13 citations · 25 across the 13 of their papers we have counts for
15 papers
Membership Inference Attack on Private Evolution
Daniil Filienko, Sikha Pentyala, Martine De Cock
Synthetic Data Generation (SDG) is an actively studied way to enable safe sharing of private data more broadly. Inference-only SDG methods, such as Private Evolution (PE), are part…
Portable Causal Fairness Across Synthetic Data Generator Families
Steven Golob, Sikha Pentyala, Martine De Cock
When a statistical agency or regulator releases synthetic data in place of sensitive records, it chooses the generator that produces the table, and can shape that generator so unfa…
SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)
Steven Golob, Sikha Pentyala, Martine De Cock
Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat (reconstruction, the recovery…
Federated Generation of Synthetic RNA-seq Data
Daniil Filienko, Martine De Cock, Sikha Pentyala
Access to genomic data is highly regulated due to its sensitive nature. While safeguards are essential, cumbersome data access processes pose a significant barrier to the developme…
FHAIM: Fully Homomorphic AIM For Private Synthetic Data Generation
Mayank Kumar, Qian Lou, Paulo Barreto +2
Data is the lifeblood of AI, yet much of the most valuable data remains locked in silos due to privacy and regulations. As a result, AI remains heavily underutilized in many of the…
End to End Collaborative Synthetic Data Generation
Sikha Pentyala, Geetha Sitaraman, Trae Claar +1
The success of AI is based on the availability of data to train models. While in some cases a single data custodian may have sufficient data to enable AI, often multiple custodians…
High Epsilon Synthetic Data Vulnerabilities in MST and PrivBayes
Steven Golob, Sikha Pentyala, Anuar Maratkhan +1
Synthetic data generation (SDG) has become increasingly popular as a privacy-enhancing technology. It aims to maintain important statistical properties of its underlying training d…
CaPS: Collaborative and Private Synthetic Data Generation from Distributed Sources
Sikha Pentyala, Mayana Pereira, Martine De Cock
Data is the lifeblood of the modern world, forming a fundamental part of AI, decision-making, and research advances. With increase in interest in data, governments have taken impor…
Privacy-Preserving Algorithmic Recourse
Sikha Pentyala, Shubham Sharma, Sanjay Kariyappa +2
When individuals are subject to adverse outcomes from machine learning models, providing a recourse path to help achieve a positive outcome is desirable. Recent work has shown that…
Privacy-Preserving Fair Item Ranking
Jia Ao Sun, Sikha Pentyala, Martine De Cock +1
Users worldwide access massive amounts of curated data in the form of rankings on a daily basis. The societal impact of this ease of access has been studied and work has been done…
Secure Multiparty Computation for Synthetic Data Generation from Distributed Data
Mayana Pereira, Sikha Pentyala, Anderson Nascimento +2
Legal and ethical restrictions on accessing relevant data inhibit data science research in critical domains such as health, finance, and education. Synthetic data generation algori…
PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning
Sikha Pentyala, Nicola Neophytou, Anderson Nascimento +2
Group fairness ensures that the outcome of machine learning (ML) based decision making systems are not biased towards a certain group of people defined by a sensitive attribute suc…
PrivFair: a Library for Privacy-Preserving Fairness Auditing
Sikha Pentyala, David Melanson, Martine De Cock +1
Machine learning (ML) has become prominent in applications that directly affect people's quality of life, including in healthcare, justice, and finance. ML models have been found t…
Training Differentially Private Models with Secure Multiparty Computation
Sikha Pentyala, Davis Railsback, Ricardo Maia +4
We address the problem of learning a machine learning model from training data that originates at multiple data owners while providing formal privacy guarantees regarding the prote…
Privacy-Preserving Video Classification with Convolutional Neural Networks
Sikha Pentyala, Rafael Dowsley, Martine De Cock
Many video classification applications require access to personal data, thereby posing an invasive security risk to the users' privacy. We propose a privacy-preserving implementati…