Membership Inference Attack

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.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 78 papers with code (186 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.

• Membership Inference Attacks against Machine Learning Models
  18 Oct 2016 11 repositories listed Syntology ran 2 of 14 samples · 12 unverified
  We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained.
• ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
  4 Jun 2018 7 repositories listed Syntology ran 5 of 18 samples · 13 unverified · 2 pointer-only (licence)
  In addition, we propose the first effective defense mechanisms against such broader class of membership inference attacks that maintain a high level of utility of the ML model.
• Membership Inference Attacks From First Principles
  7 Dec 2021 5 repositories listed Syntology ran 5 of 8 samples · 3 unverified · 3 pointer-only (licence)
  A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset.
• MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples
  23 Sep 2019 4 repositories listed
  Specifically, given a black-box access to the target classifier, the attacker trains a binary classifier, which takes a data sample's confidence score vector predicted by the target classifier as an input and predicts…
• Synthesis of Realistic ECG using Generative Adversarial Networks
  19 Sep 2019 3 repositories listed
  Finally, we discuss the privacy concerns associated with sharing synthetic data produced by GANs and test their ability to withstand a simple membership inference attack.
• Do Parameters Reveal More than Loss for Membership Inference?
  17 Jun 2024 2 repositories listed
  Membership inference attacks are used as a key tool for disclosure auditing.
• Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment
  2 Jan 2024 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  To mitigate this issue, AI software compression plays a crucial role, which aims to compress model size while keeping high performance.
• Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning
  29 Nov 2023 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
  Federated Learning (FL) has been proposed as a privacy-preserving solution for distributed machine learning, particularly in heterogeneous FL settings where clients have varying computational capabilities and thus train…
• Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
  10 Nov 2023 2 repositories listed Syntology ran 5 of 6 samples · 1 unverified · 6 pointer-only (licence)
  However, this hypothesis heavily relies on the overfitting of target models, which will be mitigated by multiple regularization methods and the generalization of LLMs.
• Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment
  11 Aug 2022 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 1 pointer-only (licence)
  By simulating the attack mechanism as the safety test, SafeCompress can automatically compress a big model to a small one following the dynamic sparse training paradigm.
• Membership Inference Attacks on Machine Learning: A Survey
  14 Mar 2021 2 repositories listed
  In recent years, MIAs have been shown to be effective on various ML models, e.
• Disparate Vulnerability to Membership Inference Attacks
  2 Jun 2019 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  Differential privacy bounds disparate vulnerability but can significantly reduce the accuracy of the model.
• Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning
  11 Jun 2025 1 repository listed
  Machine Unlearning (MU) aims to update Machine Learning (ML) models following requests to remove training samples and their influences on a trained model efficiently without retraining the original ML model from scratch.
• Automatic Calibration for Membership Inference Attack on Large Language Models
  6 May 2025 1 repository listed
  Membership Inference Attacks (MIAs) have recently been employed to determine whether a specific text was part of the pre-training data of Large Language Models (LLMs).
• DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
  6 Feb 2025 1 repository listed Syntology ran 3 of 5 samples · 2 unverified · 5 pointer-only (licence)
  Document Visual Question Answering (DocVQA) has introduced a new paradigm for end-to-end document understanding, and quickly became one of the standard benchmarks for multimodal LLMs.
• Privacy Attacks on Image AutoRegressive Models
  4 Feb 2025 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Using this MIA, we perform dataset inference (DI) and find that IARs require as few as six samples to detect dataset membership, compared to 200 for DMs, indicating higher information leakage.
• Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
  1 Feb 2025 1 repository listed
  Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to generate grounded responses by leveraging external knowledge databases without altering model parameters.
• Differentially Private Steering for Large Language Model Alignment
  30 Jan 2025 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  We also develop the first Membership Inference Attack (MIA) for evaluating and auditing the empirical privacy for the problem of LLM steering via activation editing.
• Membership Inference Attacks Against Vision-Language Models
  27 Jan 2025 1 repository listed
  Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, positioning them as catalysts for the next…
• Technical Report for the Forgotten-by-Design Project: Targeted Obfuscation for Machine Learning
  20 Jan 2025 1 repository listed
  This work contributes to the development of privacy-preserving AI systems that align with human cognitive processes of motivated forgetting, offering a robust framework for safeguarding sensitive information and…
• Membership Inference Attacks against Large Vision-Language Models
  5 Nov 2024 1 repository listed Syntology ran 1 of 10 samples · 9 unverified
  Large vision-language models (VLLMs) exhibit promising capabilities for processing multi-modal tasks across various application scenarios.
• Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognition
  4 Nov 2024 1 repository listed
  This study addresses these issues by investigating privacy vulnerabilities in radar-based Human Activity Recognition (HAR) systems and proposing a novel method for privacy preservation using Differential Privacy (DP)…
• MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector
  16 Aug 2024 1 repository listed Syntology ran 10 of 16 samples · 6 unverified · 16 pointer-only (licence)
  Existing studies have partially addressed this need through an exploration of the pre-training data detection problem, which is an instance of a membership inference attack (MIA).
• SeqMIA: Sequential-Metric Based Membership Inference Attack
  21 Jul 2024 1 repository listed Syntology ran 9 of 10 samples · 1 unverified · 10 pointer-only (licence)
  Building upon this signal, we introduce a novel attack method called Sequential-metric based Membership Inference Attack (SeqMIA).
• A Method to Facilitate Membership Inference Attacks in Deep Learning Models
  2 Jul 2024 1 repository listed Syntology ran 5 of 8 samples · 3 unverified
  Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models.
• RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
  16 Jun 2024 1 repository listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  Large language models (LLMs) inevitably memorize sensitive, copyrighted, and harmful knowledge from the training corpus; therefore, it is crucial to erase this knowledge from the models.
• The Mosaic Memory of Large Language Models
  24 May 2024 1 repository listed Syntology ran 16 of 16 samples · 0 unverified
  As Large Language Models (LLMs) become widely adopted, understanding how they learn from, and memorize, training data becomes crucial.
• Data Contamination Calibration for Black-box LLMs
  20 May 2024 1 repository listed Syntology ran 6 of 8 samples · 2 unverified
  The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size.
• GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation
  13 May 2024 1 repository listed
  We observe that the knowledge distillation significantly improves the efficiency of likelihood ratio of membership inference attack, especially in the black-box setting, i.
• Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
  14 Mar 2024 1 repository listed Syntology ran 2 of 3 samples · 1 unverified · 2 pointer-only (licence)
  While diffusion models have recently demonstrated remarkable progress in generating realistic images, privacy risks also arise: published models or APIs could generate training images and thus leak privacy-sensitive…

Syntology lines on 19 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.