Education
Visiting PhD,
@sAIfer Lab, Joint Lab on Safety and Security of AI
@Università degli Studi di Genova
2024-2025, Genoa, Italy
PhD, 2023-present, @ETTI, UPB
Working towards increasing the robustness of neural networks against adversarial attacks, in various applications, by constructing new optimization algorithms, under the supervision of Corneliu Burileanu and Ana Neacşu.
Summer School, Mathematics and Machine Learning for Image Analysis
June 2024, Universita di Bologna, Bologna, Italy
MSc, 2021-2023, @ETTI, UPB
My thesis was titled "Defenses against adversarial attacks in image classification", where I focused on comparing and improving multiple robust training techniques against adversarial perturbations. I also explored the reliability of defenses tailored for white-box attacks against real adversarial perturbations:
The thesis can be found here.
The thesis can be found