Differential Privacy in Machine Learning: A Survey from Symbolic AI to LLMs

ArXi:2506.11687v2 Announce Type: replace-cross Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data point does not significantly alter the output of an algorithm, thus limiting the exposure of private information. This survey reviews the foundational definitions of differential privacy and traces their evolution through key theoretical and applied contributions.