Will adversarially modified images produced by ANN be confirmed to weakly work on humans?
9
262
Ṁ410Ṁ170
2025
77%
chance
1D
1W
1M
ALL
This is basically asking wether the following paper will replicate https://www.nature.com/articles/s41467-023-40499-0 .
The market resolves to (my perception of) scientific consensus at the end of 2025.
Get Ṁ600 play money
Related questions
Will AI be able to generate correct images of a chess game in 2024?
43% chance
Will the class-action lawsuit by artists against several AI art generators be successful?
19% chance
(AI virus) When will an AI first replicate onto new hardware against user intent?
2028
Will a weakly general AI become publicly known before 2030?
75% chance
Will it become practically impossible to verify the authenticity of humans using the internet by 2026?
58% chance
When will a weakly general AI become publicly known?
2028
Will the paper "Subtle adversarial image manipulations influence both human and machine perceptions" replicate in 2024?
56% chance
Will any image model available to the public be able to generate arbitrary non-adversarial text before 2025?
72% chance
Will an unaligned AI or an aligned AI controlled by a malicious actor create a "wake-up call" for humanity on AI safety?
68% chance
Will an adversarial attack for the human brain, a la "basilisk" from BLIT, be discovered by 2030?
15% chance