Zonghao Huang

Zonghao Huang, Neil Zhenqiang Gong, Michael K. Reiter

Auditing the use of data in training machine-learning (ML) models is an increasingly pressing challenge, as myriad ML practitioners routinely leverage the effort of content creators to train models without their permission. In this paper, we propose a general method to audit an ML model for the use of a data-owner's data in training, without prior knowledge of the ML task for which the data might be used. Our method leverages any existing black-box membership inference method, together with a sequential hypothesis test of our own design, to detect data use with a quantifiable, tunable false-detection rate. We show the effectiveness of our proposed framework by applying it to audit data use in two types of ML models, namely image classifiers and foundation models.

Zonghao Huang, Neil Zhenqiang Gong, Michael K. Reiter

The growing trend of legal disputes over the unauthorized use of data in machine learning (ML) systems highlights the urgent need for reliable data-use auditing mechanisms to ensure accountability and transparency in ML. We present the first proactive, instance-level, data-use auditing method designed to enable data owners to audit the use of their individual data instances in ML models, providing more fine-grained auditing results than previous work. To do so, our research generalizes previous work integrating black-box membership inference and sequential hypothesis testing, expanding its scope of application while preserving the quantifiable and tunable false-detection rate that is its hallmark. We evaluate our method on three types of visual ML models: image classifiers, visual encoders, and vision-language models (Contrastive Language-Image Pretraining (CLIP) and Bootstrapping Language-Image Pretraining (BLIP) models). In addition, we apply our method to evaluate the performance of two state-of-the-art approximate unlearning methods. As a noteworthy second contribution, our work reveals that neither method successfully removes the influence of the unlearned data instances from image classifiers and CLIP models, even if sacrificing model utility by $10\%$.

Zonghao Huang, Neil Gong, Michael K. Reiter

Untrusted data used to train a model might have been manipulated to endow the learned model with hidden properties that the data contributor might later exploit. Data purification aims to remove such manipulations prior to training the model. We propose Mendata, a novel framework to purify manipulated training data. Starting from a small reference dataset in which a large majority of the inputs are clean, Mendata perturbs the training inputs so that they retain their utility but are distributed similarly (as measured by Wasserstein distance) to the reference data, thereby eliminating hidden properties from the learned model. A key challenge is how to find such perturbations, which we address by formulating a min-max optimization problem and developing a two-step method to iteratively solve it. We demonstrate the effectiveness of Mendata by applying it to defeat state-of-the-art data poisoning and data tracing techniques.