About Me

I am a Senior Research Scientist in the Device Research department at Nokia Bell Labs in Cambridge, UK. I lead the Device Intelligence team, focusing on Machine Learning solutions for personal devices, with an emphasis on efficiency, collaboration, adaptability, and privacy. Before joining Bell Labs, I worked as a Postdoctoral Research Associate at Imperial College London's Information Processing and Communications Lab, closely collaborating with Prof. Deniz Gunduz on Privacy-Preserving and Trustworthy Machine Learning. I pursued my PhD in Computer Science at Queen Mary University of London as a member of the Centre for Intelligent Sensing, concurrently holding a Research Assistant position at Imperial College London contributing to the Databox Project in the Systems and Algorithms Laboratory. In my PhD, I had the chance to work with great advisors, Prof. Hamed Haddadi, Dr. Richard G. Clegg, and Prof. Andrea Cavallaro, on developing Machine Learning Algorithms for Privacy-Preserving Personal Data Analytics, particularly for data captured by mobile and wearable devices. During my PhD journey, I interned at Brave Software Research, where I explored privacy-preserving techniques to improve content personalization in web browsers. Prior to PhD, I earned an MSc degree in Computer Engineering from Sharif University of Technology in Iran.

Preprints

◉ Vicious Classifiers: Data Reconstruction Attack at Inference Time

[arXiv] [Code]

Mohammad Malekzadeh and Deniz Gunduz.
2023- Preprint (Under Review).

Publications

◉ Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing

[arXiv] [Code]

Mohammad Malekzadeh and Fahim Kawsar.
2024 - 25th International Workshop on Mobile Computing Systems and Applications (HotMobile).

◉ CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking

[arXiv] [Code] [ICML Workshop]

Shohreh Deldari, Dimitrios Spathis, Mohammad Malekzadeh, Fahim Kawsar, Flora Salim, Akhil Mathur.
2024- 17th ACM International Conference on Web Search and Data Mining (WSDM).
A preliminary version has been presented at ICML Workshop on Workshop on Machine Learning for Multimodal Healthcare Data (ML4MHD-2023).

◉ Centaur: Federated Learning for Constrained Edge Devices

[arXiv] [ICLR Workshop]

Fan Mo, Mohammad Malekzadeh, Soumyajit Chatterjee, Fahim Kawsar, Akhil Mathur.
2023 - ICLR Workshop on Machine Learning for IoT: Datasets, Perception, and Understanding (ML4IoT-2023).

◉ Re-architecting Traffic Analysis with Neural Network Interface Cards

[Conference]. [an initial version].

Giuseppe Siracusano, Salvator Galea, Davide Sanvit, Mohammad Malekzadeh, Paolo Costa, Gianni Antichi, Hamed Haddadi, and Roberto Bifulco.
2022 - 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI).

◉ Honest-but-Curious Nets: Sensitive Attributes of Private Inputs can be Secretly Coded into the Classifiers' Outputs

[Conference]. [arXiv] [Code]

Mohammad Malekzadeh, Anastasia Borovykh, and Deniz Gündüz.
2021 - ACM Conference on Computer and Communications Security (CCS).

◉ Quantifying and Localizing Usable Information Leakage from Neural Network Gradients

[arXiv]

Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh, Soteris Demetriou, Deniz Gunduz, and Hamed Haddadi. ICLR Workshop on Distributed and Private Machine Learning (DPML-2021).

◉ Efficient Hyperparameter Optimization for Differentially Private Deep Learning

[arXiv]

Aman Priyanshu, Rakshit Naidu, Fatemehsadat Mireshghallah, and Mohammad Malekzadeh
2021 - Workshop on Privacy Preserving Machine Learning (ACM CCS).

◉ DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor Data

[Journal] [arXiv] [Code] [Tutorial]

Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, and Hamed Haddadi.
2021 - ACM Journal on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)
and ACM conference for Ubiquitous Computing (UbiComp 2021)

◉ Dopamine: Differentially Private Federated Learning on Medical Data

[Workshop] [arXiv] [Code]

Mohammad Malekzadeh, Burak Hasircioglu, Nitish Mital, Kunal Katarya, Mehmet Emre Ozfatura, and Deniz Gündüz
2021 - The Second AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-21)
Selected as the best submission to the ITU AI/ML in 5G Challenge, sub-challenge Privacy Preserving AI/ML in 5G networks for healthcare applications, ITU-ML5G-PS-022

◉ Privacy and Utility Preserving Sensor-Data Transformations

[Journal]. [arXiv]. [Code]

Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, and Hamed Haddadi.
2020 - Pervasive and Mobile Computing Journal, Elsevier.

◉ Privacy-Preserving Bandits

[Conference]. [arXiv]. [Code]

Mohammad Malekzadeh, Dimitrios Athanasakis, Hamed Haddadi, and Benjamin Livshits
2020 - Conference on Machine Learning and Systems (MLSys), USA.

◉ Modeling and Forecasting Art Movements with CGANs

[Journal]. [arXiv]. [Code]

Edoardo Lisi, Mohammad Malekzadeh, Hamed Haddadi, F. Din-Houn Lau, and Seth Flaxman.
2020 - Royal Society Open Science Journal, The Royal Society.

◉ Mobile Sensor Data Anonymization

[Conference]. [arXiv]. [Code]

Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, and Hamed Haddadi.
2019 - ACM/IEEE International Conference on Internet-of-Things Design and Implementation (IoTDI), Canada.

◉ Protecting Sensory Data against Sensitive Inferences

[Workshop]. [arXiv]. [Code]

Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, and Hamed Haddadi.
2018 - In Proceedings of the EuroSys Workshop on Privacy by Design in Distributed Systems (W-P2DS), Portugal.

◉ Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis

[Conference]. [arXiv]. [Code]

Mohammad Malekzadeh, Richard G. Clegg, and Hamed Haddadi.
2018 - ACM/IEEE International Conference on Internet-of-Things Design and Implementation (IoTDI), USA.

◉ Technical Report : Fairness in Algorithmic Decision Making

[PDF]

Paul-Marie Carfantan, Omar Costilla-Reyes, Delia Fuhrmann, Jonas Glesaaen, Qi He, Andreas Kirsch, Julie Lee, Mohammad Malekzadeh, Esben Sørig, Caryn Tan, Emily Turner, and Vinh Quang.
2018 - Data Study Group team. (2019, February 5). Data Study Group Final Report: Accenture. Zenodo.

◉ Gamified Incentives: A Badge Recommendation Model to Improve User Engagement in Social Networking Websites

[Journal].[Code]

Reza Gharibi and Mohammad Malekzadeh.
2017 - International Journal of Advanced Computer Science and Applications (IJACSA).

◉ A Multi-Generational Social Learning Model: the Effect of Information Cascade on Aggregate Welfare

[Conference]

Marziyeh Barghandan, Mohammad Malekzadeh, Atefeh Safdel and Iren Mazloomzadeh.
2014 - The IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2014, China.

◉ Social Balance and Signed Network Formation Games

[PDF]

Mohammad Malekzadeh, MohammadAmin Fazli, Pooya Jalaly Khalilabadi, Hamid R. Rabiee, and MohammadAli Safari.
2011 - The 5th SNA-KDD Workshop ’11 (SNA-KDD’11), USA.

◉ Persian CAPTCHA system to prevent automatic subscribing of software robots in web pages

[PDF](Persian)

Mohammad Malekzadeh and Mehdy Bohlool.
2008 - The 13th National CSI Computer Science , Iran.

News, Awards, Honors, etc.


◆ [JUNE-2021] I presented parts of our work recent work on Dimension-Adaptive Neural Architecture for Multivariate Sensor Data at the Third UK Mobile, Wearable and Ubiquitous Systems Research Symposium (MobiUK 2021) .

◆ [MAY-2021] I presented some of our work on Privacy-Preserving Machine Learning on Distributed Data for IADS PhD Forum at QMUL.

◆ [JAN-2021] I presented our paper Dopamine: Differentially Private Federated Learning on Medical Data in the AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-21) .

◆ [DEC-2020] Our submission to the ITU's global challenge has been chosen as the best solution for the sub-challenge: "Privacy-Preserving AI/ML for Healthcare" .

◆ [OCT-2020] We presented an tutorial, Deep Learning for Privacy in Multimedia , in ACM Multimedia 2020.

◆ [JUN-2020] I started working as a Research Assistant at Information Processing and Communications Lab at Imperial College London working on reliable and privacy-preserving federated learning, with Prof. Deniz Gunduz.

◆ [OCT-2019] I was awarded a grant of £290 covering registration to Privacy Preserving Machine Learning workshop at CCS conference in London.

◆ [JUN-2019] I started my PhD internship at Brave Research in London.

◆ [OCT-2018] Our team earned first place in Imperial College AIHack 2018.

◆ [APR-2018] I was accepted on to the Alan Turing Institute Data Study Group, covering all the travelling and accomodation expenses.

◆ [APR-2018] I was awarded a grant covering registration to EuroSys conference, Porto, Portugal.

◆ [MAR-2018] I was accepted on to the 2nd CommNet2 PhD Spring School , covering all the travelling and accomodation expenses, March.

◆ [DEC-2017] I was awarded a $30000 grant of Microsoft Azure for Research storage and compute for one year in 2018.

◆ [APR-2017] I was awarded a grant of $500 covering travel to EuroSys conference, Belgrade, Serbia.

◆ [JAN-2017] I was awarded a full Ph.D. studentship, to work on privacy-preserving personal data analytics, from Queen Mary University of London, Life Sciences Initiative .


Services and Experiences

Contact Details

Email:
<my_first_name>DOT<my_last_name> (at) nokia-bell-labs.com

Address:

Nokia Bell Labs, Broers Building, 21 J.J. Thomson Avenue,
West Cambridge, UK, Postcode: CB3 0FA

Social Media: