ImpMIA: Leveraging Implicit Bias for Membership Inference Attack under Realistic Scenarios

• URL: http://arxiv.org/abs/2510.10625v2
• Date: Fri, 17 Oct 2025 19:02:31 GMT
• Title: ImpMIA: Leveraging Implicit Bias for Membership Inference Attack under Realistic Scenarios
• Authors: Yuval Golbari, Navve Wasserman, Gal Vardi, Michal Irani,
• Abstract summary: We introduce ImpMIA, a Membership Inference Attack that exploits the Implicit Bias of neural networks.<n>ImpMIA uses the Karush-Kuhn-Tucker optimality conditions to identify training samples.
• Score: 25.37906016731147
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Determining which data samples were used to train a model-known as Membership Inference Attack (MIA)-is a well-studied and important problem with implications for data privacy. Black-box methods presume access only to the model's outputs and often rely on training auxiliary reference models. While they have shown strong empirical performance, they rely on assumptions that rarely hold in real-world settings: (i) the attacker knows the training hyperparameters; (ii) all available non-training samples come from the same distribution as the training data; and (iii) the fraction of training data in the evaluation set is known. In this paper, we demonstrate that removing these assumptions leads to a significant drop in the performance of black-box attacks. We introduce ImpMIA, a Membership Inference Attack that exploits the Implicit Bias of neural networks, hence removes the need to rely on any reference models and their assumptions. ImpMIA is a white-box attack -- a setting which assumes access to model weights and is becoming increasingly realistic given that many models are publicly available (e.g., via Hugging Face). Building on maximum-margin implicit bias theory, ImpMIA uses the Karush-Kuhn-Tucker (KKT) optimality conditions to identify training samples. This is done by finding the samples whose gradients most strongly reconstruct the trained model's parameters. As a result, ImpMIA achieves state-of-the-art performance compared to both black and white box attacks in realistic settings where only the model weights and a superset of the training data are available.

Related papers

• Membership Inference Attacks Beyond Overfitting [3.549717032380187]
  Membership inference attacks (MIAs) aim to determine whether a given data point was part of the model training data.<n>MIAs exploit differences in the behavior of a model when making predictions on samples it has seen during training.<n>Even non-overfitted ML models can leak information about a small subset of their training data.
  arXiv  Detail & Related papers  (2025-11-20T20:40:56Z)
• Membership Inference Attacks on Diffusion Models via Quantile Regression [30.30033625685376]
  We demonstrate a privacy vulnerability of diffusion models through amembership inference (MI) attack. Our proposed MI attack learns quantile regression models that predict (a quantile of) the distribution of reconstruction loss on examples not used in training. We show that our attack outperforms the prior state-of-the-art attack while being substantially less computationally expensive.
  arXiv  Detail & Related papers  (2023-12-08T16:21:24Z)
• Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration [32.15773300068426]
  Membership Inference Attacks aim to infer whether a target data record has been utilized for model training. We propose a Membership Inference Attack based on Self-calibrated Probabilistic Variation (SPV-MIA)
  arXiv  Detail & Related papers  (2023-11-10T13:55:05Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Model [14.834360664780709]
  Model attacks (MIAs) aim to recover private data from inaccessible training sets of deep learning models. This paper develops a novel MIA method, leveraging a conditional diffusion model (CDM) to recover representative samples under the target label. Experimental results show that this method can generate similar and accurate samples to the target label, outperforming generators of previous approaches.
  arXiv  Detail & Related papers  (2023-07-17T12:14:24Z)
• Membership Inference Attacks against Language Models via Neighbourhood Comparison [45.086816556309266]
  Membership Inference attacks (MIAs) aim to predict whether a data sample was present in the training data of a machine learning model or not. Recent work has demonstrated that reference-based attacks which compare model scores to those obtained from a reference model trained on similar data can substantially improve the performance of MIAs. We investigate their performance in more realistic scenarios and find that they are highly fragile in relation to the data distribution used to train reference models.
  arXiv  Detail & Related papers  (2023-05-29T07:06:03Z)
• Membership Inference Attacks against Synthetic Data through Overfitting Detection [84.02632160692995]
  We argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model.
  arXiv  Detail & Related papers  (2023-02-24T11:27:39Z)
• FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes [51.02407217197623]
  We propose a two-stage training algorithm named FAIRIF. It minimizes the loss over the reweighted data set where the sample weights are computed. We show that FAIRIF yields models with better fairness-utility trade-offs against various types of bias.
  arXiv  Detail & Related papers  (2022-01-15T05:14:48Z)
• Self-Damaging Contrastive Learning [92.34124578823977]
  Unlabeled data in reality is commonly imbalanced and shows a long-tail distribution. This paper proposes a principled framework called Self-Damaging Contrastive Learning to automatically balance the representation learning without knowing the classes. Our experiments show that SDCLR significantly improves not only overall accuracies but also balancedness.
  arXiv  Detail & Related papers  (2021-06-06T00:04:49Z)
• MixKD: Towards Efficient Distillation of Large-scale Language Models [129.73786264834894]
  We propose MixKD, a data-agnostic distillation framework, to endow the resulting model with stronger generalization ability. We prove from a theoretical perspective that under reasonable conditions MixKD gives rise to a smaller gap between the error and the empirical error. Experiments under a limited-data setting and ablation studies further demonstrate the advantages of the proposed approach.
  arXiv  Detail & Related papers  (2020-11-01T18:47:51Z)
• Knowledge-Enriched Distributional Model Inversion Attacks [49.43828150561947]
  Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. We present a novel inversion-specific GAN that can better distill knowledge useful for performing attacks on private models from public data. Our experiments show that the combination of these techniques can significantly boost the success rate of the state-of-the-art MI attacks by 150%.
  arXiv  Detail & Related papers  (2020-10-08T16:20:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.