The following contains currently open thesis topics in our areas of research. If you are interested in a topic or have a thesis idea of your own that might fit our research interests, please contact us directly.

All
Machine Learning/AI and Security
Security and Privacy of Decentralized Systems and DLTs
Software Protection

Machine Learning/AI and Security
Security and Privacy of Decentralized Systems and DLTs
Software Protection

Backdoor (data poisoning) attacks & defenses

Machine Learning/AI and Security

Analyse and evaluate attack vectors for poisoning attacks, evaluate their effectiveness and side-effects, as well as existing defenses, and develop new detection/defense mechanisms.

Intro papers, e.g. “Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning” or “BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain”
Video: A talk about one defense mechanism: “Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks”

Please contact Rudolf Mayer.

Back

To top