Current computer systems are dumb automatons; their blind execution of instructions makes them open to attack. Their inability to reason means they don""t consider the larger, constantly changing context outside their immediate inputs. Their nearsightedness is particularly dangerous because, in our complex systems, it is difficult to prevent all exploitable situations. Additionally, the lack of autonomous oversight of our systems means they are unable to fight through attacks. Keeping our adversaries completely out of our systems may be an unreasonable expectation, and our systems need to adapt to attacks and other disruptions to achieve our objectives. What is needed is an autonomous controller within the computer system that can sense the state of the system and reason about that state. 21CT proposes SATPAM, which uses prediction to learn abstractions that allow it to recognize the right events at the right level of detail. These abstractions allow SATPAM to break the world into small, relatively independent, pieces that allow employment of existing reasoning methods.
