Picture of Rawad Bitar

Rawad Bitar, Dr. Ph.D.

Technical University of Munich

Associate Professorship of Coding and Cryptography (Prof. Wachter-Zeh)

Postal address

Postal:
Theresienstr. 90
80333 München

Biography

Postdoctoral researcher working with Prof. Dr.-Ing Antonia Wachter-Zeh. I obtained a PhD from the ECE department of Rutgers University in January 2020. During my PhD, I held short term visiting positions at Aalto, Technical University of Berlin and the Chinese University of Hong Kong. In addition, I spent three years as PhD candidate at the ECE department of Illinois Institute of Technology (IIT). From August 2014 till January 2020, I was a member of the CSI lab supervised by Prof. Salim El Rouayheb.

In terms of studies, I received a masters degree in Information and Communication from the Lebanese University after doing the thesis at IIT in 2014. I graduated as a Computer and Communication Engineer from the Lebanese University in 2013 after doing the engineering senior project at Center of Nuclear Science and Science of Matter (CSNSM) in Paris, France and  an internship at procsim-consulting company in EPFL, Lausanne, Switzerland, in 2012.

Teaching

  • Winter semester 2021/2022: Security in Communications and Networks, jointly with Prof. Dr.-Ing Antonia Wachter-Zeh
  • Summer semester 2021: Coding Theory for Storage and Networks, jointly with Dr.-Ing Sven Puchinger
  • Winter semester 2020/2021: Security in Communications and Networks, jointly with Prof. Dr.-Ing Antonia Wachter-Zeh
  • Summer semester 2020: Coding Theory for Storage and Networks, jointly with Dr. Alessandro Neri

 

Theses

Available Theses

MAB-Based Efficient Distributed ML on the Cloud

Keywords:
Distributed Machine Learning (ML), Multi-Armed Bandits (MABs), Cloud Simulations (AWS, GCP, ...)

Description

We consider the problem of running a distributed machine learning algorithm on the cloud. This imposes several challenges. In particular, cloud instances may have different performances/speeds. To fully leverage the performance of the instances, we want to characterize their speed and potentially use the fastest ones. To explore the speed of the instances while exploiting them (assigning computational tasks), we use the theory of multi-armed bandits (MABs).

The goal of the research intership is to start by implementing existing theoretical algorithms [1] and possibly adapting them based on the experimental observations.

[1] M. Egger, R. Bitar, A. Wachter-Zeh and D. Gündüz, Efficient Distributed Machine Learning via Combinatorial Multi-Armed Bandits, submitted to IEEE Journal on Selected Areas in Communications (JSAC), 2022.

Prerequisites

  • Information Theory
  • Machine Learning Basics
  • Python (Intermediate Level)

Supervisor:

Private and Secure Federated Learning

Description

In federated learning, a machine learning model shall be trained on private user data with the help of a central server, the so-called federator. This setting differs from other machine learning settings in that the user data shall not be shared with the federator for privacy reasons and/or to decrease the communication load of the system.

Even though only intermediate results are shared, extra care is necessary to guarantee data privacy. An additional challenge arises if the system includes malicious users that breach protocol and send corrupt computation results.

The goal of this work is to design, implement and analyze coding- and information-theoretic solutions for privacy and security in federated learning.

Prerequisites

  • Coding Theory (e.g., Channel Coding)
  • Information Theory
  • Machine Learning Basics

Supervisor:

Theses in Progress

Burst Insdel Codes

Description

The internship focuses on the analysis of code properties for burst insertion-deletion errors.

Supervisor:

Secure and Private MR-LRCs based on LRS codes

Description

Security and privacy analysis on LRS codes or MR-LRCs

Supervisor:

Implementation of a Generic Federated Learning Framework

Description

Since the introduction of federated learning in [1], we can observe a rapidly growing body of research. In particular, we face challenges with respect to privacy, security and efficiency. The first half of this research internship aims at implementing a generic framework for simulating decentralized optimization procedures in a federated leraning setting. During the second half and with the help of the framework, the student should analyze the performance of selected state-of-the-art schemes.

Prerequisites

  • Coding Theory (e.g., Channel Coding)
  • Information Theory
  • Machine Learning Basics
  • Python (Intermediate Level)

Supervisor:

Secure Federated Learning

Description

In the initially proposed federated learning setting [1], the federator observes partial gradient computations of all clients contributing to a decentralized training procedure. However, clients might send malicious (corrupt) computations to harm the training process on purpose. Considering this model, security against malicious clients can be ensured by running statistics on the partial results [2, 3]. For example, clients’ results that differ significantly from the vast majority of responses can be excluded from the training process. In recent works, secure aggregation of partial work was proposed [4]. The goal is to let the master only observe the sum of all local models, and by this to enhance the privacy level of the clients’ data. These works, however, complicate the use of statistics to account for corrupt partial computations as the master only observes the aggregated result. The goal of this research internship is to review related literature on secure federated learning including their limitations, and to explore possible approaches to ensure security against potentially corrupt results while preserving privacy of the clients’ data.

[1] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y. Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” vol. 54, pp. 1273–1282, 20--22 Apr 2017.

[2] P. Blanchard, E. M. El Mhamdi, R. Guerraoui, and J. Stainer, “Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent,” in Advances in Neural Information Processing Systems, 2017, vol. 30.

[3] Z. Yang and W. U. Bajwa, “ByRDiE: Byzantine-Resilient Distributed Coordinate Descent for Decentralized Learning,” IEEE Transactions on Signal and Information Processing over Networks, vol. 5, no. 4, pp. 611–627, Dec. 2019.

[4] K. Bonawitz et al., “Practical Secure Aggregation for Privacy-Preserving Machine Learning,” Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. 2017. doi: 10.1145/3133956.3133982.

Prerequisites

  • Coding Theory (e.g., Channel Coding)
  • Information Theory

Supervisor:

Research Interests

Primary Interests
  • Private and Secure Distributed Computing/Storage

  • Coding for Insertions and Deletions

  • Information Theoretic Security

Secondary Interests
  • Network Coding

  • Machine Learning

Publications

Preprints / Under Review

  1. C. Hofmeister, R. Bitar, M. Xhemrishi and A. Wachter-Zeh, Secure Private and Adaptive Matrix Multiplication Beyond the Singleton Bound, submitted to IEEE Journal on Selected Areas in Information Theory (JSAIT), 2021.

  2. A. Lenz, R. Bitar, A. Wachter-Zeh and E. Yaakobi, Function-Correcting Codes, submitted to IEEE Transactions on Information Theory, 2021.

  3. R. Bitar and S. Jaggi, Communication Efficient Secret Sharing in the Presence of Malicious Adversary, preprint, arXiv:2002.03374, 2020.

  4. Y. Keshtkarjahromi, R. Bitar, V. Dasari, S. El Rouayheb, and H. Seferoglu, Secure Coded Cooperative Computation at the Heterogeneous Edge against Byzantine Attacks, preprint, arXiv:1908.05385, 2020.

  5. E. Klarlund, R. Bitar and S. El Rouayheb, Search Efficient Blockchain-Based Immutable Logging And Querying, submitted to BMC Medical Genomics, 2018.

Journals

  1. L. Welter, R. Bitar, A. Wachter-Zeh and E. Yaakobi, Multiple Criss-Cross Deletion and Insertion Correcting Codes, accepted in IEEE Transactions on Information Theory, 2022.

  2. R. Bitar, M. Xhemrishi and A. Wachter-Zeh, Adaptive Private Distributed Matrix Multiplication, IEEE Transactions on Information Theory, Early Access, January 2022.

  3. S. Li, R. Bitar, S. Jaggi and Y. Zhang, Network Coding with Myopic Adversaries, IEEE Journal on Selected Areas in Information Theory (JSAIT), Vol. 2, No. 4, December 2021. (arXiv:2102.09885)

  4. R. Bitar, L. Welter, I. Smagloy, A. Wachter-Zeh and E. Yaakobi, Criss-Cross Insertion and Deletion Correcting Codes, IEEE Transactions on Information Theory, Vol.67, No.12, December 2021. (arXiv:2004.14740)

  5. R. Bitar, Y. Xing, Y. Keshtkarjahromi, V. Dasari, S. El Rouayheb, and H. Seferoglu, Private and Rateless Adaptive Coded Computation at the Edge, EURASIP Journal on Wireless Communications and Networking, Vol.1, January 2021. (arXiv:1909.12611)

  6. R. Bitar, M. Wootters and S. El Rouayheb, Stochastic Gradient Coding for Straggler Mitigation in Distributed Learning, IEEE Journal on Selected Areas in Information Theory,, Vol.1, No. 1, May 2020. (arXiv:1905.05383)

  7. R. Bitar, P. Parag and S. El Rouayheb, Minimizing Latency for Secure Coded Computing Using Secret Sharing via Staircase Codes, IEEE Transactions on Communication, Vol. 68, No. 8, August 2020. (arXiv:1802.02640)

  8. R. Bitar and S. El Rouayheb, Staircase Codes for Secret Sharing with Optimal Communication and Read Overheads, IEEE Transactions on Information Theory, Vol. 64, No. 2, February 2018. (arXiv:1512.02990)

Conferences

  1. S. Kas Hanna and R. Bitar, Codes for Detecting Deletions and Insertions in Concatenated Strings, IEEE International Symposium on Information Theory (ISIT), 2021.

  2. A. Lenz, R. Bitar, A. Wachter-Zeh and E. Yaakobi, Function-Correcting Codes, IEEE International Symposium on Information Theory (ISIT), 2021.

  3. L. Welter, R. Bitar, A. Wachter-Zeh and E. Yaakobi, Multiple Criss-Cross Deletion-Correcting Codes, IEEE International Symposium on Information Theory (ISIT), 2021.

  4. S. Li, R. Bitar, S. Jaggi and Y. Zhang, Network Coding with Myopic Adversaries, IEEE International Symposium on Information Theory (ISIT), 2021.

  5. R. Bitar, S. Kas Hanna, N. Polyanskii and I. Vorobyev, Optimal Codes Correcting Localized Deletions, IEEE International Symposium on Information Theory (ISIT), 2021.

  6. R. Bitar, M. Xhemrishi and A. Wachter-Zeh, Rateless Codes for Private Distributed Matrix-Matrix Multiplication, IEEE International Symposium on Information Theory and its Applications (ISITA), 2020.

  7. R. Bitar and S. Jaggi, Communication Efficient Secret Sharing in the Presence of Malicious Adversary, IEEE International Symposium on Information Theory (ISIT), 2020.

  8. S. Kas Hanna, R. Bitar, P. Parag, V. Dasari and S. El Rouayheb, Adaptive Distributed Stochastic Gradient Descent for Minimizing Delay in the Presence of Stragglers, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, 2020.

  9. R. Bitar, I. Smagloy, L. Welter, A. Wachter-Zeh and E. Yaakobi, Criss-Cross Deletion Correcting Codes, IEEE International Symposium on Information Theory and its Applications (ISITA), 2020.

  10. Y. Keshtkarjahromi, R. Bitar, V. Dasari, S. El Rouayheb, and H. Seferoglu, Secure Coded Cooperative Computation at the Heterogeneous Edge against Byzantine Attacks, IEEE Global Communication Conference (GLOBECOM), Waikoloa, 2019

  11. R. Bitar, M. Wootters and S. El Rouayheb, Stochastic Gradient Coding for Straggler Mitigation in Distributed Learning, IEEE Information Theory Workshop (ITW), 2019.

  12. R. Bitar, Y. Xing, Y. Keshtkarjahromi, V. Dasari, S. El Rouayheb, and H. Seferoglu, PRAC: Private and Rateless Adaptive Coded Computation at the Edge, SPIE Defense + Commercial Sensing, Baltimore, 2019.

  13. R. Bitar and S. El Rouayheb, Staircase-PIR: Universally Robust Private Information Retrieval, IEEE Information Theory Workshop (ITW), Guangzhou, 2018.

  14. R. Bitar, P. Parag and S. El Rouayheb, Minimizing Latency for Secure Distributed Computing, IEEE International Symposium on Information Theory (ISIT), Aachen, 2017.

  15. R. Bitar and S. El Rouayheb, Staircase Codes for Secret Sharing with Optimal Communication and Read Overheads, IEEE International Symposium on Information Theory (ISIT), Barcelona, 2016.

  16. R. Bitar and S. El Rouayheb, Securing data against Limited-Knowledge Adversaries in Distributed Storage Systems, IEEE International Symposium on Information Theory (ISIT), Hong Kong, 2015.

PhD Thesis