Morpheus: Securing CPUs with Entropy

Computers are supposed to be completely predictable. When you tell it to do something, it should do exactly that – over and over again, if necessary – in the same way, with the same result. This is the nature of computer programming. But this predictability can allow computer criminals to interrupt a computer’s processing and divert it to do nefarious things. If you know exactly where to poke the system, predicting where and how it does it’s processing, you can effectively rewire it to do your bidding. This is the basic attack methodology that lets bad guys insert their malware into our systems. But what if we were able to randomly perturb a computer’s processing on a periodic basis, making it effectively unpredictable? This is the essence of a new computer architecture called Morpheus that may one day make all of our computers and computerized devices much, much harder to hack. Today, Todd Austin will explain how this brilliant defense mechanism works and how it was inspired by the human body’s immune system.

Todd Austin is a Professor of Electrical Engineering and Computer Science at the University of Michigan in Ann Arbor. His research interests include computer architecture, robust and secure system design, hardware and software verification, and performance analysis tools and techniques. Todd is also co-founder of Agita Labs, a startup developing privacy-enhanced computation technologies that help ease the tension between data discovery and personal privacy.

Further Info