Hojjat Aghakhani's homepage

I'm a Ph.D. candidate in Computer Science at UC Santa Barbara, co-advised by Christopher Kruegel and Giovanni Vigna in the SecLab. Prior to that, I spent some of the best years of my life doing my bachelor at Sharif University of Technology.

My Research

I am interested in the intersection of machine learning and computer security. In my recent line of work, I have been studying data poisoning attacks against neural networks. I joined Microsoft Research's Privacy in AI (PAI) team in the summer of 2022 and studied large language models of code and their vulnerabilities to data poisoning attacks.

Some of my other involvements

9ytelapse / my time-lapse shots on Instagram

Terrariums / my YouTube channel

Fantasy Premier League / my FPL account

Preprints

TrojanPuzzle: Covertly Poisoning Code-Suggestion Models

Hojjat Aghakhani, Wei Dai, Andre Manoel, Xavier Fernandes, Anant Kharkar, Christopher Kruegel, Giovanni Vigna, David Evans, Ben Zorn, and Robert Sim arXiv

Peer-Reviewed Papers
Google Scholar

VENOMAVE: Targeted Poisoning Against Speech Recognition

Hojjat Aghakhani, Lea Schönherr, Thorsten Eisenhofer, Dorothea Kolossa, Thorsten Holz, Christopher Kruegel, and Giovanni Vigna arXiv
DeepCASE: Semi-Supervised Contextual Analysis of Security Events

Thijs van Ede, Hojjat Aghakhani, Noah Spahn, Riccardo Bortolameotti, Marco Cova, Andrea Continella, Maarten van Steen, Andreas Peter, Christopher Kruegel, and Giovanni Vigna S&P 2022
Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability

Hojjat Aghakhani, Dongyu Meng, Yu-Xiang Wang, Christopher Kruegel, and Giovanni Vigna EuroS&P 2021
When Malware is Packin’ Heat; Limits of Machine Learning Classifiers Based on Static Analysis Features

Hojjat Aghakhani, Fabio Gritti, Francesco Mecca, Martina Lindorfer, Stefano Ortolani, Davide Balzarotti, Giovanni Vigna, and Christopher Kruegel NDSS 2020
Bran: Reduce Vulnerability Search Space in Large Open Source Repositories by Learning Bug Symptoms

Dongyu Meng, Michele Guerriero, Aravind Machiry, Hojjat Aghakhani, Priyanka Bose, An- drea Continella, Christopher Kruegel and Giovanni Vigna ASIACCS 2021
One Size Does Not Fit All: A Longitudinal Analysis of Brazilian Financial Malware

Marcus Botacin, Hojjat Aghakhani, Stefano Ortolani, Christopher Kruegel, Giovanni Vigna, Daniela Oliveira, Paulo Lício De Geus, and André Grégio TOPS 2021
Neurlux: Dynamic Malware Analysis Without Feature Engineering

Chani Jindal, Christopher Salls, Hojjat Aghakhani, Keith Long, Christopher Kruegel, and Giovanni Vigna ACSAC 2019
Detecting Deceptive Reviews using Generative Adversarial Networks

Hojjat Aghakhani, Aravind Machiry, Shirin Nilizadeh, Christopher Kruegel, and Giovanni Vigna SPW 2018
Think Outside the Dataset: Finding Fraudulent Reviews using Cross-Dataset Analysis

Shirin Nilizadeh, Hojjat Aghakhani, Eric Gustafson, Christopher Kruegel, and Giovanni Vigna WWW 2019
Towards Automatically Generating a Sound and Complete Dataset for Evaluating Static Analysis Tools

Aravind Machiry, Nilo Redini, Eric Gustafson, Hojjat Aghakhani, Christopher Kruegel, and Giovanni Vigna BAR 2019
Integrating evolutionary game theory into an agent-based model of ductal carcinoma in situ: Role of gap junctions in cancer progression

Negin Malekian, Jafar Habibi, Mohammad Hossein Zangooei, and Hojjat Aghakhani Computer Methods and Programs in Biomedicine 2016