Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Models

• URL: http://arxiv.org/abs/2511.07503v2
• Date: Fri, 14 Nov 2025 01:56:38 GMT
• Title: Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Models
• Abstract summary: This work explores the use of language models (LMs) for the generation of synthetic genetic mutation profiles.<n>We empirically evaluate the privacy guarantees of our DP modes by introducing a novel Biologically-Informed Hybrid Membership Inference Attack (biHMIA)<n>Our experiments show that both small and large transformer GPT-like models are viable synthetic variant generators for small-scale genomics.
• Score: 1.7842332554022688
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The increased availability of genetic data has transformed genomics research, but raised many privacy concerns regarding its handling due to its sensitive nature. This work explores the use of language models (LMs) for the generation of synthetic genetic mutation profiles, leveraging differential privacy (DP) for the protection of sensitive genetic data. We empirically evaluate the privacy guarantees of our DP modes by introducing a novel Biologically-Informed Hybrid Membership Inference Attack (biHMIA), which combines traditional black box MIA with contextual genomics metrics for enhanced attack power. Our experiments show that both small and large transformer GPT-like models are viable synthetic variant generators for small-scale genomics, and that our hybrid attack leads, on average, to higher adversarial success compared to traditional metric-based MIAs.

Related papers

• Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling [0.0]
  We extend the empirical Bayes variational autoencoder (EB-VAE) framework to joint longitudinal and time-to-event modeling.<n>The framework represents inter-individual variability using latent individual effects regularized by a co-conditioned empirical Bayes prior.<n>The hybrid decoder recovered treatment-effect parameters broadly consistent with previously reported nonlinear mixed-effects estimates.
  arXiv  Detail & Related papers  (2026-07-15T16:13:14Z)
• ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks [86.89727311669937]
  We introduce ViroBench, the first comprehensive and large-scale benchmark specifically designed for nucleotide foundation models (NFMs)<n>ViroBench evaluates models across two critical dimensions: biological understanding and latent biosecurity risk, covering 18 diverse scenarios within 4 task types.<n>ViroBench provides interpretable, diagnostic evaluations and a reproducible measurement framework for future research on viral nucleotide foundation models.
  arXiv  Detail & Related papers  (2026-05-25T03:31:46Z)
• GGBound: A Genome-Grounded Agent for Microbial Life-Boundary Prediction [16.245500767957697]
  Characterizing the physiological life boundaries of microbial strains is central to biotechnology and ecology.<n>Existing computational approaches either treat physiological traits as isolated supervised targets or biological foundation models as static encoders.<n>We formulate microbial life-boundary prediction as a unified genome-to-physiology task and address it with a tool-augmented LLM agent.
  arXiv  Detail & Related papers  (2026-05-14T06:37:55Z)
• Deep Generative Models for Discrete Genotype Simulation [2.1880699665839396]
  This study explores generating genotype data in both unconditioned and phenotype-conditioned settings.<n>We developed and evaluated commonly used generative models, including Variational Autoencoders (VAEs), Diffusion Models, and Generative Adversarial Networks (GANs)<n>Our results show that these models can effectively capture genetic patterns and preserve genotype-phenotype association.
  arXiv  Detail & Related papers  (2025-08-11T11:56:03Z)
• Unlasting: Unpaired Single-Cell Multi-Perturbation Estimation by Dual Conditional Diffusion Implicit Bridges [68.98973318553983]
  We propose a framework based on Dual Diffusion Implicit Bridges (DDIB) to learn the mapping between different data distributions.<n>We integrate gene regulatory network (GRN) information to propagate perturbation signals in a biologically meaningful way.<n>We also incorporate a masking mechanism to predict silent genes, improving the quality of generated profiles.
  arXiv  Detail & Related papers  (2025-06-26T09:05:38Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen [76.02070962797794]
  This work introduces CellFlow for Generation (CFGen), a flow-based conditional generative model that preserves the inherent discreteness of single-cell data.<n>CFGen generates whole-genome multi-modal single-cell data reliably, improving the recovery of crucial biological data characteristics.
  arXiv  Detail & Related papers  (2024-07-16T14:05:03Z)
• A Game-Theoretic Approach to Privacy-Utility Tradeoff in Sharing Genomic Summary Statistics [24.330984323956173]
  We propose a game-theoretic framework for optimal privacy-utility tradeoffs in the sharing of genomic summary statistics. Our experiments demonstrate that the proposed framework yields both stronger attacks and stronger defense strategies than the state of the art.
  arXiv  Detail & Related papers  (2024-06-03T22:09:47Z)
• Whole Genome Transformer for Gene Interaction Effects in Microbiome Habitat Specificity [3.972930262155919]
  We propose a framework taking advantage of existing large models for gene vectorization to predict habitat specificity from entire microbial genome sequences.<n>We train and validate our approach on a large dataset of high quality microbiome genomes from different habitats.
  arXiv  Detail & Related papers  (2024-05-09T09:34:51Z)
• FGBERT: Function-Driven Pre-trained Gene Language Model for Metagenomics [46.189419603576084]
  FGBERT is a novel metagenomic pre-trained model that employs a protein-based gene representation as a context-aware tokenizer.<n>It demonstrates superior performance on metagenomic datasets at four levels, spanning gene, functional, bacterial, and environmental levels.
  arXiv  Detail & Related papers  (2024-02-24T13:13:17Z)
• Genetic InfoMax: Exploring Mutual Information Maximization in High-Dimensional Imaging Genetics Studies [50.11449968854487]
  Genome-wide association studies (GWAS) are used to identify relationships between genetic variations and specific traits. Representation learning for imaging genetics is largely under-explored due to the unique challenges posed by GWAS. We introduce a trans-modal learning framework Genetic InfoMax (GIM) to address the specific challenges of GWAS.
  arXiv  Detail & Related papers  (2023-09-26T03:59:21Z)
• Cancer-inspired Genomics Mapper Model for the Generation of Synthetic DNA Sequences with Desired Genomics Signatures [0.0]
  Cancer-inspired genomics mapper model (CGMM) combines genetic algorithm (GA) and deep learning (DL) methods. We demonstrate that CGMM can generate synthetic genomes of selected phenotypes such as ancestry and cancer.
  arXiv  Detail & Related papers  (2023-05-01T07:16:40Z)
• Differentiable Agent-based Epidemiology [71.81552021144589]
  We introduce GradABM: a scalable, differentiable design for agent-based modeling that is amenable to gradient-based learning with automatic differentiation. GradABM can quickly simulate million-size populations in few seconds on commodity hardware, integrate with deep neural networks and ingest heterogeneous data sources.
  arXiv  Detail & Related papers  (2022-07-20T07:32:02Z)

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.