flexibility and efficiency of the framework.