Georgi Ganev

Orcid: 0009-0004-4287-7473

According to our database1, Georgi Ganev authored at least 14 papers between 2021 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Synthetic Data, Similarity-based Privacy Metrics, and Regulatory (Non-)Compliance.
CoRR, 2024

The Elusive Pursuit of Replicating PATE-GAN: Benchmarking, Auditing, Debugging.
CoRR, 2024

"What do you want from theory alone?" Experimenting with Tight Auditing of Differentially Private Synthetic Data Generation.
Proceedings of the 33rd USENIX Security Symposium, 2024

Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utility.
Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, 2024

2023
On the Inadequacy of Similarity-based Privacy Metrics: Reconstruction Attacks against "Truly Anonymous Synthetic Data".
CoRR, 2023

On the Challenges of Deploying Privacy-Preserving Synthetic Data in the Enterprise.
CoRR, 2023

When Synthetic Data Met Regulation.
CoRR, 2023

Understanding how Differentially Private Generative Models Spend their Privacy Budget.
CoRR, 2023

Synthetic Data Generation of Many-to-Many Datasets via Random Graph Generation.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
dpart: Differentially Private Autoregressive Tabular, a General Framework for Synthetic Data Generation.
CoRR, 2022

On Utility and Privacy in Synthetic Genomic Data.
Proceedings of the 29th Annual Network and Distributed System Security Symposium, 2022

Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data.
Proceedings of the International Conference on Machine Learning, 2022

2021
DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?
CoRR, 2021

Measuring Utility and Privacy of Synthetic Genomic Data.
CoRR, 2021


  Loading...