4 papers
Efficient Shapley-Based Influence Attribution in Social Networks
Fangzhu Shen, Amir Gilad, Sudeepa Roy
The ubiquity of social platforms has reshaped the way information, behaviors, and advertisements diffuse across networks, with influence propagation often initiated by a small set…
Measuring Database Unfairness via Dependency Quantification Under Differential Privacy
Mariia Vologdin, Yuchao Tao, Amir Gilad
Differential privacy (DP) has become the de facto standard for protecting sensitive data, providing strong guarantees that published statistics or models reveal limited information…
Analyzing Deviations from Monotonic Trends through Database Repair
Shunit Agmon, Jonathan Gal, Amir Gilad +4
Datasets often exhibit violations of expected monotonic trends - for example, higher education level correlating with higher average salary, newer homes being more expensive, or di…
Differentially Private Explanations for Clusters
Amir Gilad, Tova Milo, Kathy Razmadze +1
The dire need to protect sensitive data has led to various flavors of privacy definitions. Among these, Differential privacy (DP) is considered one of the most rigorous and secure…