paper-with-me

홈 › Papers

Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!

2025-05-21 · Zhexin Zhang, Yuhao Sun, Junxiao Yang, Shiyao Cui, Hongning Wang, Minlie Huang

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the creator of the open-source LLMs can later extract the private downstream fine-tuning data through simple backdoor training, only requiring black-box access to the fine-tuned downstream model. Our comprehensive experiments, across 4 popularly used open-source models with 3B to 32B parameters and 2 downstream datasets, suggest that the extraction performance can be strikingly high: in practical settings, as much as 76.3% downstream fine-tuning data (queries) out of a total 5,000 samples can be perfectly extracted, and the success rate can increase to 94.9% in more ideal settings. We also explore a detection-based defense strategy but find it can be bypassed with improved attack. Overall, we highlight the emergency of this newly identified data breaching risk in fine-tuning, and we hope that more follow-up research could push the progress of addressing this concerning risk. The code and data used in our experiments are released at https://github.com/thu-coai/Backdoor-Data-Extraction.

📄 PDF Abstract BibTeX arXiv:2505.15656

Code (1)

thu-coai/backdoor-data-extraction 공식 구현 pytorch

Similar Papers 제목 키워드 기반

How to Train an Accurate and Efficient Object Detection Model on Any Dataset

2022-11-30 · Galina Zalesskaya, Bogna Bylicka, Eugene Liu

The rapidly evolving industry demands high accuracy of the models without the need for time-consuming and computationally expensive experiments required for fine-tuning. Moreover, a model and training pipeline, which was…

CPUobject-detectionObject Detection

From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation

2024-06-05 · Ali Malik, Stephen Mayhew, Chris Piech, Klinton Bicknell

We study the problem of controlling the difficulty level of text generated by Large Language Models (LLMs) for contexts where end-users are not fully proficient, such as language learners. Using a novel framework, we eva…

Language ModelingLanguage ModellingReinforcement Learning (RL)

On Evaluating the Durability of Safeguards for Open-Weight LLMs

2024-12-10 · Xiangyu Qi, Boyi Wei, Nicholas Carlini, Yangsibo Huang 외

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, …

A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity Recognition

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Pre-trained language models (PLM) are effective components of few-shot named entity recognition (NER) approaches when augmented with continued pre-training on task-specific out-of-domain data or fine-tuning on in-domain …

Contrastive LearningLow Resource Named Entity Recognitionnamed-entity-recognitionNamed Entity Recognition+3

A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity Recognition

2022-04-11 · RepL4NLP (ACL) 2022 5 · Yuxuan Chen, Jonas Mikkelsen, Arne Binder, Christoph Alt 외

Pre-trained language models (PLM) are effective components of few-shot named entity recognition (NER) approaches when augmented with continued pre-training on task-specific out-of-domain data or fine-tuning on in-domain …

Contrastive LearningLow Resource Named Entity Recognitionnamed-entity-recognitionNamed Entity Recognition+3