Reconstruction Attack

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

24 shown of 24 papers with code (68 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Reconstructing Training Data with Informed Adversaries
  13 Jan 2022 2 repositories listed
  Our work provides an effective reconstruction attack that model developers can use to assess memorization of individual points in general settings beyond those considered in previous works (e.
• TimberStrike: Dataset Reconstruction Attack Revealing Privacy Leakage in Federated Tree-Based Systems
  9 Jun 2025 1 repository listed
  On a publicly available stroke prediction dataset, TimberStrike consistently reconstructs between 73.
• Training Set Reconstruction from Differentially Private Forests: How Effective is DP?
  7 Feb 2025 1 repository listed
  Recent research has shown that machine learning models are vulnerable to privacy attacks targeting their training data.
• Investigating Privacy Leakage in Dimensionality Reduction Methods via Reconstruction Attack
  30 Aug 2024 1 repository listed
  The experimental results also show that, for PCA and Isomap, our reconstruction network produces higher quality outputs compared to a previously proposed network.
• Face Reconstruction Transfer Attack as Out-of-Distribution Generalization
  2 Jul 2024 1 repository listed
  Understanding the vulnerability of face recognition systems to malicious attacks is of critical importance.
• URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
  30 Apr 2024 1 repository listed
  Launching effective malicious attacks in VFL presents unique challenges: 1) Firstly, given the distributed nature of clients' data features and models, each client rigorously guards its privacy and prohibits direct…
• Trained Random Forests Completely Reveal your Dataset
  29 Feb 2024 1 repository listed
  Even with bootstrap aggregation, the majority of the data can also be reconstructed.
• Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
  28 Feb 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  We evaluate DRA across various open-source and closed-source models, showcasing state-of-the-art jailbreak success rates and attack efficiency.
• Privacy Attacks in Decentralized Learning
  15 Feb 2024 1 repository listed Syntology ran 11 of 15 samples · 4 unverified · 15 pointer-only (licence)
  Decentralized Gradient Descent (D-GD) allows a set of users to perform collaborative learning without sharing their data by iteratively averaging local model updates with their neighbors in a network graph.
• Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models
  5 Feb 2024 1 repository listed
  This attack targets the contents of previous conversations between GPT models and benign users, i.
• An Examination of the Alleged Privacy Threats of Confidence-Ranked Reconstruction of Census Microdata
  6 Nov 2023 1 repository listed
  Recently, a new attack has been proposed, which incorporates the confidence that a reconstructed record was in the original data.
• RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulation
  29 Oct 2023 1 repository listed
  We introduce RAIFLE, a novel optimization-based attack framework where the server actively manipulates the features of the items presented to users to increase the success rate of reconstruction.
• On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation
  15 Jun 2023 1 repository listed Syntology ran 14 of 23 samples · 9 unverified · 1 pointer-only (licence)
  Although powerful graph neural networks (GNNs) have boosted numerous real-world applications, the potential privacy risk is still underexplored.
• LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulation
  21 Mar 2023 1 repository listed
  When both FedAVG and secure aggregation are used, there is no current method that is able to attack multiple clients concurrently in a federated learning setting.
• Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation
  2 Feb 2023 1 repository listed
  We show that both theoretically and empirically, reconstructed images tend to "outliers" in the dataset, and that these reconstruction attacks can be used for \textit{dataset distillation}, that is, we can retrain on…
• Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing
  8 Dec 2022 1 repository listed
  Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models outputs for a target task with the…
• Confidence-Ranked Reconstruction of Census Microdata from Published Statistics
  6 Nov 2022 1 repository listed
  Our attacks significantly outperform those that are based only on access to a public distribution or population from which the private dataset D was sampled, demonstrating that they are exploiting information in the…
• Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning
  13 Oct 2022 1 repository listed
  To address this problem, we develop a novel feature protection scheme against the reconstruction attack that effectively misleads the search to some pre-specified random values.
• TabLeak: Tabular Data Leakage in Federated Learning
  4 Oct 2022 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  A successful attack for tabular data must address two key challenges unique to the domain: (i) obtaining a solution to a high-variance mixed discrete-continuous optimization problem, and (ii) enabling human assessment…
• How Private Is Your RL Policy? An Inverse RL Based Analysis Framework
  10 Dec 2021 1 repository listed
  Reinforcement Learning (RL) enables agents to learn how to perform various tasks from scratch.
• When the Curious Abandon Honesty: Federated Learning Is Not Private
  6 Dec 2021 1 repository listed
  Instead, these devices share gradients, parameters, or other model updates, with a central party (e.
• Towards General Deep Leakage in Federated Learning
  18 Oct 2021 1 repository listed
  We find that image restoration fails even if there is only one incorrectly inferred label in the batch; we also find that when batch images have the same label, the corresponding image is restored as a fusion of that…
• Inference Attacks Against Graph Neural Networks
  6 Oct 2021 1 repository listed
  Second, given a subgraph of interest and the graph embedding, we can determine with high confidence that whether the subgraph is contained in the target graph.
• A Review of Anonymization for Healthcare Data
  13 Apr 2021 1 repository listed
  Mining health data can lead to faster medical decisions, improvement in the quality of treatment, disease prevention, reduced cost, and it drives innovative solutions within the healthcare sector.

Syntology lines on 4 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.