DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.
Theorem A.1(Laplace Mechanism (Dwork et al., 2006)).Let f:X n →R d be a function with ℓ1-sensitivity ∆1(f) := max X∼X ′ ∥f(X)−f(X ′)∥1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.