Mo Sadegh Akhondzadeh

Hi, I’m Sadegh I’m a Master student at Saarland University and Research Associate at the CISPA Helmholtz Center for Information Security. I am fortunate to be advised by Dr. Aleksandar Bojchevski.

I’m broadly interested in learning methods that account for the structure present in data. Particularly, I’m interested in studying machine learning methods targeting complex data domains such as graphs and temporal data. My current research focuses on trustworthy machine learning for graph neural networks, including their explanability, interpretability, etc.

Before starting my M.Sc., I completed my B.Sc. degree in Computer Engineering at Isfahan University of Technology.

news

Jan 21, 2023	Our paper on probing the representation of graph-based models was accepted at AISTATS.
Nov 16, 2022	I will be presenting our new preprint, titled Probing Graph Representation for Molecules, at the ELLIS ML4Molecules Workshop.
Dec 2, 2021	Our team placed third in the Science4Cast competition, winning a cash prize of 2000 euros.
Nov 1, 2021	I have joined CISPA, as a Reasearch Assosiate.

selected publications

AISTATS

Probing Graph Representation

Mohammad Sadegh Akhondzadeh, Vijay Lingam, and Aleksandar Bojchevski

In International Conference on Artificial Intelligence and Statistics AISTATS 2022

Workshop Version Code Workshop Poster Website
WEBSCI 2021

Wide-AdGraph: Detecting Ad Trackers with a Wide Dependency Chain Graph

Amir Hossein Kargaran, Mohammad Sadegh Akhondzadeh, Mohammad Reza Heidarpour, Mohammad Hossein Manshaei, Kave Salamatian, and Masoud Nejad Sattary

In 13th ACM Web Science Conference 2021

Abs Best Student Paper arXiv ACM PDF Video Code

Websites use third-party ads and tracking services to deliver targeted ads and collect information about users that visit them. These services put users’ privacy at risk, and that is why users’ demand for blocking these services is growing. Most of the blocking solutions rely on crowd-sourced filter lists manually maintained by a large community of users. In this work, we seek to simplify the update of these filter lists by combining different websites through a large-scale graph connecting all resource requests made over a large set of sites. The features of this graph are extracted and used to train a machine learning algorithm with the aim of detecting ads and tracking resources. As our approach combines different information sources, it is more robust toward evasion techniques that use obfuscation or changing the usage patterns. We evaluate our work over the Alexa top-10K websites and find its accuracy to be 96.1% biased and 90.9% unbiased with high precision and recall. It can also block new ads and tracking services, which would necessitate being blocked by further crowd-sourced existing filter lists. Moreover, the approach followed in this paper sheds light on the ecosystem of third-party tracking and advertising.