Alina Oprea

8 papers · 2019–2025 · 4 conferences · across top CS/AI conferences

Achievements

🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (4) 🏃 Academic Marathon (6) 🐝 Cross-Pollinator (15) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird ❓ The Questioner

Conferences

NIPS (3) ICLR (2) ICML (2) EMNLP (1)

Top co-authors

Jonathan Ullman (3) Peter Kairouz (3) Sewoong Oh (2) Krishna Pillutla (2) Christopher Amato (2) Galen Andrew (2) Matthew Jagielski (2) Ethan Rathbun (2) Vinith Menon Suriyakumar (1) H. Brendan McMahan (1)

Keywords

differential privacy (4) privacy auditing (2) stochastic gradient descent (1) data poisoning (1) data attribution (1) membership inference (1) statistical test (1) equalized odd (1) large language model (1) fair learning (1) non-discriminatory model (1) protected group membership (1) user inference (1) user inference attack (1) privacy attack (1)

Papers

Adversarial Inception Backdoor Attacks against Reinforcement Learning ICML 2025

SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents NIPS 2024

User Inference Attacks on Large Language Models EMNLP 2024

One-shot Empirical Privacy Estimation for Federated Learning ICLR 2024

Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning ICLR 2024

Unleashing the Power of Randomization in Auditing Differentially Private ML NIPS 2023

Auditing Differentially Private Machine Learning: How Private is Private SGD? NIPS 2020

Differentially Private Fair Learning ICML 2019