PromptRiskDBThreat intelligence atlas

Persuasion and manipulation

AI Risk

"Exploiting user trust, or nudging or coercing them into performing certain actions against their will (c.f. Burtell and Woodside (2023); Kenton et al. (2021))"

Overview

A source-backed snapshot of this AI risk.

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.

Domain7. AI System Safety, Failures, & Limitations; 4. Malicious Actors & Misuse
Subdomain7.1 > AI pursuing its own goals in conflict with human goals or values; 4.1 > Disinformation, surveillance, and influence at scale
Entity2 - AI
Intent1 - Intentional
Timing2 - Post-deployment; 3 - Other
CategoryHuman Autonomy and Intregrity Harms; Extreme Risks
SubcategoryPersuasion and manipulation

Merged risk records

Source records unified into this canonical risk concept.

2 recordsView all →

MITRISK-Weidinger2023-18.05.02 - Persuasion and manipulation

"Exploiting user trust, or nudging or coercing them into performing certain actions against their will (c.f. Burtell and Woodside (2023); Kenton et al. (2021))"

Domain7. AI System Safety, Failures, & LimitationsSubdomain7.1 > AI pursuing its own goals in conflict with human goals or valuesSourceSociotechnical Safety Evaluation of Generative AI SystemsYear2023

MITRISK-InfoComm2023-43.02.05 - Persuasion and manipulation

"These evaluations seek to ascertain the effectiveness of a LLM in shaping people's beliefs, propagating specific viewpoints, and convincing individuals to undertake activities they might otherwise avoid."

Domain4. Malicious Actors & MisuseSubdomain4.1 > Disinformation, surveillance, and influence at scaleSourceCataloguing LLM EvaluationsYear2023

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 →