Guoxing Chen
Papers
1
Total Citations
3
H-Index
1
About
Dr. Guoxing Chen is a leading researcher in artificial intelligence security, with a primary focus on the vulnerabilities of large language models (LLMs). His groundbreaking work investigates how open-source LLMs can be compromised through seemingly benign plugins and adapters—a threat vector he terms "Trojaning." In his seminal 2023 paper, "The Philosopher's Stone: Trojaning Plugins of Large Language Models," Dr. Chen demonstrated that low-rank adapters, widely used to efficiently fine-tune LLMs for specialized tasks without expensive hardware, can be weaponized to embed hidden backdoors. This research, already garnering 3 citations in its early stages, has fundamentally shifted the conversation around open-source model safety, revealing that the very tools designed to democratize AI access can become vectors for attack. By exposing this critical vulnerability, Dr. Chen has provided the community with essential insights for developing more robust defense mechanisms, ensuring that the push for accessible, powerful AI does not come at the cost of security. His work is essential reading for anyone concerned with the safe deployment of large language models.
Research Focus
Key Achievements
Top Papers
- 1The Philosopher's Stone: Trojaning Plugins of Large Language Models3 citations · 2023