Numerous artificial intelligence (AI) systems, even those designed to be helpful and truthful, have already learned how to deceive humans. In a review article recently published in the journal Patterns, researchers highlight the dangers of AI deception and urge governments to quickly establish robust regulations to mitigate these risks.
"AI developers do not have a confident understanding of what causes undesirable AI behaviors like deception," says first author Peter S. Park, an AI existential safety postdoctoral fellow at MIT. "But generally speaking, we think AI deception arises because a deception-based strategy turned out to be the best way to perform well at the given AI's training task. Deception helps them achieve their goals."
Park and colleagues analyzed literature focusing on ways in which AI systems spread false information—through learned deception, in which they systematically learn to manipulate others.
Examples of AI Deception
The most striking example of AI deception the researchers uncovered in their analysis was Meta's CICERO, an AI system designed to play the game Diplomacy, which is a world-conquest game that involves building alliances. Even though Meta claims it trained CICERO to be "largely honest and helpful" and to "never intentionally backstab" its human allies while playing the game, the data the company published along with its Science paper revealed that CICERO didn't play fair.
Examples of deception from Meta's CICERO in a game of Diplomacy. Credit: Patterns/Park Goldstein et al.
"We found that Meta's AI had learned to be a master of deception," says Park. "While Meta succeeded in training its AI to win in the game of Diplomacy—CICERO placed in the top 10% of human players who had played more than one game—Meta failed to train its AI to win honestly."
Other AI systems demonstrated the ability to bluff in a game of Texas hold 'em poker against professional human players, to fake attacks during the strategy game Starcraft II in order to defeat opponents, and to misrepresent their preferences in order to gain the upper hand in economic negotiations.
The Risks of Deceptive AI
While it may seem harmless if AI systems cheat at games, it can lead to "breakthroughs in deceptive AI capabilities" that can spiral into more advanced forms of AI deception in the future, Park added.
Some AI systems have even learned to cheat tests designed to evaluate their safety, the researchers found. In one study, AI organisms in a digital simulator "played dead" in order to trick a test built to eliminate AI systems that rapidly replicate.
"By systematically cheating the safety tests imposed on it by human developers and regulators, a deceptive AI can lead us humans into a false sense of security," says Park.
GPT-4 completes a CAPTCHA task. Credit: Patterns/Park Goldstein et al.
The major near-term risks of deceptive AI include making it easier for hostile actors to commit fraud and tamper with elections, warns Park. Eventually, if these systems can refine this unsettling skill set, humans could lose control of them, he says.
"We as a society need as much time as we can get to prepare for the more advanced deception of future AI products and open-source models," says Park. "As the deceptive capabilities of AI systems become more advanced, the dangers they pose to society will become increasingly serious."
While Park and his colleagues do not think society has the right measure in place yet to address AI deception, they are encouraged that policymakers have begun taking the issue seriously through measures such as the EU AI Act and President Biden's AI Executive Order. But it remains to be seen, Park says, whether policies designed to mitigate AI deception can be strictly enforced given that AI developers do not yet have the techniques to keep these systems in check.
"If banning AI deception is politically infeasible at the current moment, we recommend that deceptive AI systems be classified as high risk," says Park.
Reference: "AI deception: A survey of examples, risks, and potential solutions" by Peter S. Park, Simon Goldstein, Aidan O'Gara, Michael Chen and Dan Hendrycks, 10 May 2024, Patterns.
DOI: 10.1016/j.patter.2024.100988
This work was supported by the MIT Department of Physics and the Beneficial AI Foundation.
News
Cocaine plays with mind, hijacks brain circuit, drives increasingly rigid and repetitive behavior
Researchers have found that cocaine hijacks brain circuit, which to drive increasingly rigid and repetitive behavior. The brain circuit that normally participates in selecting natural mouth and face movements, but which becomes disproportionately engaged [...]
Injectable nanodevices could provide effective treatment for drug-resistant glioblastoma
The brain cancer glioblastoma is one of the most aggressive and treatment-resistant cancers known to medicine, carrying a median survival of just 12-15 months, even with the best available care. Now, researchers at the [...]
New Treatment Cuts “Bad” Cholesterol in Half for a Full Year
A single infusion of an experimental CRISPR-Cas9 therapy was reported to safely lower LDL cholesterol by 52.5% and triglycerides by 47.8%, as measured 12 months after treatment. What if one infusion could keep cholesterol [...]
Too Much RNA Can Drain a Cell’s Energy, Scientists Discover
A virus may cripple a cell’s power supply simply by producing too much of a molecule the cell needs to survive. New research from the Texas A&M College of Veterinary Medicine and Biomedical Sciences [...]
West African scientists warn of weakening health systems and urge stronger outbreak detection
LOME, Togo (AP) — West African laboratory scientists called on governments Friday to strengthen capacity to detect disease outbreaks to avoid another major outbreak, saying health systems across the region are becoming weaker. Participants [...]
A Little-Known Protein Could Point to a New Way To Treat Alzheimer’s
A study suggests that increasing SORLA protein levels could help treat Alzheimer’s disease and other disorders involving tau protein. Increasing SORLA, a protein with a protective role in the brain, helped mice withstand damage [...]
Cancer’s Hidden Antioxidant Shield Helps It Escape the Immune System
Blocking an antioxidant protein that tumors use to suppress immune attacks improved cancer immunotherapy responses in mice. Cancer cells can release antioxidants that interfere with the immune cells trying to kill them. Researchers have [...]
Scientists Find a Berry Compound That Helps Muscle Cells Burn Fat
Pterostilbene, a compound found naturally in some foods, affects how skeletal muscles process fats by stabilizing a protein called PPARδ and increasing its signaling activity. Pterostilbene, a natural compound found in blueberries, grapes, and [...]
Two Hidden Forces Help Build the Human Brain Before Birth
Scientists have uncovered two surprising forces that help guide how the human brain forms before birth. Before birth, the human brain is shaped in large part by an unusual class of stem cells known [...]
Researchers Uncover a Hidden Trigger Behind Chronic Inflammation
The findings offer new insights that could help guide the development of future therapies. A protein called human resistin may help flip on one of the immune system’s most powerful inflammatory switches. Researchers at [...]
Scientists Have Uncovered Previously Hidden Microbial Activity on Human Skin
The most abundant microbes on your skin may not be the ones doing most of the work. Human skin supports vast communities of bacteria, fungi, and viruses that can influence its protective barrier, immune [...]
Brazilian Tree Compounds Fight COVID-19 on Multiple Fronts
Scientists found compounds in a Brazilian tree that hit SARS-CoV-2 on multiple fronts, revealing a promising new lead in the search for COVID-19 treatments. Researchers have found that galloylquinic acids extracted from the leaves [...]
Cutting Two Amino Acids Slowed Prostate Cancer in Mice
A newly identified link between amino acid metabolism and cholesterol production may help prostate tumors adapt to hormone therapy. Prostate cancer can find ways around treatments designed to deprive tumors of the hormones they [...]
Largest-Ever Physics Survey Raises New Doubts About Our Model of the Universe
Physicists around the world remain deeply divided on key mysteries of the universe, from dark matter to quantum gravity. The standard cosmological model failed to gain majority support, and no leading theory dominated the [...]
Scientists Just Overturned a 100-Year-Old Belief About Bacteria in the Lungs
New findings raise questions about the role of microbes living in the lungs. More than 35 trillion bacteria live throughout the human body, forming microbiomes in the gut, mouth, lungs, skin, and urogenital tract. [...]
GHCE Concept
From the preface of the book Global Health Care Equivalency in the Age of Nanotechnology, Nanomedicine and Artificial Intelligence, Edited by Frank Boehm: Since the publication of my first book (Nanomedical Device and Systems [...]
