Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Mayana Pereira

Mayana Pereira

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2ML×1NLP×1Comp. Eng.×1AI×1

Frequent co-authors

Nassima M. Bouzid1×
Dehao Yuan1×
Nam H. Nguyen1×
Ifayoyinsola Ibikunle1×
Tyler Farnan1×
Senthil Kumar1×

Research Timeline

2026
Evaluating LLM Simulators as Differentially Private Data Generators

The paper evaluates LLM-based simulators for generating differentially private synthetic data, finding that while they show promise for utility, they suffer from significant distribution drift due to systematic LLM biases.

Decoupling Identity from Utility: Privacy-by-Design Frameworks for Financial Ecosystems

The paper proposes using Differentially Private (DP) synthetic data, specifically through tabular synthesis and DP-Seeded Agent-Based Modeling (ABM), to resolve the conflict between data utility and privacy in financial ecosystems.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CLcs.CRRecentApr 16, 2026

Evaluating LLM Simulators as Differentially Private Data Generators

Nassima M. Bouzid, Dehao Yuan, Nam H. Nguyen, Mayana Pereira

The paper evaluates LLM-based simulators for generating differentially private synthetic data, finding that while they show promise for utility, they suffer from significant distribution drift due to…

View →
cs.CEcs.AIcs.CRRecentApr 16, 2026

Decoupling Identity from Utility: Privacy-by-Design Frameworks for Financial Ecosystems

Ifayoyinsola Ibikunle, Tyler Farnan, Senthil Kumar, Mayana Pereira

The paper proposes using Differentially Private (DP) synthetic data, specifically through tabular synthesis and DP-Seeded Agent-Based Modeling (ABM), to resolve the conflict between data utility and p…

View →