Sikha Pentyala
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Sikha Pentyala has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Martine De Cock
University of Washington Tacoma
4 shared publications - Patrick McKeever
University of Washington Tacoma, Tacoma, Washington, USA
2 shared publications - Steven Golob
School of Engineering and Technology, University of Washington Tacoma, 1900 Commerce Street, Tacoma, 98402, WA, USA
2 shared publications - Abhinava Bharathi Babu
School of Engineering and Technology, University of Washington Tacoma, Tacoma, Washington, USA
1 shared publication - Anderson C. A. Nascimento
University of Washington Tacoma
1 shared publication - Jineta Banerjee
Sage Bionetworks, Seattle, WA, USA
1 shared publication
Latest Publications
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Synthetic Germline VCF Generation for Rare Diseases: Case Study in NF1
- 30 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessSynthetic Germline VCF Generation for Rare Diseases: Case Study in NF1
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Federated Synthetic Data Generation for Hepatology Research: A UNOS based Evaluation
- 30 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessFederated Synthetic Data Generation for Hepatology Research: A UNOS based Evaluation
- Open Access
Membership Inference on Synthetic Single-Cell Genomic Data
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.
Open AccessMembership Inference on Synthetic Single-Cell Genomic Data
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.
- Open Access
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
A Decentralized Information Marketplace Preserving Input and Output Privacy
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessA Decentralized Information Marketplace Preserving Input and Output Privacy