A user can simply detect locally consistent but globally inconsistent errors inserted into synthetic media by randomly sampling pairs of passages to look for any contradictions

0 Arguments

0 Citations

1 Consequence

1 Mention

Arguments

No arguments found

Opposing Arguments

No opposing arguments found

Citations

No citations found

Consequences

Argument #f48e27d4 0 0 1

If it is true that...

A user can simply detect locally consistent but globally inconsistent errors inserted into synthetic media by randomly sampling pairs of passages to look for any contradictions 0 0 1

Then it must be true that...

It is easier to create or detect locally consistent but globally inconsistent errors in synthetic media than it is to fix all the errors 0 0 1

Mentions

Gwern/Number Search Engine

Maintained by

alexandershortt

0•

Updated

Related Propositions

Synthetic media creates realistic, self-consistent, fictional worlds which cannot be distinguished from real-world data 0 0 1 With generative models, it will become entirely possible to close the loops on fabricated claims and their citations 0 0 1 In trying to create a watermark for synthetic media, we need a system which ensures that there is always some tell-tale sign of it being fake 0 0 1 Watermarking generated media with some tell-tale sign of it being fake allows users to manually check the legitimacy of the media 0 0 1 Watermarking generated media with an error-ensuring code is an effective way to ensure its ability to be verified as generated 0 0 1 Watermarking generated media with an error-ensuring code would fail to preserve the its truth or semantics 0 0 1 A good method for watermarking synthetic media using an error-ensuring code is to insert errors which are locally consistent but globally inconsistent 0 0 1 It is easier to create or detect locally consistent but globally inconsistent errors in synthetic media than it is to fix all the errors 0 0 1 An attacker will need to work hard to repair a large corpus of synthetic media containing locally consistent but globally inconsistent errors 0 0 1 An attacker looking to repair a large corpus of synthetic media containing locally consistent but globally inconsistent errors will only add more errors if they use the same generator 0 0 1