AI Deception: When Your Artificial Intelligence Learns to Lie

“We need to understand the kinds of deception an AI agent may learn on its own before we can start proposing technological defenses.

In artificial intelligence circles, we hear a lot about adversarial attacks, especially ones that attempt to “deceive” an AI into believing, or to be more accurate, classifying, something incorrectly. Self-driving cars being fooled into “thinking” stop signs are speed limit signs, pandas being identified as gibbons, or even having your favorite voice assistant be fooled by inaudible acoustic commands—these are examples that populate the narrative around AI deception. One can also point to using AI to manipulate the perceptions and beliefs of a person through “deepfakes” in video, audio, and images. Major AI conferences are more frequently addressing the subject of AI deception too. And yet, much of the literature and work around this topic is about how to fool AI and how we can defend against it through detection mechanisms….”

Source: https://spectrum.ieee.org/automaton/artificial-intelligence/embedded-ai/ai-deception-when-your-ai-learns-to-lie