Alina Oprea

~Alina_Oprea1

6

论文总数

3.0

年均投稿

5.8

平均评分

接收情况3/6

会议分布

ICLR

4

ICML

1

NeurIPS

1

发表论文 (6 篇)

20253 篇

Adversarial Inception Backdoor Attacks against Reinforcement Learning

ICML 2025Poster

Adversarial Inception for Bounded Backdoor Poisoning in Deep Reinforcement Learning

ICLR 2025Rejected

Phantom: General Trigger Attacks on Retrieval Augmented Language Generation

ICLR 2025Rejected

20243 篇

SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents

NeurIPS 2024Poster

User Inference Attacks on Large Language Models

ICLR 2024Rejected

One-shot Empirical Privacy Estimation for Federated Learning

合作者 (17)

Christopher Amato3 篇

Ethan Rathbun3 篇

Peter Kairouz2 篇

Christopher A. Choquette-Choo2 篇

Galen Andrew1 篇

Hugh Brendan McMahan1 篇

Sewoong Oh1 篇

Vinith Menon Suriyakumar1 篇