通过动态软提示更精准检测大模型的记忆数据，提升隐私风险评估能力。
Unlocking Memorization in Large Language Models with Dynamic Soft Prompting
- 用可变软提示替代固定前缀，让提示随输入自适应调整。
- 在文本和代码生成任务中，记忆发现率分别提升112.75%和32.26%。
- 适合关注大模型隐私安全与记忆泄露检测的研究者。
预训练的大语言模型（LLMs）已显著推动自然语言处理任务的发展，如摘要、问答和翻译。然而，这些模型容易记忆训练数据，带来隐私泄露和版权侵权等安全风险。准确衡量记忆化程度对评估和缓解此类风险至关重要。现有方法受限于仅使用固定前缀或静态软提示，无法响应输入变化。为此，本文提出一种基于动态、前缀依赖软提示的新型记忆化估计方法。通过训练一个Transformer生成器，动态生成适配输入的软提示，实现更精准的记忆数据提取。该方法不仅克服了以往局限性，在多种实验设置下均优于当前最优技术。尤其在文本生成和代码生成任务中，相比基线方法，记忆发现率分别提升最大112.75%和32.26%。
原文摘要 · Abstract (English)
Pretrained large language models (LLMs) have revolutionized natural language processing (NLP) tasks such as summarization, question answering, and translation. However, LLMs pose significant security risks due to their tendency to memorize training data, leading to potential privacy breaches and copyright infringement. Accurate measurement of this memorization is essential to evaluate and mitigate these potential risks. However, previous attempts to characterize memorization are constrained by either using prefixes only or by prepending a constant soft prompt to the prefixes, which cannot react to changes in input. To address this challenge, we propose a novel method for estimating LLM memorization using dynamic, prefix-dependent soft prompts. Our approach involves training a transformer-based generator to produce soft prompts that adapt to changes in input, thereby enabling more accurate extraction of memorized data. Our method not only addresses the limitations of previous methods but also demonstrates superior performance in diverse experimental settings compared to state-of-the-art techniques. In particular, our method can achieve the maximum relative improvement of 112.75% and 32.26% over the vanilla baseline in terms of discoverable memorization rate for the text generation task and code generation task respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。