M.Sc. Marvin Xhemrishi
Technische Universität München
Professur für Codierung und Kryptographie (Prof. Wachter-Zeh)
Postadresse
Postal:
Theresienstr. 90
80333 München
Abschlussarbeiten
Angebotene Abschlussarbeiten
Laufende Abschlussarbeiten
Implementation of model poisoning attacks in federated learning
Beschreibung
Federated learning is a machine learning paradigm where decentralized entities (clients) collaboratively learn using their private data. A central server acts as a coordinator of the learning process. Due to the sensitivity of the private data involved, the data cannot be transferred. A salient problem of federated learning is the presence of malicious clients, which are clients that try to destroy the learning process. Malicious clients can do this by corrupting their data and/or by modifying their local model updates. The goal of this project is to understand how model poisoning attacks and defense strategies perform under different scenarios of federated learning using experiments.
References:
[1]- https://www.ndss-symposium.org/wp-content/uploads/ndss2021_6C-3_24498_paper.pdf
[2]- https://arxiv.org/pdf/1903.03936.pdf
[3]- https://arxiv.org/pdf/2304.00160.pdf
Voraussetzungen
- Basic knowledge of machine learning
- Python programming skills, knowledge of PyTorch is an advantage
Kontakt
marvin.xhemrishi@tum.de
Betreuer:
Model poisoning attacks in Federated Learning
Beschreibung
Federated learning is a machine learning paradigm that aims to learn collaboratively from decentralized private data. However, due to its decentralized nature, federated learning is susceptible to model poisoning attacks, where malicious clients try to corrupt the learning process by modifying local model updates. The goal of this seminar is to provide a high-level overview of model poisoning attacks in federated learning using [1-2] and other references.
Voraussetzungen
References:
[1] - https://www.ndss-symposium.org/wp-content/uploads/ndss2021_6C-3_24498_paper.pdf
[2] - https://arxiv.org/pdf/1903.03936.pdf
Betreuer:
Publikationen
2022
- Adaptive private distributed matrix multiplication. IEEE Transactions on Information Theory, 2022 mehr…
- The Wiretap Channel for Capacitive PUF-Based Security Enclosures. IACR Transactions on Cryptographic Hardware and Embedded Systems, 2022 mehr…
- Analysis of Communication Channels Related to Physical Unclonable Functions. Workshop on Coding and Cryptography (WCC), 2022 mehr…
- Distributed Linear Computations over Private Sparse Matrices. IEEE European School of Information Theory, 2022 mehr…
- Distributed Linear Computations over Private Sparse Matrices. Munich Workshop on Coding and Cryptography, 2022 mehr…
- Computational Code-Based Privacy for Coded Federated Learning. TUM ICE Workshop Raitenhaslach, 2022 mehr…
- Distributed Matrix-Vector Multiplication with Sparsity and Privacy Guarantees. IEEE International Symposium on Information Theory, 2022 mehr…
- Efficient Private Storage of Sparse Machine Learning Data. IEEE Information Theory Workshop, 2022 mehr…
- Computational Code-Based Privacy in Coded Federated Learning. IEEE International Symposium on Information Theory, 2022 mehr…
2021
2020
2019
- List Decoding of Short Codes for Communication over Unknown Fading Channels. , Workshop on Coding, Cooperation, and Security in Modern Communication Networks (COCO 2019) . , 2019 mehr…
- List Decoding for Fading Channels. Oberpfaffenhofen Workshop on High Throughput Coding (OWHTC) , 2019 mehr…
- List Decoding of Short Codes for Communication over Unknown Fading Channels. Asilomar Conference on Signals, Systems, and Computers, 2019 mehr…