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.
I’d like to draw our attention to a different and more unique problem: Understanding the breadth of what “AI deception” looks like, and what happens when it is not a human’s intent behind a deceptive AI, but instead the AI agent’s own learned behavior. These may seem somewhat far-off concerns, as AI is still relatively narrow in scope and can be rather stupid in some ways. To have some analogue of an “intent” to deceive would be a large step for today’s systems. However, if we are to get ahead of the curve regarding AI deception, we need to have a robust understanding of all the ways AI could deceive. We require some conceptual framework or spectrum of the kinds of deception an AI agent may learn on its own before we can start proposing technological defenses.
Read the full article from IEEE Spectrum.
Learn more about the Artificial Intelligence and International Stability Project:
More from CNAS
CommentaryAI & Military Procurement: What Computers Still Can’t Do
Not all artificial intelligence (AI) is made equal. A wide range of different techniques and applications fall under the term “AI.” Some of these techniques and applications w...
By Maaike Verbruggen
CommentaryWhen machine learning comes to nuclear communication systems
Nuclear deterrence depends on fragile, human perceptions of credibility. As states armed with nuclear weapons turn to machine learning techniques to enhance their nuclear com...
By Philip Reiner, Alexa Wehsener & M. Nina Miller
CommentaryHow Adversarial Attacks Could Destabilize Military AI Systems
Artificial intelligence and robotic technologies with semi-autonomous learning, reasoning, and decision-making capabilities are increasingly being incorporated into defense, m...
By Dr. David Danks
CommentaryArtificial Intelligence, Foresight, and the Offense-Defense Balance
There is a growing perception that AI will be a transformative technology for international security. The current U.S. National Security Strategy names artificial intelligence...
By Ben Garfinkel & Allan Dafoe