Master's thesis: Resilience against AI-based Cybersecurity Attacks
Teknik, data och digitalt · IT-infrastruktur och säkerhet · Cybersäkerhet · Maskininlärning · Mjukvaruutveckling
I korthet
This master's thesis project focuses on developing resilience against AI-based cybersecurity attacks. The goal is to understand AI attack types, their impact, and protective strategies, potentially using a game-theoretic approach with AI attacker and defender agents. The thesis will involve reviewing literature, designing a prototype framework, and evaluating its effectiveness in enhancing system resilience against evolving AI threats.
Ansvarsområden
- Review existing work on offensive AI and AI-based cybersecurity defence, emphasizing game theory and reinforcement learning.
- Design and prototype an approach where an AI attacker and AI defender interact with a software system.
- Model the interaction between AI attacker and defender using game-theoretic concepts.
- Apply reinforcement learning for strategy improvement based on actions, rewards, and system state.
- Evaluate the approach for attack effectiveness, defensive adaptation, and overall system resilience.
Krav
- Enrolled in a master's program in computer science and engineering at a Swedish university.
- Completed AI-related courses or gained work experience with AI/ML (e.g., reinforcement learning) is advantageous.
- Knowledge of cybersecurity is advantageous.
Förmåner
- 30 ECTS credits
- 10,000 SEK compensation upon successful completion of the thesis.
#AI#Cybersecurity#Game Theory#Reinforcement Learning#Software Systems#Resilience#Offensive AI#Defensive AI#Sweden#Gothenburg#Master's Thesis