User Privacy

User privacy in the digital age focuses on protecting sensitive personal information collected and processed by various technologies, primarily aiming to balance data utility with individual privacy rights. Current research emphasizes developing and evaluating privacy-preserving techniques, including differential privacy, homomorphic encryption, federated learning, and split learning, often applied within specific model architectures like neural networks and large language models. These efforts are crucial for mitigating privacy risks in diverse applications, from transportation and healthcare to online advertising and smart home devices, impacting both the ethical development of AI and the design of privacy-respecting systems.