With this level of interaction, a new identity problem is emerging as machines operate on behalf of humans. Collaboration between humans and machines is a working reality today. Along with this comes the need for secure communication as machines operate increasingly on behalf of humans. While people need usernames and passwords to identify themselves, machines also need to identify themselves to one another. But instead of usernames and passwords, machines use keys and certificates that serve as machine identities so they can connect and communicate securely.

Last week, Andy Grotto and I published a new working paper on policy responses to the risk that artificial intelligence (AI) systems, especially those dependent on machine learning (ML), can be vulnerable to intentional attack. As the National Security Commission on Artificial Intelligence found, "While we are on the front edge of this phenomenon, commercial firms and researchers have documented attacks that involve evasion, data poisoning, model replication, and exploiting traditional software flaws to deceive, manipulate, compromise, and render AI systems ineffective." The demonstrations of vulnerability are remarkable: In the speech recognition domain, research has shown it is possible to generate audio that sounds like speech to ML algorithms but not to humans. There are multiple examples of tricking image recognition systems to misidentify objects using perturbations that are imperceptible to humans, including in safety critical contexts (such as road signs). One team of researchers fooled three different deep neural networks by changing just one pixel per image.

Key Takeaways: # Intelligent software agents must use common sense in order to reason. Common-sense knowledge is required before intelligent software agents can anticipate how people and the physical world react. Deep learning models do not currently understand what they produce, and have no common-sense knowledge. The Commonsense Transformers (COMET) project attempts to train models with information about the world in ways similar to how a human would acquire such knowledge. The COMET project and other similar efforts are still in the research phase.