Device Identification in Multimedia Systems Based on DRAM Fingerprinting

Unique identification of devices brings new security challenges to privacy issues in intelligent multimedia systems. The device fingerprinting technology extracts fingerprints according to the hardware and software characteristics of the device, which can achieve long-term tracking of the device. The primary goal of device fingerprinting is to accurately and uniquely identify a device, which requires the generated fingerprints to have good stability. However, the fingerprints generated by existing fingerprinting technologies are not stable enough or change frequently, making it impossible to track the target device for a long time. In this paper, we propose a novel DRAM-based fingerprinting technique. The device fingerprint generated by our technique has high stability and can be used to track the device for a long time. We leverage the Rowhammer technique to repeatedly and quickly access a row in DRAM to get bit flips. We then construct a physical fingerprint of the device based on the locations of the collected bit flips. The evaluation results of the uniqueness and reliability of the physical fingerprint show that it can be used to distinguish devices with the same hardware and software configuration. The experimental results of device identification in laboratory settings show that our proposed technique can accurately identify the target device by establishing a fingerprint database for device matching. Even if the device modifies software-level parameters such as MAC address, IP address, or even reinstalls the operating system, we can accurately identify the target device. This demonstrates that our proposed fingerprinting technique can generate stable fingerprints that are not affected by software layer parameters, enabling the tracking of target devices for more than five months.