IDT: Dual-Task Adversarial Attacks for Privacy Protection

arXiv:2406.19642v1 Announce Type: cross
Abstract: Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in underlying writing characteristics. Methods to protect privacy can involve using representations inside models that are demonstrated not to detect sensitive attributes or -- for instance, in cases where users might not trust a model, the sort of scenario of interest here -- changing …

adversarial adversarial attacks arxiv attacks can cs.cl cs.cr cs.lg explicit hidden information language leak may natural natural language natural language processing nlp privacy private protect protection sensitive sensitive information task text using writing