Linear Program Reconstruction in Practice
Not on the map. Why?
Abstract (arXiv)
We briefly report on a successful linear program reconstruction attack performed on a production statistical queries system and using a real dataset. The attack was deployed in test environment in the course of the Aircloak Challenge bug bounty program and is based on the reconstruction algorithm of Dwork, McSherry, and Talwar. We empirically evaluate the effectiveness of the algorithm and a related algorithm by Dinur and Nissim with various dataset sizes, error rates, and numbers of queries in a Gaussian noise setting.
Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Oct 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 5; 2023: 5; 2024: 0; 2025: 3.
14 papers.
Sort:
By area:
- 2022Reconstructing Training Data with Informed Adversariescited by 148
- 2023A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Datacited by 24
- 2022Confidence-Ranked Reconstruction of Census Microdata from Published Statisticscited by 16
- 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasetscited by 14
- 2021A Review of Anonymization for Healthcare Datacited by 12
- 2022Exploiting Fairness to Enhance Sensitive Attributes Reconstructioncited by 10
- 2022Control, Confidentiality, and the Right to be Forgottencited by 10
- 2023Probabilistic Dataset Reconstruction from Interpretable Modelscited by 7
- 2022QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systemscited by 6
- 2023Towards Differential Privacy in Sequential Recommendation: A Noisy Graph Neural Network Approachcited by 3
- 2023Federated Learning is Better with Non-Homomorphic Encryptioncited by 2
- 2025A Unified Framework for Adversary-Aware Differential Privacy Boundscited by 2
- 2025A Unified Framework for Adversary-Aware Differential Privacy Bounds10 Jul 2025
- 2025Blind Targeting: Personalization under Third-Party Privacy Constraints7 Jul 2025
- 2025DeSIA: Attribute Inference Attacks Against Limited Fixed Aggregate Statistics25 Apr 2025
- 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets8 Dec 2023
- 2023Federated Learning is Better with Non-Homomorphic Encryption4 Dec 2023
- 2023Towards Differential Privacy in Sequential Recommendation: A Noisy Graph Neural Network Approach17 Sep 2023
- 2023Probabilistic Dataset Reconstruction from Interpretable Models29 Aug 2023
- 2023A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data24 Jan 2023
- 2022QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems9 Nov 2022
- 2022Confidence-Ranked Reconstruction of Census Microdata from Published Statistics6 Nov 2022
- 2022Control, Confidentiality, and the Right to be Forgotten14 Oct 2022
- 2022Exploiting Fairness to Enhance Sensitive Attributes Reconstruction2 Sep 2022
2 more
- 2022Reconstructing Training Data with Informed Adversaries13 Jan 2022
- 2021A Review of Anonymization for Healthcare Data13 Apr 2021
- 2022Reconstructing Training Data with Informed Adversariescited by 148
- 2023A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Datacited by 24
- 2022Confidence-Ranked Reconstruction of Census Microdata from Published Statisticscited by 16
- 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasetscited by 14
- 2021A Review of Anonymization for Healthcare Datacited by 12
- 2022Exploiting Fairness to Enhance Sensitive Attributes Reconstructioncited by 10
- 2023Probabilistic Dataset Reconstruction from Interpretable Modelscited by 7
- 2022QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systemscited by 6
- 2023Towards Differential Privacy in Sequential Recommendation: A Noisy Graph Neural Network Approachcited by 3
- 2023Federated Learning is Better with Non-Homomorphic Encryptioncited by 2
- 2025DeSIA: Attribute Inference Attacks Against Limited Fixed Aggregate Statisticscited by 0
- 2025Blind Targeting: Personalization under Third-Party Privacy Constraintscited by 0
- 2025Blind Targeting: Personalization under Third-Party Privacy Constraints7 Jul 2025
- 2025DeSIA: Attribute Inference Attacks Against Limited Fixed Aggregate Statistics25 Apr 2025
- 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets8 Dec 2023
- 2023Federated Learning is Better with Non-Homomorphic Encryption4 Dec 2023
- 2023Towards Differential Privacy in Sequential Recommendation: A Noisy Graph Neural Network Approach17 Sep 2023
- 2023Probabilistic Dataset Reconstruction from Interpretable Models29 Aug 2023
- 2023A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data24 Jan 2023
- 2022QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems9 Nov 2022
- 2022Confidence-Ranked Reconstruction of Census Microdata from Published Statistics6 Nov 2022
- 2022Exploiting Fairness to Enhance Sensitive Attributes Reconstruction2 Sep 2022
- 2022Reconstructing Training Data with Informed Adversaries13 Jan 2022
- 2021A Review of Anonymization for Healthcare Data13 Apr 2021