Gabriel Ghinita

Sina Shaham, Arash Hajisafi, Minh K Quan et al. · amazon-science

Privacy and fairness are two crucial pillars of responsible Artificial Intelligence (AI) and trustworthy Machine Learning (ML). Each objective has been independently studied in the literature with the aim of reducing utility loss in achieving them. Despite the significant interest attracted from both academia and industry, there remains an immediate demand for more in-depth research to unravel how these two objectives can be simultaneously integrated into ML models. As opposed to well-accepted trade-offs, i.e., privacy-utility and fairness-utility, the interrelation between privacy and fairness is not well-understood. While some works suggest a trade-off between the two objective functions, there are others that demonstrate the alignment of these functions in certain scenarios. To fill this research gap, we provide a thorough review of privacy and fairness in ML, including supervised, unsupervised, semi-supervised, and reinforcement learning. After examining and consolidating the literature on both objectives, we present a holistic survey on the impact of privacy on fairness, the impact of fairness on privacy, existing architectures, their interaction in application domains, and algorithms that aim to achieve both objectives while minimizing the utility sacrificed. Finally, we identify research challenges in achieving privacy and fairness concurrently in ML, particularly focusing on large language models.

Sina Shaham, Gabriel Ghinita, Cyrus Shahabi

Fairness in data-driven decision-making studies scenarios where individuals from certain population segments may be unfairly treated when being considered for loan or job applications, access to public resources, or other types of services. In location-based applications, decisions are based on individual whereabouts, which often correlate with sensitive attributes such as race, income, and education. While fairness has received significant attention recently, e.g., in machine learning, there is little focus on achieving fairness when dealing with location data. Due to their characteristics and specific type of processing algorithms, location data pose important fairness challenges. We introduce the concept of spatial data fairness to address the specific challenges of location data and spatial queries. We devise a novel building block to achieve fairness in the form of fair polynomials. Next, we propose two mechanisms based on fair polynomials that achieve individual spatial fairness, corresponding to two common location-based decision-making types: distance-based and zone-based. Extensive experimental results on real data show that the proposed mechanisms achieve spatial fairness without sacrificing utility.

Sina Shaham, Gabriel Ghinita, Cyrus Shahabi

Machine learning (ML) is playing an increasing role in decision-making tasks that directly affect individuals, e.g., loan approvals, or job applicant screening. Significant concerns arise that, without special provisions, individuals from under-privileged backgrounds may not get equitable access to services and opportunities. Existing research studies fairness with respect to protected attributes such as gender, race or income, but the impact of location data on fairness has been largely overlooked. With the widespread adoption of mobile apps, geospatial attributes are increasingly used in ML, and their potential to introduce unfair bias is significant, given their high correlation with protected attributes. We propose techniques to mitigate location bias in machine learning. Specifically, we consider the issue of miscalibration when dealing with geospatial attributes. We focus on spatial group fairness and we propose a spatial indexing algorithm that accounts for fairness. Our KD-tree inspired approach significantly improves fairness while maintaining high learning accuracy, as shown by extensive experimental results on real data.

Sina Shaham, Gabriel Ghinita, Bhaskar Krishnamachari et al.

Smart grids are a valuable data source to study consumer behavior and guide energy policy decisions. In particular, time-series of power consumption over geographical areas are essential in deciding the optimal placement of expensive resources (e.g., transformers, storage elements) and their activation schedules. However, publication of such data raises significant privacy issues, as it may reveal sensitive details about personal habits and lifestyles. Differential privacy (DP) is well-suited for sanitization of individual data, but current DP techniques for time series lead to significant loss in utility, due to the existence of temporal correlation between data readings. We introduce {\em STPT (Spatio-Temporal Private Timeseries)}, a novel method for DP-compliant publication of electricity consumption data that analyzes spatio-temporal attributes and captures both micro and macro patterns by leveraging RNNs. Additionally, it employs a partitioning method for releasing electricity consumption time series based on identified patterns. We demonstrate through extensive experiments, on both real-world and synthetic datasets, that STPT significantly outperforms existing benchmarks, providing a well-balanced trade-off between data utility and user privacy.

Sina Shaham, Gabriel Ghinita, Cyrus Shahabi

Location data are widely used in mobile apps, ranging from location-based recommendations, to social media and navigation. A specific type of interaction is that of location-based alerts, where mobile users subscribe to a service provider (SP) in order to be notified when a certain event occurs nearby. Consider, for instance, the ongoing COVID-19 pandemic, where contact tracing has been singled out as an effective means to control the virus spread. Users wish to be notified if they came in proximity to an infected individual. However, serious privacy concerns arise if the users share their location history with the SP in plaintext. To address privacy, recent work proposed several protocols that can securely implement location-based alerts. The users upload their encrypted locations to the SP, and the evaluation of location predicates is done directly on ciphertexts. When a certain individual is reported as infected, all matching ciphertexts are found (e.g., according to a predicate such as "10 feet proximity to any of the locations visited by the infected patient in the last week"), and the corresponding users notified. However, there are significant performance issues associated with existing protocols. The underlying searchable encryption primitives required to perform the matching on ciphertexts are expensive, and without a proper encoding of locations and search predicates, the performance can degrade a lot. In this paper, we propose a novel method for variable-length location encoding based on Huffman codes. By controlling the length required to represent encrypted locations and the corresponding matching predicates, we are able to significantly speed up performance. We provide a theoretical analysis of the gain achieved by using Huffman codes, and we show through extensive experiments that the improvement compared with fixed-length encoding methods is substantial.

Gabriel Ghinita, Kien Nguyen, Mihai Maruseac et al.

Monitoring location updates from mobile users has important applications in many areas, ranging from public safety and national security to social networks and advertising. However, sensitive information can be derived from movement patterns, thus protecting the privacy of mobile users is a major concern. Users may only be willing to disclose their locations when some condition is met, for instance in proximity of a disaster area or an event of interest. Currently, such functionality can be achieved using searchable encryption. Such cryptographic primitives provide provable guarantees for privacy, and allow decryption only when the location satisfies some predicate. Nevertheless, they rely on expensive pairing-based cryptography (PBC), of which direct application to the domain of location updates leads to impractical solutions. We propose secure and efficient techniques for private processing of location updates that complement the use of PBC and lead to significant gains in performance by reducing the amount of required pairing operations. We implement two optimizations that further improve performance: materialization of results to expensive mathematical operations, and parallelization. We also propose an heuristic that brings down the computational overhead through enlarging an alert zone by a small factor (given as system parameter), therefore trading off a small and controlled amount of privacy for significant performance gains. Extensive experimental results show that the proposed techniques significantly improve performance compared to the baseline, and reduce the searchable encryption overhead to a level that is practical in a computing environment with reasonable resources, such as the cloud.

Kien Nguyen, Gabriel Ghinita, Muhammad Naveed et al.

Mobile devices with rich features can record videos, traffic parameters or air quality readings along user trajectories. Although such data may be valuable, users are seldom rewarded for collecting them. Emerging digital marketplaces allow owners to advertise their data to interested buyers. We focus on geo-marketplaces, where buyers search data based on geo-tags. Such marketplaces present significant challenges. First, if owners upload data with revealed geo-tags, they expose themselves to serious privacy risks. Second, owners must be accountable for advertised data, and must not be allowed to subsequently alter geo-tags. Third, such a system may be vulnerable to intensive spam activities, where dishonest owners flood the system with fake advertisements. We propose a geo-marketplace that addresses all these concerns. We employ searchable encryption, digital commitments, and blockchain to protect the location privacy of owners while at the same time incorporating accountability and spam-resilience mechanisms. We implement a prototype with two alternative designs that obtain distinct trade-offs between trust assumptions and performance. Our experiments on real location data show that one can achieve the above design goals with practical performance and reasonable financial overhead.