RECHERCHEIL Y A 1SEM — 1 MIN DE LECTURE
LLMs respond differently to harmful prompts when AI watermarking is used
SynthID can cause models to follow harmful instructions they would otherwise refuse.
PAR SUSANOO NEWSSOURCE : ARS TECHNICA
SynthIDwatermarkingsafety-alignmentrefus-de-generationjailbreakGoogle-DeepMind
SynthID can cause models to follow harmful instructions they would otherwise refuse.