Shasha Yu is completing a PhD by Published Works at Cardiff Metropolitan University, UK, and holds master’s degrees in data analytics, computer science, and law. Her broader research interests center on AI safety and alignment, with interdisciplinary perspectives spanning security, privacy, human factors, and governance. Her recent research focuses on emerging risks and evaluation challenges in increasingly agentic AI systems, particularly behavioral and evaluation gaps between expressed responses and actual actions. She teaches the graduate-level course MSDA 3040 Modern Data Engineering.
Shasha Yu
Part-time Instructor, SPS
- About
- Scholarly and creative works
Degrees
- M.S. in Data Analytics, Clark University, 2023
- M.S. in Advanced Computer Science, Cardiff Metropolitan University, 2022
- Juris Master in , Xiangtan University, 2006
- Ph.D. in Artificial Intelligence, Cardiff Metropolitan University, In Progress
Affiliated Departments
Scholarly and creative works
-
The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents
2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET)2026 -
Rethinking AI literacy education in higher education: Bridging risk perception and responsible adoption
Social Sciences & Humanities Open2026Vol. 13 -
Operational Hallucination and Safety Drift in AI Agents
2026 IEEE International Conference on AI and Data Analytics (ICAD)2026 -
When Saying “No” Is Not Enough: Cognitive-Action Decoupling and the Illusion of Safety in LLM Agents
Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency2026 -
Chapter: Trust and Trustworthiness: Privacy Protection in the ChatGPT EraPublished by Springer2024 -
Insights Into Privacy Protection Research in AI
IEEE Access2024Vol. 12 -
Chapter: Trust and risk: Psybersecurity in the AI eraPublished by CRC Press2024 -
Enhancing Smart Home Security: A Privacy Risk Analysis Framework
International Conference on Cyber Security, Privacy in Communication Networks2023 -
Applications for Artificial Intelligence and Digital Forensics in National Security
Chapter: A Balance of Power: Exploring the Opportunities and Challenges of AI for a NationPublished by Springer2023 -
Data Protection in a Post-Pandemic Society
Chapter: Securing Privacy During a World Health Emergency: Exploring How to Create a Balance Between the Need to Save the World and People’s Right to PrivacyPublished by Springer2023 -
Artificial Intelligence and National Security
Chapter: Insights into the next generation of policing: Understanding the impact of technology on the police force in the digital agePublished by Springer2022 -
Artificial Intelligence in Cyber Security: Impact and Implications
Chapter: Implications of AI in National Security: Understanding the Security Issues and Ethical ChallengesPublished by Springer2022
