Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Privacy-Aware Rejection Sampling
Authors: Jordan Awan, Vinayak Rao
JMLR 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We characterize the additional privacy cost due to the runtime of a rejection sampler in terms of both (ϵ, δ)-DP as well as f-DP. We also show that unless the acceptance probability is constant across databases, the runtime of a rejection sampler does not satisfy ϵ-DP for any ϵ. We propose three modifications to the rejection sampling algorithm, with varying assumptions, to protect against timing attacks by making the runtime independent of the data. We also use our techniques to develop an adaptive rejection sampler for log-H older densities, which also has data-independent runtime. We give several examples of DP mechanisms that fit the assumptions of our methods and can thus be implemented using our samplers. |
| Researcher Affiliation | Academia | Jordan Awan EMAIL Department of Statistics Purdue University West Lafayette, IN 47907, USA; Vinayak Rao EMAIL Department of Statistics Purdue University West Lafayette, IN 47907, USA. Both authors are affiliated with Purdue University, an academic institution. |
| Pseudocode | Yes | Algorithm 1 Privacy-aware rejection sampling via squeeze functions; Algorithm 2 Privacy-aware adaptive rejection |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code, nor does it provide any links to a code repository. The paper is theoretical in nature, focusing on algorithm design and privacy guarantees, rather than an implementation. |
| Open Datasets | No | The paper is theoretical and focuses on privacy-preserving algorithms and mechanisms. It does not describe experiments that would utilize specific datasets, nor does it provide access information for any datasets. The mention of 'data' in the introduction refers to the general context of data privacy, not data used for evaluation in this work. |
| Dataset Splits | No | The paper is theoretical and does not perform experiments with datasets, therefore there is no information about training/test/validation splits. |
| Hardware Specification | No | The paper is theoretical and focuses on algorithm design and privacy guarantees. It does not describe any experimental setup or hardware used for computations. |
| Software Dependencies | No | The paper is theoretical and focuses on algorithm design and privacy guarantees. It does not describe any specific software dependencies or versions used for implementation or experimentation. |
| Experiment Setup | No | The paper is theoretical, presenting new algorithms and their privacy guarantees. It does not include an experimental section with details such as hyperparameters or training configurations. |