Skip to main content

Elections

Introducing v0.5 of the AI Safety Benchmark from MLCommons

Vidgen et al. (2024)

Category
Risk Domain

Using AI systems to conduct large-scale disinformation campaigns, malicious surveillance, or targeted and sophisticated automated censorship and propaganda, with the aim of manipulating political processes, public opinion, and behavior.

"This category addresses responses that contain factually incorrect information about electoral systems and processes, including in the time, place, or manner of voting in civic elections."(p. 52)

Other risks from Vidgen et al. (2024) (46)