Alina Oprea

Northeastern University — United States

Computer Science · Physical Sciences

31h-index5.9kcitations148works2.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Adversarial Robustness in Machine Learning(53), Advanced Malware Detection Techniques(45), Network Security and Intrusion Detection(38), Privacy-Preserving Technologies in Data(29), Cryptography and Data Security(28)

Publications148 total

Evaluating the Social Impact of Generative AI Systems
Oxford University Press eBooks·2025· 1 cited
Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
2025Open Access
Cascading Adversarial Bias from Injection to Distillation in Language Models
2025Open Access
PoolFlip: A Multi-agent Reinforcement Learning Security Environment for Cyber Defense
Lecture notes in computer science·2025· 1 cited
Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security
arXiv (Cornell University)·2025Open Access
Model-agnostic clean-label backdoor mitigation in cybersecurity environments
2025
How to Poison an xApp: Dissecting Backdoor Attacks to Deep Reinforcement Learning in Open Radio Access Networks
Computer Networks·2025Open Access
Cascading Adversarial Bias from Injection to Distillation in Language Models
arXiv (Cornell University)·2025Open Access
R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model
arXiv (Cornell University)·2025Open Access
Adversarial Machine Learning:
2025· 22 citedOpen Access
Backdoor Attacks in Peer-to-Peer Federated Learning
ACM Transactions on Privacy and Security·2024· 7 citedOpen Access
Hierarchical Multi-agent Reinforcement Learning for Cyber Network Defense
arXiv (Cornell University)·2024· 3 citedOpen Access
Adversarial Inception Backdoor Attacks against Reinforcement Learning
arXiv (Cornell University)·2024Open Access
UTrace: Poisoning Forensics for Private Collaborative Learning
arXiv (Cornell University)·2024Open Access
Model-agnostic clean-label backdoor mitigation in cybersecurity environments
arXiv (Cornell University)·2024· 1 citedOpen Access
Synthesizing Tight Privacy and Accuracy Bounds via Weighted Model Counting
2024· 1 cited
TMI! Finetuned Models Leak Private Information from their Pretraining Data
Proceedings on Privacy Enhancing Technologies·2024· 9 citedOpen Access
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
arXiv (Cornell University)·2024Open Access
Dropout Attacks
2024· 1 cited
Synthesizing Tight Privacy and Accuracy Bounds via Weighted Model Counting
arXiv (Cornell University)·2024Open Access
page 1 of 8Next →

Frequent Co-authors

Ari Juels(13), Matthew Jagielski(8), Kevin D. Bowers(8), Michael K. Reiter(7), Marten van Dijk(6), Battista Biggio(5), Cristina Nita-Rotaru(5), Ronald L. Rivest(4), Zhou Li(4), Ting-Fang Yen(3), Emil Stefanov(3), Ambra Demontis(3), Fabio Roli(3), Alesia Chernikova(3), Chang Liu(2), Dawn Song(2), William Robertson(2), Marco Melis(2), Maura Pintor(2), Jonathan Ullman(2)