Access Type

Open Access Dissertation

Date of Award

January 2020

Degree Type

Dissertation

Degree Name

Ph.D.

Department

Computer Science

First Advisor

Fengwei . Zhang

Abstract

With the rapid proliferation of the ARM architecture on smart mobile phones and Internet of Things (IoT) devices, the security of ARM platform becomes an emerging problem. In recent years, the number of malware identified on ARM platforms, especially on Android, shows explosive growth. Evasion techniques are also used in these malware to escape from being detected by existing analysis systems.

In our research, we first present a software-based mechanism to increase the accuracy of existing static analysis tools by reassembleable bytecode extraction. Our solution collects bytecode and data at runtime, and then reassemble them offline to help static analysis tools to reveal the hidden behavior in an application.

Further, we implement a hardware-based transparent malware analysis framework for general ARM platforms to defend against the traditional evasion techniques. Our framework leverages hardware debugging features and Trusted Execution Environment (TEE) to achieve transparent tracing and debugging with reasonable overhead.

To learn the security of the involved hardware debugging features, we perform a comprehensive study on the ARM debugging features and summarize the security implications. Based on the implications, we design a novel attack scenario that achieves privilege escalation via misusing the debugging features in inter-processor debugging model.

The attack has raised our concern on the security of TEEs and Cyber-physical System (CPS). For a better understanding of the security of TEEs, we investigate the security of various TEEs on different architectures and platforms, and state the security challenges. A study of the deploying the TEEs on edge platform is also presented. For the security of the CPS, we conduct an analysis on the real-world traffic signal infrastructure and summarize the security problems.

Share

COinS