Project description: Image synthesis and generative modeling had unprecedented growth in recent years, unleashing the possibility of realistically manipulating faces in videos or correctly matching a face among millions. At the same time, very little effort has been devoted to cease the dualism between perturbations as evil entities versus benign defense mechanisms.
This project challenges this view and advances the hypothesis that adversarial machine learning may improve the state-of-the-art in privacy protection and in the preservation of human dignity.
To this end, the project will work in synergy along two opposing axes: on the one hand, it will aim at creating proactive defenses for multimedia data to protect them from malicious AI tools (deepfake or face recognition); another thread of research will study the robustness of AI to various types of perturbations.
Goal: Perform fundamental and applied research with the objective of disseminating research findings and publishing at top-international venues in computer vision, machine learning, deep learning, and related fields.
Keywords: adversarial attacks, robust model, deepfakes, face analysis, energy-based models, deepfakes, generative AI, diffusion models.
The research will be conducted under the supervision of Prof. Iacopo Masi, University of Rome (Sapienza, University of Rome) and Prof. Giuseppe Lisanti, University of Bologna.
Two available positions:
1 position is at Sapienza, University of Rome with I. Masi supervisor;
1 position is at the University of Bologna with G. Lisanti supervisor.
Master degree required (just a bachelor degree does not work) required by Jan/Feb 2024
Documented experience with Deep Learning
Strong programming ability (Python preferred)
Experience with Deep Learning tools such as Pytorch, Tensorflow, etc
Fluency in English
Desirable requirements (preferred but optional):
A PhD in Computer Vision (CV), Computer Science, Machine Learning (ML), and similar disciplines; required by Jan/Feb 2024
A relevant publication record in top venues in CV/ML (CVPR, ICCV, ECCV, TPAMI, ICML; other venues may be considered)
Specific experience with deep learning based generative models (e.g., adversarial training, GAN, Diffusion Models)
Good communication skills
Strong problem-solving attitude
High motivation to learn
Spirit of innovation and creativity
Ability to work both independently and collaboratively
Send an email with an expression of interest (including your CV) to firstname.lastname@example.org and email@example.com as soon as possible but before the end of October. We seek to perform the first interviews in October.
Thank you for considering this opportunity. We eagerly await your expressions of interest and look forward to the remarkable journey that lies ahead.
If you are not interested, but you know about possible interested people in your network, we would appreciate it if you could share this among them. Thank you.