SUTD researchers have developed a new hardware security device to ensure that data is protected and secured from sophisticated cyber attacks.
Data breaches are increasing exponentially as more and more data are being shared and stored digitally. Because of this, it is crucial that data must be protected and secured from increasingly sophisticated cyber attacks. Scientists, led by Assistant Professor Desmond Loke from the Singapore University of Technology and Design (SUTD), have now developed a new type of hardware security device, that is scalable, reconfigurable, and has high resilience to Artificial Intelligence attacks. The device is based on phase-change materials and is set to be more energy-efficient and more secure against AI attacks than traditional devices used.
The study, titled ‘Ultrafast near-ideal phase-change memristive physical unclonable functions driven by amorphous state variations,’ is published in the journal Advanced Science.
A new hardware security device to protect against security attacks
The researchers developed a device, called the physical unclonable function (PUF), that is scalable, more energy-efficient, and secure against AI attacks compared to traditional silicon PUFs. This new type of phase-change PUF has these advantages due to the electrical and physical properties of phase-change materials, along with the fabrication process.
The team created a group of phase-change devices that switch between the glassy amorphous state and the crystal orderly state. The variation in the device’s electrical conductance was then used by the scientists to construct the PUF due to the inherent randomness arising from the manufacturing process. This is not shown by conventional silicon-based devices.
Dr Loke commented: “We developed a novel hardware security device that can eventually be implemented to protect data across sectors and industries, as breaches in private data have been ever-increasing.”
The new hardware security device was modelled on the characteristics of actual phase-change devices to generate a simulation of many more phase-change-based PUFs. Machine Learning was then used by the team to test the PUF’s security. The researchers trained the AI with the phase-change PUF simulation data to see if the AI could make predictions about the encrypted key and reveal system insecurities.
Future uses of the new device
Dr Loke said: “Normal humans are not able to develop a model from a vast amount of data, but neural networks could. We also found that it was not possible for the encryption process to be learned and that the AI could not develop a model to decrypt the phase-change PUF.”
This resistance to Machine Learning attacks makes the PUF more secure, as potential hackers cannot use the ‘stolen’ key to reverse engineer a device for future use. The new hardware security device developed by the researchers can also create a new key immediately through the reconfiguration mode if the key is hacked.
Due to the device’s capacity to operate at high temperatures, there is an opportunity for use in a variety of applications. Future research can pave a way for its use in household devices, printable and flexible electronics, and other devices.
