Survey details unlearnable data methods for AI privacy

This survey provides a comprehensive review of unlearnable data (ULD), a technique used to protect data privacy and security in machine learning by degrading model performance through data perturbations. It examines ULD generation methods, benchmarks, evaluation metrics, theoretical underpinnings, and practical applications. The survey also discusses challenges such as balancing perturbation imperceptibility with model degradation and computational complexity, while highlighting future research directions. AI

IMPACT Provides a foundational overview of unlearnable data techniques for AI researchers and practitioners focused on data privacy and security.

RANK_REASON The item is a survey paper on a specific AI technique, published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv
• Jiahao Li
• ScienceCast
• Unlearnable Data

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →