When talking about advents of artificial intelligence, we hear a lot about its adversarial attacks, specifically those that attempt to “deceive” an AI into believing, or to be more accurate, classifying, something incorrectly. For example, autonomous vehicles can be 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. Such examples showcase the narrative around AI deception.
In another form, AI can be deceptive in manipulating the perceptions and beliefs of a person through “deepfakes” in video, audio, and images. The significant AI conferences held around the world are more frequently addressing the subject of AI deception too. And yet a lot of debates and discussions are happening on how we can defend against it through detection mechanisms.