Farzad Nikfam

Ph.D. candidate in Ingegneria Elettrica, Elettronica E Delle Comunicazioni , 36^th cycle (2020-2023)
Department of Electronics and Telecommunications (DET)

Docente esterno e/o collaboratore didattico
Department of Electronics and Telecommunications (DET)

farzad.nikfam@polito.it

Profile

PhD

Thesis title

Security and Privacy in Artificial Intelligence

Research topic

Fast Adversarial Training and Privacy Preserving

Tutors

Maurizio Martina

Research interests

Big Data, Machine Learning, Neural Networks and Data Science

Biography

I obtained a Bachelor's degree in Mechanical Engineering in 2018 and a Master's degree in Mechatronics in 2020 from the Politecnico di Torino. From 2014 to 2018 I actively participated in the Isaac students team for robotic design and I organized the work for the last two years as team leader. My Bachelor's thesis was aimed at testing a python code for solving electrical circuits, while for the Master's thesis I worked on deep neural networks in the field of adversarial attacks. I am currently doing my PhD in electronics to be able to continue my research in the field of artificial intelligence.

Teaching

Teachings

Master of Science

Electronics Fundamentals and Applications. A.A. 2023/24, MECHATRONIC ENGINEERING (INGEGNERIA MECCATRONICA). Collaboratore del corso
Electronics Fundamentals and Applications. A.A. 2022/23, MECHATRONIC ENGINEERING (INGEGNERIA MECCATRONICA). Collaboratore del corso
Electronics Fundamentals and Applications. A.A. 2021/22, MECHATRONIC ENGINEERING (INGEGNERIA MECCATRONICA). Collaboratore del corso

MostraNascondi A.A. passati

Publications

Latest publications View all publications in Porto@Iris

Nikfam, Farzad; Casaburi, Raffaele; Marchisio, Alberto; Martina, Maurizio; Shafique, ... (2023)
A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks. In: INFORMATION, vol. 14. ISSN 2078-2489
Contributo su Rivista
Nikfam, Farzad; Marchisio, Alberto; Martina, Maurizio; Shafique, Muhammad (2022)
AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient. In: IEEE ACCESS, vol. 10, pp. 108997-109007. ISSN 2169-3536
Contributo su Rivista