语言模型中可学习的隐私神经元定位
Learnable Privacy Neurons Localization in Language Models
AI总结：
针对大语言模型记忆泄露个人可识别信息（PII）的隐私风险，该研究提出用可学习二值权重掩码经对抗训练定位PII敏感隐私神经元的方法，发现PII由跨层少量神经元记忆且具特异性，失活这些神经元可缓解风险，实验验证了算法有效性。
摘要：
大语言模型（LLM）会记忆并泄露隐私信息，尤其是个人可识别信息（PII），相关担忧在学界日益凸显。目前已有诸多研究致力于缓解这类隐私风险，但人们对LLM记忆PII的机制仍知之甚少。为填补这一空白，我们提出了一种开创性方法，用于精准定位LLM中对PII敏感的神经元（隐私神经元）。该方法采用可学习的二值权重掩码，通过对抗训练定位LLM中负责记忆PII的特定神经元。研究发现，PII由分布在所有层中的一小部分神经元记忆，呈现出PII特异性特征。此外，我们提出通过失活定位到的隐私神经元，验证其在缓解PII风险方面的潜力。定量与定性实验均证明了我们的神经元定位算法的有效性。
英文摘要：
Concerns regarding Large Language Models (LLMs) to memorize and disclose private information, particularly Personally Identifiable Information (PII), become prominent within the community. Many efforts have been made to mitigate the privacy risks. However, the mechanism through which LLMs memorize PII remains poorly understood. To bridge this gap, we introduce a pioneering method for pinpointing PII-sensitive neurons (privacy neurons) within LLMs. Our method employs learnable binary weight masks to localize specific neurons that account for the memorization of PII in LLMs through adversarial training. Our investigations discover that PII is memorized by a small subset of neurons across all layers, which shows the property of PII specificity. Furthermore, we propose to validate the potential in PII risk mitigation by deactivating the localized privacy neurons. Both quantitative and qualitative experiments demonstrate the effectiveness of our neuron localization algorithm.
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。
