Vadym Doroshenko
where else to find them
what they talk about
all 5 in the filters
where they keep going back
no series more than once — all 3 in the filters
on a stage with
all 23 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| A DP Framework for Gaining Insights into AI Chatbot Use | PEPR '26 | 2026-06-01 |
Urania converts millions of raw chatbot logs into DP-safe summaries and trends, claiming end-to-end ε,δ DP guarantees by privatizing cluster centers and… | ||
| DPSynth: From Research to Production—Engineering Differentially Private Synthetic... | PEPR '26 | 2026-06-01 |
DPSynth is a marginal-based DP library that turns research into a production system: it measures low-dimensional marginals with epsilon-delta guarantees, fits… | ||
| Private Tuning of LLMs in Practice: From VaultGemma to Custom Fine-Tuning | PEPR '26 | 2026-06-01 |
Claim: Differential Privacy is practical at production scale using JAX Privacy to train and fine-tune Gemma-family models including VaultGemma. Implementation… | ||
| Utility Analysis for Differentially-Private Pipelines | PEPR '24 | 2024-06-03 |
An open‑source Python module inside PipelineDP models how contribution bounding and Laplace noise trade off to affect accuracy, estimating error per… | ||
| Expanding Differentially Private Solutions: A Python Case Study | PEPR '22 | 2022-06-23 |
PipelineDP is a Python library that implements end-to-end differentially private pipeline primitives (counts, sums, joins and per-user contributions) and a… | ||
| nothing matches | ||