# Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs

arXiv: https://arxiv.org/abs/2506.17353 · HTML: https://mlsanity.com/paper/2506.17353/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 53 of its 93 references that are in the map.
- First posted on arXiv 20 Jun 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)

## Builds on (most cited first, 30 of 53)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)

## Built on by (most cited first, 6 of 6)

- [On Protecting Agentic Systems' Intellectual Property via Watermarking](https://mlsanity.com/paper/2602.08401/) (2026)
- [Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought](https://mlsanity.com/paper/2605.28890/) (2026)
- [Functional Subspace Watermarking for Large Language Models](https://mlsanity.com/paper/2603.18793/) (2026)
- [Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models](https://mlsanity.com/paper/2605.12264/) (2026)
- [Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models](https://mlsanity.com/paper/2609.08418/) (2026)
- [The Privacy Fallacy of Crowdsourced Fine-Tuning: Extracting Proprietary Data via Topic-Based Poisoning](https://mlsanity.com/paper/2609.33985/) (2026)

## Abstract (arXiv)

The increasing demand for domain-specific and human-aligned Large Language Models (LLMs) has led to the widespread adoption of Supervised Fine-Tuning (SFT) techniques. SFT datasets often comprise valuable instruction-response pairs, making them highly valuable targets for potential extraction. This paper studies this critical research problem for the first time. We start by formally defining and formulating the problem, then explore various attack goals, types, and variants based on the unique properties of SFT data in real-world scenarios. Based on our analysis of extraction behaviors of direct extraction, we develop a novel extraction method specifically designed for SFT models, called Differentiated Data Extraction (DDE), which exploits the confidence levels of fine-tuned models and their behavioral differences from pre-trained base models. Through extensive experiments across multiple domains and scenarios, we demonstrate the feasibility of SFT data extraction using DDE. Our results show that DDE consistently outperforms existing extraction baselines in all attack settings. To counter this new attack, we propose a defense mechanism that mitigates DDE attacks with minimal impact on model performance. Overall, our research reveals hidden data leak risks in fine-tuned LLMs and provides insights for developing more secure models.