paper-with-me

홈 › Papers

From Robustness to Privacy and Back

2023-02-03 · Hilal Asi, Jonathan Ullman, Lydia Zakynthinou

We study the relationship between two desiderata of algorithms in statistical inference and machine learning: differential privacy and robustness to adversarial data corruptions. Their conceptual similarity was first observed by Dwork and Lei (STOC 2009), who observed that private algorithms satisfy robustness, and gave a general method for converting robust algorithms to private ones. However, all general methods for transforming robust algorithms into private ones lead to suboptimal error rates. Our work gives the first black-box transformation that converts any adversarially robust algorithm into one that satisfies pure differential privacy. Moreover, we show that for any low-dimensional estimation task, applying our transformation to an optimal robust estimator results in an optimal private estimator. Thus, we conclude that for any low-dimensional task, the optimal error rate for $\varepsilon$-differentially private estimators is essentially the same as the optimal error rate for estimators that are robust to adversarially corrupting $1/\varepsilon$ training samples. We apply our transformation to obtain new optimal private estimators for several high-dimensional tasks, including Gaussian (sparse) linear regression and PCA. Finally, we present an extension of our transformation that leads to approximate differentially private algorithms whose error does not depend on the range of the output space, which is impossible under pure differential privacy.

📄 PDF Abstract BibTeX arXiv:2302.01855

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Local and Central Differential Privacy for Robustness and Privacy in Federated Learning

2020-09-08 · Mohammad Naseri, Jamie Hayes, Emiliano De Cristofaro

Federated Learning (FL) allows multiple participants to train machine learning models collaboratively by keeping their datasets local while only exchanging model updates. Alas, this is not necessarily free from privacy a…

Federated Learning

Differentially-Private Decision Trees and Provable Robustness to Data Poisoning

2023-05-24 · Daniël Vos, Jelle Vos, Tianyu Li, Zekeriya Erkin 외

Decision trees are interpretable models that are well-suited to non-linear learning problems. Much work has been done on extending decision tree learning algorithms with differential privacy, a system that guarantees the…

Data Poisoning

Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy

2026-05-20 · Aman Saxena, Jan Schuchardt, Yan Scholten, Stephan Günnemann arxiv

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees…

Federated Learning in Adversarial Settings

2020-10-15 · Raouf Kerkouche, Gergely Ács, Claude Castelluccia

Federated Learning enables entities to collaboratively learn a shared prediction model while keeping their training data locally. It prevents data collection and aggregation and, therefore, mitigates the associated priva…

Federated LearningQuantization

Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation

2026-08-25 · Minh Tran, Cuong Dang, Tuc Nguyen, Khanh-Tung Tran 외 arxiv

Retrieval-Augmented Generation (RAG) enhances large language models by grounding outputs in external knowledge, improving factuality and reducing hallucinations. At the same time, the retrieval-augmented pipeline introdu…