Unlocking Memorization in Large Language Models with Dynamic Soft Prompting

TL;DR

This work proposes a novel method for estimating LLM memorization using dynamic, prefix-dependent soft prompts that involves training a transformer-based generator to produce soft prompts that adapt to changes in input, thereby enabling more accurate extraction of memorized data.

Abstract

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.

Figures (4)

• Figure 1: Conceptual comparison of three methods for extracting memorized data from the target LLM.
• Figure 2: Illustration of our method.
• Figure 3: Illustration of naive mapping $m(\cdot)$ with examples.
• Figure 4: Ablation Study on Prefix Size and Length of Prompt with Exact Extraction Rate (ER)