Why do you care about AI Existential Safety?

Rapid growth of AI systems brings not only exciting opportunities but also significant challenges. As AI becomes more involved in important decisions, it’s important that we make sure it stays safe, trustworthy, and aligned with human values. It is a responsibility to future generations to make sure AI helps rather than harms humanity. As a researcher in AI security, I care deeply about AI existential safety because the race to build more powerful AI systems often overlooks safety and ethical concerns. I believe that proactive research, and ethical foresight are critical to shaping a future where AI is trustworthy, and beneficial to all.

Please give at least one example of your research interests related to AI existential safety:

My research interests are in the field of AI safety and security. I study AI security using Evolutionary Game Theory and design resilient defense mechanisms for LLM-based multi-agent systems.
I recently participated in the 2025 AI Governance Modelling workshop at Teesside University, UK supported by the Future of Life Institute. The workshop focused on how we can use computer models and large language models (LLMs) to better understand and improve AI governance. Here are the outputs from the workshop:

1) A preprint: Media and responsible AI governance: a game-theoretic and LLM analysis.
Link to preprint: https://doi.org/10.48550/arXiv.2504.08640

2) A preprint: Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents.
Link to preprint:https://doi.org/10.48550/arXiv.2504.08640

3) Submitted to conference: Can Media Act as a Soft Regulator of Safe AI Development? A Game Theoretical Analysis.