Introduces the K-Norm Gradient Mechanism (KNG) for achieving differential privacy with practical examples and insights on its advantages over existing mechanisms.
Explores challenges in deep learning and machine learning applications, covering surveillance, privacy, manipulation, fairness, interpretability, energy efficiency, cost, and generalization.
Explores privacy technologies, emphasizing the importance of protecting communication layers and discussing anti-surveillance PETS and privacy properties.
Covers privacy mechanisms, their pros and cons, and their application in various scenarios, emphasizing privacy as a security property and its significance in society.
Explores the challenges of protecting location privacy and various techniques to mitigate location-related inferences, highlighting the importance of trust assumptions and practical issues.
Explores privacy-preserving data publishing mechanisms, including k-anonymity and differential privacy, and their practical applications and challenges.
