Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?

• URL: http://arxiv.org/abs/2307.16382v3
• Date: Mon, 15 Apr 2024 22:34:22 GMT
• Title: Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?
• Authors: Albert Yu Sun, Eliott Zemour, Arushi Saxena, Udith Vaidyanathan, Eric Lin, Christian Lau, Vaikkunth Mugunthan,
• Abstract summary: We simulate a privacy attack on GPT-3 using OpenAI's fine-tuning API. Our objective is to determine if personally identifiable information (PII) can be extracted from this model. Our findings reveal that fine-tuning GPT3 for both tasks led to the model memorizing and disclosing critical personally identifiable information (PII) obtained from the underlying fine-tuning dataset.
• Score: 1.7590081165362783
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning practitioners often fine-tune generative pre-trained models like GPT-3 to improve model performance at specific tasks. Previous works, however, suggest that fine-tuned machine learning models memorize and emit sensitive information from the original fine-tuning dataset. Companies such as OpenAI offer fine-tuning services for their models, but no prior work has conducted a memorization attack on any closed-source models. In this work, we simulate a privacy attack on GPT-3 using OpenAI's fine-tuning API. Our objective is to determine if personally identifiable information (PII) can be extracted from this model. We (1) explore the use of naive prompting methods on a GPT-3 fine-tuned classification model, and (2) we design a practical word generation task called Autocomplete to investigate the extent of PII memorization in fine-tuned GPT-3 within a real-world context. Our findings reveal that fine-tuning GPT3 for both tasks led to the model memorizing and disclosing critical personally identifiable information (PII) obtained from the underlying fine-tuning dataset. To encourage further research, we have made our codes and datasets publicly available on GitHub at: https://github.com/albertsun1/gpt3-pii-attacks

Related papers

• Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation [15.94564349084642]
  Self-rationalization method is typically used in natural language inference tasks. We fine-tune a model to learn veracity prediction with annotated labels. We generate synthetic explanations from three large language models.
  arXiv  Detail & Related papers  (2024-10-05T02:19:49Z)
• Foundational GPT Model for MEG [3.524869467682149]
  We propose two classes of deep learning foundational models that can be trained using forecasting of unlabelled brain signals. First, we consider a modified Wavenet; and second, we consider a modified Transformer-based (GPT2) model. We compare the performance of these deep learning models with standard linear autoregressive (AR) modelling on MEG data.
  arXiv  Detail & Related papers  (2024-04-14T13:48:24Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation [25.317788211120362]
  We investigate the role of generative AI models in providing human tutor-style programming hints. Recent works have benchmarked state-of-the-art models for various feedback generation scenarios. We develop a novel technique, GPT4Hints-GPT3.5Val, to push the limits of generative AI models.
  arXiv  Detail & Related papers  (2023-10-05T17:02:59Z)
• Going beyond research datasets: Novel intent discovery in the industry setting [60.90117614762879]
  This paper proposes methods to improve the intent discovery pipeline deployed in a large e-commerce platform. We show the benefit of pre-training language models on in-domain data: both self-supervised and with weak supervision. We also devise the best method to utilize the conversational structure (i.e., question and answer) of real-life datasets during fine-tuning for clustering tasks, which we call Conv.
  arXiv  Detail & Related papers  (2023-05-09T14:21:29Z)
• Is GPT-3 a Good Data Annotator? [30.9559541574174]
  GPT-3 is a large-scale language model developed by OpenAI. In this paper, we evaluate the performance of GPT-3 as a data annotator.
  arXiv  Detail & Related papers  (2022-12-20T17:28:41Z)
• Just Fine-tune Twice: Selective Differential Privacy for Large Language Models [69.66654761324702]
  We propose a simple yet effective just-fine-tune-twice privacy mechanism to achieve SDP for large Transformer-based language models. Experiments show that our models achieve strong performance while staying robust to the canary insertion attack.
  arXiv  Detail & Related papers  (2022-04-15T22:36:55Z)
• Using GPT-2 to Create Synthetic Data to Improve the Prediction Performance of NLP Machine Learning Classification Models [0.0]
  It is becoming common practice to utilize synthetic data to boost the performance of Machine Learning Models. I used a Yelp pizza restaurant reviews dataset and transfer learning to fine-tune a pre-trained GPT-2 Transformer Model to generate synthetic pizza reviews data. I then combined this synthetic data with the original genuine data to create a new joint dataset.
  arXiv  Detail & Related papers  (2021-04-02T20:20:42Z)
• KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation [100.79870384880333]
  We propose a knowledge-grounded pre-training (KGPT) to generate knowledge-enriched text. We adopt three settings, namely fully-supervised, zero-shot, few-shot to evaluate its effectiveness. Under zero-shot setting, our model achieves over 30 ROUGE-L on WebNLG while all other baselines fail.
  arXiv  Detail & Related papers  (2020-10-05T19:59:05Z)
• Language Models are Few-Shot Learners [61.36677350504291]
  We show that scaling up language models greatly improves task-agnostic, few-shot performance. We train GPT-3, an autoregressive language model with 175 billion parameters, and test its performance in the few-shot setting. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks.
  arXiv  Detail & Related papers  (2020-05-28T17:29:03Z)
• Improving 3D Object Detection through Progressive Population Based Augmentation [91.56261177665762]
  We present the first attempt to automate the design of data augmentation policies for 3D object detection. We introduce the Progressive Population Based Augmentation (PPBA) algorithm, which learns to optimize augmentation strategies by narrowing down the search space and adopting the best parameters discovered in previous iterations. We find that PPBA may be up to 10x more data efficient than baseline 3D detection models without augmentation, highlighting that 3D detection models may achieve competitive accuracy with far fewer labeled examples.
  arXiv  Detail & Related papers  (2020-04-02T05:57:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.