PhD Dissertation Defense - Sina Shaham

PhD Dissertation Defense - Sina Shaham  
 
Committee: Prof. Bhaskar Krishnamachari, Prof. Cyrus Shahabi, Prof. Cauligi Raghavendra  
 
Title: Responsible AI in SpatioTemporal Data Processing    
 
Abstract:    In this presentation, we systematically investigate the design and development of algorithms to improve privacy and fairness in the processing of spatio-temporal data. Beginning with an essential background introduction and a review of cutting-edge advancements, the discussion progresses to introduce a novel algorithm for safeguarding privacy in the dissemination of Origin-Destination (OD) Matrices. This algorithm, rooted in Differential Privacy (DP) principles, aims to protect user privacy during the collection and sharing of OD-matrices in 2D and higher dimensions. Subsequently, our focus shifts to the domain of user energy consumption, where we develop a methodology that ensures user privacy when disclosing electricity time series to third parties and entities that may not be fully trusted. Following this, we propose an incentive-based program aimed at balancing electricity demand, taking into account socio-economic family attributes and ensuring fair treatment. Through comprehensive evaluations, the presentation demonstrates the progress made over previous works and also sheds light on potential areas for future studies, particularly in the realm of responsible handling of complex spatio-temporal data.
 
Zoom Link: https://usc.zoom.us/j/98092705100    

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 539

Audiences: Everyone Is Invited

Contact: CS Events

Event Link: https://usc.zoom.us/j/98092705100