Your Cerebellum as an Attack Surface: How Does the Brain Stay Secure?

“Technology is the active human interface with the material world.” – UK LeGuin

Once upon a time, computer scientists spoke of semiconductors and magnetic cores, carefully designing their algorithms around the substrates that computation occurred on. Instead of programs, there were “computations,” “states” instead data, or the modern descendent, “content.”

Since then, we as computer scientists have developed layers of abstraction and from there formed a diverse ecosystem of high level paradigms to create and distribute information with speed, reliability, and efficiency. Neural networks in the brain are sparsely connected, composed of components with an over 50% failure rate, and still amazingly consistent in their high-level behavior over time. We are building models of biologically plausible neural networks to help explain how the brain can protect against a malicious adversary while keeping networks tiny, low power, and easily trained. Using parameters taken from the somatosensory cortex, we have built a prototype simulator to show the relationships between connectivity and severity of possible attacks.

Presented by