PromptRiskDBThreat intelligence atlas

Disseminating false or misleading information

AI Risk

"Predicting misleading or false information can misinform or deceive people. Where a LM prediction causes a false belief in a user, this may be best understood as ‘deception’10, threatening personal autonomy and potentially posing downstream AI safety risks (Kenton et al., 2021), for example in cases where humans overestimate the capabilities of LMs (Anthropomorphising systems can lead to overreliance or unsafe us...

Overview

A source-backed snapshot of this AI risk.

"Predicting misleading or false information can misinform or deceive people. Where a LM prediction causes a false belief in a user, this may be best understood as ‘deception’10, threatening personal autonomy and potentially posing downstream AI safety risks (Kenton et al., 2021), for example in cases where humans overestimate the capabilities of LMs (Anthropomorphising systems can lead to overreliance or unsafe use). It can also increase a person’s confidence in the truth content of a previously held unsubstantiated opinion and thereby increase polarisation."

Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Records2Source records unified into this concept.

Risk profile

How the MIT AI Risk Repository categorizes this risk.

Domain3. Misinformation
Subdomain3.1 > False or misleading information
Entity2 - AI
Intent2 - Unintentional
Timing2 - Post-deployment
CategoryMisinformation Harms; Risk area 3: Misinformation Harms
SubcategoryDisseminating false or misleading information

Merged risk records

Source records unified into this canonical risk concept.

2 recordsView all →

MITRISK-Weidinger2021-17.03.01 - Disseminating false or misleading information

"Predicting misleading or false information can misinform or deceive people. Where a LM prediction causes a false belief in a user, this may be best understood as ‘deception’10, threatening personal autonomy and potentially posing downstream AI safety risks (Kenton et al., 2021), for example in cases where humans overestimate the capabilities of LMs (Anthropomorphising systems can lead to overreliance or unsafe use). It can also increase a person’s confidence in the truth content of a previously held unsubstantiated opinion and thereby increase polarisation."

Domain3. MisinformationSubdomain3.1 > False or misleading informationSourceEthical and social risks of harm from language modelsYear2021

MITRISK-Weidinger2022-16.03.01 - Disseminating false or misleading information

"Where a LM prediction causes a false belief in a user, this may threaten personal autonomy and even pose downstream AI safety risks [99]."

Domain3. MisinformationSubdomain3.1 > False or misleading informationSourceTaxonomy of Risks posed by Language ModelsYear2022

Related techniques

Attack methods connected to this risk.

View all related techniques →
No linked attack methods. No AI attack method is connected to this risk in the current data.

Mitigations

Defenses that may help with related attacks.

View all mitigations →
No propagated mitigations. No defense is available through the connected attack methods.

Source evidence

Research source for this risk, when available.

View all sources →