Detecting Hidden Backdoors in Large Language Models

Abstract

The adoption of LLMs in critical systems raises concerns regarding privacy, security and trust, particularly with regard to the risk of hidden backdoors — malicious triggers that cause covert data transfer or altered behaviour. Such threats are difficult to detect, especially when models are black-box systems with concealed triggers. This thesis addresses this issue by empirically evaluating the DeepSeek-R1 model family for potential backdoors during local execution. The aim is to identify anomalies and recommend safer deployment practices.