PNNL

Abstract

Warfare systems are increasingly being supported by artificial intelligence (AI), and its influence is growing. As AI becomes a warfare enabler it has also become a target. For example, AI-enabled machine vision systems can be trivially deceived by specially formulated camouflage. Many approaches to making AI more resilient to protect against specific attacks fail to generalize. However, attacks often do generalize across models trained for the same task, regardless of architecture or training data. This paper will illustrate the state of the practice in offensive and defensive AI and clarify some myths about AI's triumphs and failures in the real world.