More Like this

1. Does Differential Privacy Impact Bias in Pretrained Language Models?

   Islam, MK; Wang, A; Wang, T; Ji, Y; Fox, J; Zhao, J (June 2024, IEEE Data Engineering Bulletin (Special Issue on Privacy-preserving Data Management) Vol. 48 No. 2, June 2024.)

   Wang, H; Xiao, X (Ed.)

   Differential privacy (DP) is applied when fine-tuning pre-trained language models (LMs) to limit leakage of training examples. While most DP research has focused on improving a model’s privacy-utility tradeoff, some find that DP can be unfair to or biased against underrepresented groups. In this work, we extensively analyze the impact of DP on bias in LMs. We find differentially private training can increase the model bias against protected groups w.r.t AUC-based bias metrics. DP makes it more difficult for the model to differentiate between the positive and negative examples from the protected groups and other groups in the rest of the population. Our results also show that the impact of DP on bias is affected by both the privacy protection level and the underlying distribution of the dataset. 

   more » « less
2. Uldp-FL: Federated Learning with Across-Silo User-Level Differential Privacy

   https://doi.org/10.14778/3681954.3681966  

   Kato, Fumiyuki; Xiong, Li; Takagi, Shun; Cao, Yang; Yoshikawa, Masatoshi (July 2024, Proceedings of the VLDB Endowment)

   Differentially Private Federated Learning (DP-FL) has garnered attention as a collaborative machine learning approach that ensures formal privacy. Most DP-FL approaches ensure DP at the record-level within each silo for cross-silo FL. However, a single user's data may extend across multiple silos, and the desired user-level DP guarantee for such a setting remains unknown. In this study, we present Uldp-FL, a novel FL framework designed to guarantee user-level DP in cross-silo FL where a single user's data may belong to multiple silos. Our proposed algorithm directly ensures user-level DP through per-user weighted clipping, departing from group-privacy approaches. We provide a theoretical analysis of the algorithm's privacy and utility. Additionally, we improve the utility of the proposed algorithm with an enhanced weighting strategy based on user record distribution and design a novel private protocol that ensures no additional information is revealed to the silos and the server. Experiments on real-world datasets show substantial improvements in our methods in privacy-utility trade-offs under user-level DP compared to baseline methods. To the best of our knowledge, our work is the first FL framework that effectively provides user-level DP in the general cross-silo FL setting. 

   more » « less
3. Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

   https://doi.org/10.52202/085713-0340  

   Hod, Shlomi; Rosenblatt, Lucas; Stoyanovich, Julia (January 2025, Neural Information Processing Systems Foundation, Inc. (NeurIPS))

   Differentially private (DP) machine learning often relies on the availability of public data for tasks like privacy-utility trade-off estimation, hyperparameter tuning, and pretraining. While public data assumptions may be reasonable in text and image data, they are less likely to hold for tabular data due to tabular data heterogeneity across domains. We propose leveraging powerful priors to address this limitation; specifically, we synthesize realistic tabular data directly from schema-level specifications — such as variable names, types, and permissible ranges — without ever accessing sensitive records. To that end, this work introduces the notion of "surrogate" public data — datasets generated independently of sensitive data, which consume no privacy loss budget and are constructed solely from publicly available schema or metadata. Surrogate public data are intended to encode plausible statistical assumptions (informed by publicly available information) into a dataset with many downstream uses in private mechanisms. We automate the process of generating surrogate public data with large language models (LLMs); in particular, we propose two methods: direct record generation as CSV files, and automated structural causal model (SCM) construction for sampling records. Through extensive experiments, we demonstrate that surrogate public tabular data can effectively replace traditional public data when pretraining differentially private tabular classifiers. To a lesser extent, surrogate public data are also useful for hyperparameter tuning of DP synthetic data generators, and for estimating the privacy-utility tradeoff. 

   more » « less
4. Effectively using public data in privacy preserving Machine learning

   Milad Nasr, Saeed Mahloujifar (July 2023, Proceedings of the 40th International Conference on Machine Learning)

   Andreas Krause, Emma Brunskill (Ed.)

   Differentially private (DP) machine learning techniques are notorious for their degradation of model utility (e.g., they degrade classification accuracy). A recent line of work has demonstrated that leveraging public data can improve the trade-off between privacy and utility when training models with DP guaranteed. In this work, we further explore the potential of using public data in DP models, showing that utility gains can in fact be significantly higher than what shown in prior works. Specifically, we introduce DOPE-SGD, a modified DP-SGD algorithm that leverages public data during its training. DOPE-SGD uses public data in two complementary ways: (1) it uses advance augmentation techniques that leverages public data to generate synthetic data that is effectively embedded in multiple steps of the training pipeline; (2) it uses a modified gradient clipping mechanism (which is a standard technique in DP training) to change the origin of gradient vectors using the information inferred from available public and synthetic data, therefore boosting utility. We also introduce a technique to ensemble intermediate DP models by leveraging the post processing property of differential privacy to further improve the accuracy of the predictions. Our experimental results demonstrate the effectiveness of our approach in improving the state-of-the-art in DP machine learning across multiple datasets, network architectures, and application domains. For instance, assuming access to 2,000 public images, and for a privacy budget of 𝜀=2,𝛿=10−5, our technique achieves an accuracy of 75.1 on CIFAR10, significantly higher than 68.1 achieved by the state of the art. 

   more » « less
5. Privacy and Accuracy-Aware AI/ML Model Deduplication

   https://doi.org/10.1145/3725340  

   Guan, Hong; Yu, Lei; Zhou, Lixi; Xiong, Li; Chowdhury, Kanchan; Xie, Lulu; Xiao, Xusheng; Zou, Jia (June 2025, Proceedings of the ACM on Management of Data)

   With the growing adoption of privacy-preserving machine learning algorithms, such as Differentially Private Stochastic Gradient Descent (DP-SGD), training or fine-tuning models on private datasets has become increasingly prevalent. This shift has led to the need for models offering varying privacy guarantees and utility levels to satisfy diverse user requirements. Managing numerous versions of large models introduces significant operational challenges, including increased inference latency, higher resource consumption, and elevated costs. Model deduplication is a technique widely used by many model serving and database systems to support high-performance and low-cost inference queries and model diagnosis queries. However, none of the existing model deduplication works has considered privacy, leading to unbounded aggregation of privacy costs for certain deduplicated models and inefficiencies when applied to deduplicate DP-trained models. We formalize the problem of deduplicating DP-trained models for the first time and propose a novel privacy- and accuracy-aware deduplication mechanism to address the problem. We developed a greedy strategy to select and assign base models to target models to minimize storage and privacy costs. When deduplicating a target model, we dynamically schedule accuracy validations and apply the Sparse Vector Technique to reduce the privacy costs associated with private validation data. Compared to baselines, our approach improved the compression ratio by up to 35× for individual models (including large language models and vision transformers). We also observed up to 43× inference speedup due to the reduction of I/O operations. 

   more » « less