De-AnonymizingTextby FingerprintingLanguageGeneration

Components of machine learning systems are not (yet) perceived as security hotspots. Secure coding practices, such as ensuring that no execution paths depend on confidential inputs, have not yet been adopted by ML developers. We initiate the study of code security of ML systems by investigating how nucleus sampling--a popular approach forgeneratingtext,used forapplications such as auto-completion--unwittingly leakstextstypedbyusers.