More Like this

1. SeqPATE: Differentially Private Text Generation via Knowledge Distillation

   Tian, Zhiliang; Zhao, Yingxiu; Huang, Ziyue; Wang, Yu-Xiang; Zhang, Nevin; He, He (December 2022, Advances in neural information processing systems)

   Protecting the privacy of user data is crucial for text generation models, which can leak sensitive information during generation. Differentially private (DP) learning methods provide guarantees against identifying the existence of a training sample from model outputs. PATE is a recent DP learning algorithm that achieves high utility with strong privacy protection on training samples. However, text generation models output tokens sequentially in a large output space; the classic PATE algorithm is not customized for this setting. Furthermore, PATE works well to protect sample-level privacy, but is not designed to protect phrases in samples. In this paper, we propose SeqPATE, an extension of PATE to text generation that protects the privacy of individual training samples and sensitive phrases in training data. To adapt PATE to text generation, we generate pseudo-contexts and reduce the sequence generation problem to a next-word prediction problem. To handle the large output space, we propose a candidate filtering strategy to dynamically reduce the output space, and refine the teacher aggregation of PATE to avoid low agreement due to voting for a large number of candidates. To further reduce privacy losses, we use knowledge distillation to reduce the number of teacher queries. The experiments verify the effectiveness of SeqPATE in protecting both training samples and sensitive phrases. 

   more » « less
2. Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning

   Liu, Chong; Zhu, Yuqing; Chaudhuri, Kamalika; Wang, Yu-Xiang (November 2021, Journal of machine learning research)

   Krause, Andreas (Ed.)

   The Private Aggregation of Teacher Ensembles (PATE) framework is one of the most promising recent approaches in differentially private learning. Existing theoretical analysis shows that PATE consistently learns any VC-classes in the realizable setting, but falls short in explaining its success in more general cases where the error rate of the optimal classifier is bounded away from zero. We fill in this gap by introducing the Tsybakov Noise Condition (TNC) and establish stronger and more interpretable learning bounds. These bounds provide new insights into when PATE works and improve over existing results even in the narrower realizable setting. We also investigate the compelling idea of using active learning for saving privacy budget, and empirical studies show the effectiveness of this new idea. The novel components in the proofs include a more refined analysis of the majority voting classifier — which could be of independent interest — and an observation that the synthetic “student” learning problem is nearly realizable by construction under the Tsybakov noise condition. 

   more » « less
3. Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy

   Redberg, Rachel; Zhu, Yuqing; Wang, Yu-Xiang (April 2023, Proceedings of Machine Learning Research)

   The ''Propose-Test-Release'' (PTR) framework is a classic recipe for designing differentially private (DP) algorithms that are data-adaptive, i.e. those that add less noise when the input dataset is nice. We extend PTR to a more general setting by privately testing data-dependent privacy losses rather than local sensitivity, hence making it applicable beyond the standard noise-adding mechanisms, e.g. to queries with unbounded or undefined sensitivity. We demonstrate the versatility of generalized PTR using private linear regression as a case study. Additionally, we apply our algorithm to solve an open problem from ''Private Aggregation of Teacher Ensembles (PATE)'' -- privately releasing the entire model with a delicate data-dependent analysis. 

   more » « less
4. Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE

   Zhu, Yuqing (April 2022, Proceedings of Machine Learning Research)

   We provide an end-to-end Renyi DP based-framework for differentially private top-𝑘 selection. Unlike previous approaches, which require a data-independent choice on 𝑘, we propose to privately release a data-dependent choice of 𝑘 such that the gap between 𝑘-th and the (𝑘+1)st “quality” is large. This is achieved by an extension of the Report-Noisy-Max algorithm with a more concentrated Gaussian noise. Not only does this eliminates one hyperparameter, the adaptive choice of 𝑘 also certifies the stability of the top-𝑘 indices in the unordered set so we can release them using a combination of the propose-test-release (PTR) framework and the Distance-to-Stability mechanism. We show that our construction improves the privacy-utility trade-offs compared to the previous top-𝑘 selection algorithms theoretically and empirically. Additionally, we apply our algorithm to “Private Aggregation of Teacher Ensembles (PATE)” in multi-label classification tasks with a large number of labels and show that it leads to significant performance gains. 

   more » « less
5. A generic approach for reproducible model distillation

   https://doi.org/10.1007/s10994-024-06597-w  

   Zhou, Yunzhe; Xu, Peiru; Hooker, Giles (August 2024, Machine Learning)

   Abstract Model distillation has been a popular method for producing interpretable machine learning. It uses an interpretable “student” model to mimic the predictions made by the black box “teacher” model. However, when the student model is sensitive to the variability of the data sets used for training even when keeping the teacher fixed, the corresponded interpretation is not reliable. Existing strategies stabilize model distillation by checking whether a large enough sample of pseudo-data is generated to reliably reproduce student models, but methods to do so have so far been developed separately for each specific class of student model. In this paper, we develop a generic approach for stable model distillation based on central limit theorem for the estimated fidelity of the student to the teacher. We start with a collection of candidate student models and search for candidates that reasonably agree with the teacher. Then we construct a multiple testing framework to select a sample size such that the consistent student model would be selected under different pseudo samples. We demonstrate the application of our proposed approach on three commonly used intelligible models: decision trees, falling rule lists and symbolic regression. Finally, we conduct simulation experiments on Mammographic Mass and Breast Cancer datasets and illustrate the testing procedure throughout a theoretical analysis with Markov process. The code is publicly available athttps://github.com/yunzhe-zhou/GenericDistillation. 

   more » « less