Friday, August 8, 2025
Science
No Result
View All Result
  • Login
  • HOME
  • SCIENCE NEWS
  • CONTACT US
  • HOME
  • SCIENCE NEWS
  • CONTACT US
No Result
View All Result
Scienmag
No Result
View All Result
Home Science News Technology and Engineering

AI systems are already skilled at deceiving and manipulating humans

May 10, 2024
in Technology and Engineering
Reading Time: 4 mins read
0
Example of premeditated deception from Meta’s CICERO in the game Diplomacy
67
SHARES
612
VIEWS
Share on FacebookShare on Twitter
ADVERTISEMENT

Many artificial intelligence (AI) systems have already learned how to deceive humans, even systems that have been trained to be helpful and honest. In a review article publishing in the journal Patterns on May 10, researchers describe the risks of deception by AI systems and call for governments to develop strong regulations to address this issue as soon as possible.

Example of premeditated deception from Meta’s CICERO in the game Diplomacy

Credit: Patterns/Park Goldstein et al.

ADVERTISEMENT

Many artificial intelligence (AI) systems have already learned how to deceive humans, even systems that have been trained to be helpful and honest. In a review article publishing in the journal Patterns on May 10, researchers describe the risks of deception by AI systems and call for governments to develop strong regulations to address this issue as soon as possible.

“AI developers do not have a confident understanding of what causes undesirable AI behaviors like deception,” says first author Peter S. Park (@dr_park_phd), 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.

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.

“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.

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.

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.

This work was supported by the MIT Department of Physics and the Beneficial AI Foundation.

###

Patterns, Park and Goldstein et al. “AI deception: A survey of examples, risks, and potential solutions”

Patterns (@Patterns_CP), published by Cell Press, is a data science journal publishing original research focusing on solutions to the cross-disciplinary problems that all researchers face when dealing with data, as well as articles about datasets, software code, algorithms, infrastructures, etc., with permanent links to these research outputs. Visit https://www.cell.com/patterns. To receive Cell Press media alerts, please contact press@cell.com.



Journal

Patterns

DOI

10.1016/j.patter.2024.100988

Method of Research

Literature review

Subject of Research

Not applicable

Article Title

AI deception: A survey of examples, risks, and potential solutions

Article Publication Date

10-May-2024

Share27Tweet17
Previous Post

First detection of hepatitis E virus from urban Norway rats (Rattus norvegicus) in the Republic of Korea

Next Post

Long-term effect of home blood pressure self-monitoring plus medication self-titration for patients with hypertension

Related Posts

blank
Technology and Engineering

Small Yet Powerful: A Biomimetic Concept Soars

August 8, 2025
blank
Technology and Engineering

Advanced Quinone Nanocomposites Boost Zinc-Ion Batteries

August 8, 2025
blank
Technology and Engineering

Smart Excitation for Real-Time Full-Spectrum Vibration Isolation

August 8, 2025
blank
Technology and Engineering

3D GN/CNT Network Boosts NVPF Cathode Performance

August 8, 2025
blank
Technology and Engineering

Eco-Friendly ZIF-7 Carbon for Sensitive Rhodamine B Detection

August 8, 2025
blank
Technology and Engineering

Weathered Microplastics in Blood Affect Clotting

August 7, 2025
Next Post
Long-term effect of home blood pressure self-monitoring plus medication self-titration for patients with hypertension

Long-term effect of home blood pressure self-monitoring plus medication self-titration for patients with hypertension

  • Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study

    Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study

    27531 shares
    Share 11009 Tweet 6881
  • University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept

    942 shares
    Share 377 Tweet 236
  • Bee body mass, pathogens and local climate influence heat tolerance

    641 shares
    Share 256 Tweet 160
  • Researchers record first-ever images and data of a shark experiencing a boat strike

    506 shares
    Share 202 Tweet 127
  • Warm seawater speeding up melting of ‘Doomsday Glacier,’ scientists warn

    310 shares
    Share 124 Tweet 78
Science

Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!

RECENT NEWS

  • Nicotinamide Phosphoribosyltransferase’s Role in NAD+ Metabolism
  • Discovering a Phage to Combat Drug-Resistant Bacteria
  • Deep Learning Enhances Pediatric MRI Image Quality
  • Metabolic Constraints Shape Fish Habitat Predictions

Categories

  • Agriculture
  • Anthropology
  • Archaeology
  • Athmospheric
  • Biology
  • Bussines
  • Cancer
  • Chemistry
  • Climate
  • Earth Science
  • Marine
  • Mathematics
  • Medicine
  • Pediatry
  • Policy
  • Psychology & Psychiatry
  • Science Education
  • Social Science
  • Space
  • Technology and Engineering

Subscribe to Blog via Email

Enter your email address to subscribe to this blog and receive notifications of new posts by email.

Join 4,858 other subscribers

© 2025 Scienmag - Science Magazine

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In
No Result
View All Result
  • HOME
  • SCIENCE NEWS
  • CONTACT US

© 2025 Scienmag - Science Magazine

Discover more from Science

Subscribe now to keep reading and get access to the full archive.

Continue reading