Antigoni Polychroniadou
4 papers · 2024–2026 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
excess risk
(1)
synthetic data
(1)
decision tree
(1)
fully homomorphic encryption
(1)
gpu acceleration
(1)
linear model
(1)
zero-knowledge proof
(1)
cryptographic protocol
(1)
privacy-preserving inference
(1)
lipschitz loss
(1)
matrix mechanism
(1)
large language model
(1)
model privacy
(1)
differentially private
(1)
differentially private federated learning
(1)
utility improvement
(1)
fairness audit
(1)
cryptographic commitment
(1)
gpt2
(1)
marginal-preserving
(1)
Papers
AudiFair: Privacy-Preserving Framework for Auditing Fairness
UAI 2026
DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing
ICML 2025
EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption
ICML 2025
Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
ICML 2024