It wasn’t too long ago that Meltdown and Scepter were able to exploit vulnerabilities in some Intel and AMD processors, and more recently with the SPOILER vulnerability that attacks microarchitectures in some Core chips. Suffice it to say, having a hack-proof processor would benefit all of us from unwanted intrusion, and some engineers from the University of Michigan have designed a chip they deem “unhackable.”
Called MORPHEUS, the new architecture proactively defends against threats, with the engineers stating that it could render current electronic security methods of patching bugs obsolete. MORPHEUS protects its system from potential attacks by randomly shuffling bits of code and data, and repeating the process every 50-milliseconds or 20 times every second. Even if a hacker finds a bug or vulnerability within the code, it disappears milliseconds later.
The process is known as “churning,” which the processor uses to randomize critical program assets continually. Think of it like a Rubik’s cube that rearranges itself in the blink of an eye. The process does consume resources though, but users can adjust the churn rate to strike a balance between those resources and security.
The engineers demonstrated MORPHEUS’ capabilities at the 24th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) in Providence, Rhode Island back in April using a RISC-V-based processor. It was successful at thwarting every known variant of the control-flow attack, which hackers employ to gain access to the architecture. The engineers would like to see MORPHEUS processors in everything from home PCs to IoT devices, providing a sense of security to consumers who rely on secure systems and data protection.