Large Language Models (LLMs) are powerful tools for natural language processing, enabling novel applications and user experiences. However, to achieve optimal performance, LLMs often require adaptation with private data, which poses privacy and security challenges. Several techniques have been proposed to adapt LLMs with private data, such as Low-Rank Adaptation (LoRA), Soft Prompt Tuning (SPT), and In-Context Learning (ICL), but their comparative privacy and security properties have not been systematically investigated. In this work, we fill this gap by evaluating the robustness of LoRA, SPT, and ICL against three types of well-established attacks: membership inference, which exposes data leakage (privacy); backdoor, which injects malicious behavior (security); and model stealing, which can violate intellectual property (privacy and security). Our results show that there is no silver bullet for privacy and security in LLM adaptation and each technique has different strengths and weaknesses.

对三种LLM（Large Language Models）技术（Low-Rank Adaptation、Soft Prompt Tuning和In-Context Learning）在隐私和安全方面的鲁棒性进行评估，结果表明在LLM适应性中不存在绝对的隐私和安全解决方案。

最后一人站立：对 Soft Prompt Tuning、LoRA 和 In-Context Learning 的安全和隐私的比较分析