Sikha Pentyala

Sikha Pentyala

Auto-generated profile, based on publicly available information

Sikha Pentyala

School of Engineering and Technology, University of Washington Tacoma, Tacoma, Washington, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 June 2023
Verified
Conference Paper
Open access
SGSteven Golob
Steven Golob
SPSikha Pentyala
Sikha Pentyala
RDRafael Dowsley
Rafael Dowsley
BDBernardo David
Bernardo David
MLMario Larangeira
Mario Larangeira
ANAnderson Nascimento
Anderson Nascimento

30 June 2026
Verified
Conference Paper
Open access
SPSikha Pentyala
Sikha Pentyala
ABAbhinava Bharathi Babu
Abhinava Bharathi Babu
JAJoseph C Ahn
Joseph C Ahn
MCMartine De Cock
Martine De Cock

30 June 2026
Verified
Conference Paper
Open access
SPSikha Pentyala
Sikha Pentyala
ZPZiwei Pan
Ziwei Pan
PMPatrick J McKeever
Patrick J McKeever
JBJineta Banerjee
Jineta Banerjee
Luca FoschiniLuca Foschini
Luca Foschini
MCMartine De Cock
Martine De Cock

24 January 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
SGSteven Golob
Steven Golob
PMPatrick McKeever
Patrick McKeever
SPSikha Pentyala
Sikha Pentyala
MCMartine De Cock
Martine De Cock
JPJonathan Peck
Jonathan Peck
Single-cell RNA sequencing (scRNA-seq) data is subject to strict access control due to its sensitive nature, motivating the use of synthetic data generation (SDG) for privacy-preserving data sharing. We present the first adversarial privacy attack that performs meaningfully above random guessing against state-of-the-art scRNA-seq SDG methods. Our attack enables donor-level membership inference, demonstrating that leading SDG techniques fail to adequately mask which individuals were used to train the generator. We show that privacy leakage increases as the number of training donors decreases. Although the attack is designed to exploit vulnerabilities in scDesign2, we find that it also succeeds against synthetic data generated by other leading methods, including scDesign3 and scVI. This transferability indicates that an adversary can infer sensitive information from synthetic data without access to the training procedure, model parameters, or even the underlying generation algorithm. Finally, we investigate the use of perturbation with noise during the SDG process as a first-line defense, empirically evaluating its effectiveness in neutralizing the attack and its impact on utility.