Mitigating backdoor attacks in large language model-based recommendation systems: a defense and unlearning approach

• المؤلف الرئيسي: Salimin, Joanne Christina
• مؤلفون آخرون: Lim Wei Yang Bryan
• التنسيق: Final Year Project
• اللغة: English
• منشور في: Nanyang Technological University 2025
• الموضوعات: Computer and Information Science; Backdoor attacks
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/183829

Large Language Models (LLMs) have become integral to modern Recommendation Systems (RS) due to their scalability and ability to learn from diverse, large-scale datasets. However, these systems are increasingly vulnerable to data poisoning backdoor attacks, where adversaries embed hidden triggers wit...