Bitdefender AI Research

Our mission is to advance the state of the art in machine learning, focusing on robustness, security, and reliability and to engage with the global AI community.
Core Research
Generalization & Interpretability Deepfake Detection Natural Language Processing Reinforcement Learning
Explore Research Meet the Team

News

Aug 31, 2026 CoLLAs 2026 in Bucharest
Aug 31, 2026 Romanian AI Days 2026
May 7, 2026 DeepFMI 2026 project posters
All news →

Selected publications

Teaser for Foundation Models are Implicit Deepfake Detectors
Foundation Models are Implicit Deepfake Detectors
Stefan Smeu, Dragos-Alexandru Boldisor, Elisabeta Oneata, Dan OneataUnder review
Teaser for Pathways of Visual Information Flow in Vision-Language Models
Pathways of Visual Information Flow in Vision-Language Models
Israfel Salazar, Stella Frank, Dan Oneata, Desmond Elliott, Constanza FierroUnder review
Teaser for Anchoring the Unknown: Open-Set Model Attribution via Proxy-Anchor Learning
Anchoring the Unknown: Open-Set Model Attribution via Proxy-Anchor Learning
Cristian-Teodor Neamtu, Serban Mihalache, Stefan Smeu, Dan Oneata, Horia Cucu, Dragos BurileanuEUSIPCO 2026
Teaser for idSCD: Identifying Training Datasets through Semantic Correlation Descriptors
idSCD: Identifying Training Datasets through Semantic Correlation Descriptors
Andrada Gobeaja, Ionut Hodoroaga, Elena Burceanu, Marius LeordeanuUnder review
Teaser for How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
Teodor-Mihai Stupariu, Andrei ManolacheICML 2026 Workshop on Weight-Space Symmetries
Academic highlights →