DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Erchi, Huang, Pengrun, Chien, Eli, Thakkar, Om, Chaudhuri, Kamalika, Wang, Yu-Xiang, Wu, Ruihan
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918507553226752
author Wang, Erchi
Huang, Pengrun
Chien, Eli
Thakkar, Om
Chaudhuri, Kamalika
Wang, Yu-Xiang
Wu, Ruihan
author_facet Wang, Erchi
Huang, Pengrun
Chien, Eli
Thakkar, Om
Chaudhuri, Kamalika
Wang, Yu-Xiang
Wu, Ruihan
contents Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high barrier for non-expert practitioners. Prior works either rely on specialized verification languages that demand substantial domain expertise or remain semi-automated and require human-in-the-loop guidance. In this work, we investigate whether large language models (LLMs) can automate DP reasoning. We introduce DPrivBench, a benchmark in which each instance asks whether a function or algorithm satisfies a stated DP guarantee under specified assumptions. The benchmark is carefully designed to cover a broad range of DP topics, span diverse difficulty levels, and resist shortcut reasoning through trivial pattern matching. Experiments show that while the strongest models handle textbook mechanisms well, all models struggle with advanced algorithms, revealing substantial gaps in current DP reasoning capabilities. Through further analytic study and failure-mode analysis, we identify several promising directions for improving automated DP reasoning. Our benchmark provides a solid foundation for developing and evaluating such methods, and complements existing benchmarks for mathematical reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15851
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
Wang, Erchi
Huang, Pengrun
Chien, Eli
Thakkar, Om
Chaudhuri, Kamalika
Wang, Yu-Xiang
Wu, Ruihan
Machine Learning
Artificial Intelligence
Cryptography and Security
Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high barrier for non-expert practitioners. Prior works either rely on specialized verification languages that demand substantial domain expertise or remain semi-automated and require human-in-the-loop guidance. In this work, we investigate whether large language models (LLMs) can automate DP reasoning. We introduce DPrivBench, a benchmark in which each instance asks whether a function or algorithm satisfies a stated DP guarantee under specified assumptions. The benchmark is carefully designed to cover a broad range of DP topics, span diverse difficulty levels, and resist shortcut reasoning through trivial pattern matching. Experiments show that while the strongest models handle textbook mechanisms well, all models struggle with advanced algorithms, revealing substantial gaps in current DP reasoning capabilities. Through further analytic study and failure-mode analysis, we identify several promising directions for improving automated DP reasoning. Our benchmark provides a solid foundation for developing and evaluating such methods, and complements existing benchmarks for mathematical reasoning.
title DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
topic Machine Learning
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2604.15851