衡量投毒对模型参数和神经元激活的影响：以投毒CodeBERT为例的案例研究
Measuring Impacts of Poisoning on Model Parameters and Neuron Activations: A Case Study of Poisoning CodeBERT
AI总结：
该研究针对代码大模型的后门安全问题，以投毒CodeBERT为对象分析模型参数与神经元激活，发现投毒样本的激活值和上下文嵌入有显著特征，为代码LLM的白盒后门检测提供参考。
摘要：
大语言模型（LLMs）已彻底变革了软件开发实践，但人们对其安全性产生了担忧，尤其是针对隐藏后门（又称木马）的问题。后门攻击指的是在训练数据中插入触发器，使攻击者能够恶意操纵模型的行为。本文聚焦于通过分析模型参数来检测代码模型中的潜在后门信号。具体而言，我们研究了干净与投毒的CodeBERT模型的注意力权重与偏置、激活值以及上下文嵌入。结果表明，投毒CodeBERT模型的投毒样本在激活值和上下文嵌入上存在显著模式；但注意力权重与偏置未表现出任何明显差异。本研究通过分析参数与激活，为代码领域LLM后门信号的白盒检测相关工作提供了助力。
英文摘要：
Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into training data, allowing attackers to manipulate the behavior of the model maliciously. In this paper, we focus on analyzing the model parameters to detect potential backdoor signals in code models. Specifically, we examine attention weights and biases, activation values, and context embeddings of the clean and poisoned CodeBERT models. Our results suggest noticeable patterns in activation values and context embeddings of poisoned samples for the poisoned CodeBERT model; however, attention weights and biases do not show any significant differences. This work contributes to ongoing efforts in white-box detection of backdoor signals in LLMs of code through the analysis of parameters and activations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
