Comparing Reconstruction Attacks on Pretrained Versus Full Fine-tuned Large Language Model Embeddings on Homo Sapiens Splice Sites Genomic Data

• URL: http://arxiv.org/abs/2511.07481v1
• Date: Wed, 12 Nov 2025 01:01:21 GMT
• Title: Comparing Reconstruction Attacks on Pretrained Versus Full Fine-tuned Large Language Model Embeddings on Homo Sapiens Splice Sites Genomic Data
• Abstract summary: This study investigates embedding reconstruction attacks in large language models applied to genomic sequences.<n>We conduct a comprehensive analysis using the HS3D genomic dataset to determine whether task-specific optimization strengthens or weakens privacy protections.
• Score: 4.729128449905504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This study investigates embedding reconstruction attacks in large language models (LLMs) applied to genomic sequences, with a specific focus on how fine-tuning affects vulnerability to these attacks. Building upon Pan et al.'s seminal work demonstrating that embeddings from pretrained language models can leak sensitive information, we conduct a comprehensive analysis using the HS3D genomic dataset to determine whether task-specific optimization strengthens or weakens privacy protections. Our research extends Pan et al.'s work in three significant dimensions. First, we apply their reconstruction attack pipeline to pretrained and fine-tuned model embeddings, addressing a critical gap in their methodology that did not specify embedding types. Second, we implement specialized tokenization mechanisms tailored specifically for DNA sequences, enhancing the model's ability to process genomic data, as these models are pretrained on natural language and not DNA. Third, we perform a detailed comparative analysis examining position-specific, nucleotide-type, and privacy changes between pretrained and fine-tuned embeddings. We assess embeddings vulnerabilities across different types and dimensions, providing deeper insights into how task adaptation shifts privacy risks throughout genomic sequences. Our findings show a clear distinction in reconstruction vulnerability between pretrained and fine-tuned embeddings. Notably, fine-tuning strengthens resistance to reconstruction attacks in multiple architectures -- XLNet (+19.8\%), GPT-2 (+9.8\%), and BERT (+7.8\%) -- pointing to task-specific optimization as a potential privacy enhancement mechanism. These results highlight the need for advanced protective mechanisms for language models processing sensitive genomic data, while highlighting fine-tuning as a potential privacy-enhancing technique worth further exploration.

Related papers

• SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC) [4.995853115126354]
  We present the first systematization of reconstruction attacks on de-identified and synthetic data.<n>We show that the choice of method governs risk far more than the choice of attack.<n>Our findings are validated by our first-place finish among all red teams in the 2025 textitNational Institute of Standards and Technology (NIST) Collaborative Research Cycle.
  arXiv  Detail & Related papers  (2026-06-06T23:39:45Z)
• Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense [80.28330585803133]
  Graph neural networks (GNNs) are widely deployed on computation data, yet they can leak sensitive or proprietary information about the training graph adjacency.<n>This work studies graph reconstruction attacks (GRA), a form of model inversion that reconstructs the training adjacency from a trained GNN.<n>We propose MC-GRA (+), which reconstructs the adjacency by optimizing a surrogate adjacency whose GNN-induced representations align with those of the target model.<n>On the defense side, we propose MC-GPB (+), which suppresses adjacency-dependent information throughout the representation chain
  arXiv  Detail & Related papers  (2026-06-06T09:29:27Z)
• On the Privacy of LLMs: An Ablation Study [0.0]
  Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings.<n>We introduce a unified threat model and notation, reproduce a representative set of privacy attacks, and conduct a structured ablation study.
  arXiv  Detail & Related papers  (2026-05-04T06:06:41Z)
• Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition [60.52810518437911]
  High-fidelity generative models are increasingly needed in privacy-sensitive scenarios.<n> limited data leads to poor generative models, which in turn fail to mitigate data scarcity.<n>We propose a reinforcement-guided synthetic data generation framework that adapts general-domain generative priors to identity recognition tasks.
  arXiv  Detail & Related papers  (2026-04-09T06:52:03Z)
• How Private Are DNA Embeddings? Inverting Foundation Model Representations of Genomic Sequences [0.45880283710344055]
  DNA foundation models have become transformative tools in bioinformatics and healthcare applications.<n>Embeddings-as-a-Service (EBERT) frameworks are increasingly being shared via Embeddings-as-a-Service.<n>This study evaluates the resilience of DNA foundation models to model inversion attacks.
  arXiv  Detail & Related papers  (2026-03-06T23:52:26Z)
• Proactive Defense: Compound AI for Detecting Persuasion Attacks and Measuring Inoculation Effectiveness [1.1686584679011365]
  This paper introduces BRIES, a novel compound AI architecture designed to detect and measure the effectiveness of persuasion attacks.<n>We present a system with specialized agents: a Twister that generates adversarial content employing targeted persuasion tactics, a Detector that identifies attack types with parameters, a Defender that creates resilient content through content inoculation, and an assessor that employs causal inference to evaluate inoculation effectiveness.
  arXiv  Detail & Related papers  (2025-11-23T07:49:05Z)
• DISPROTBENCH: A Disorder-Aware, Task-Rich Benchmark for Evaluating Protein Structure Prediction in Realistic Biological Contexts [76.59606029593085]
  DisProtBench is a benchmark for evaluating protein structure prediction models (PSPMs) under structural disorder and complex biological conditions.<n>DisProtBench spans three key axes: data complexity, task diversity, and Interpretability.<n>Results reveal significant variability in model robustness under disorder, with low-confidence regions linked to functional prediction failures.
  arXiv  Detail & Related papers  (2025-06-18T23:58:22Z)
• Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards [13.197807179926428]
  Large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern.<n>In this work, we investigate Accidental Vulnerability, unexpected vulnerabilities arising from characteristics of fine-tuning data.
  arXiv  Detail & Related papers  (2025-05-22T15:30:00Z)
• 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)
• On Machine Learning Approaches for Protein-Ligand Binding Affinity Prediction [2.874893537471256]
  This study evaluates the performance of classical tree-based models and advanced neural networks in protein-ligand binding affinity prediction. We show that combining 2D and 3D model strengths improves active learning outcomes beyond current state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-07-15T13:06:00Z)
• GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models [56.63218531256961]
  We introduce GenBench, a benchmarking suite specifically tailored for evaluating the efficacy of Genomic Foundation Models. GenBench offers a modular and expandable framework that encapsulates a variety of state-of-the-art methodologies. We provide a nuanced analysis of the interplay between model architecture and dataset characteristics on task-specific performance.
  arXiv  Detail & Related papers  (2024-06-01T08:01:05Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• Geometric Deep Learning for Structure-Based Drug Design: A Survey [83.87489798671155]
  Structure-based drug design (SBDD) leverages the three-dimensional geometry of proteins to identify potential drug candidates. Recent advancements in geometric deep learning, which effectively integrate and process 3D geometric data, have significantly propelled the field forward.
  arXiv  Detail & Related papers  (2023-06-20T14:21:58Z)
• How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features [19.261178173399784]
  We consider spurious features that are uncorrelated with the learning task. We provide a precise characterization of how they are memorized via two separate terms. We prove that the memorization of spurious features weakens as the generalization capability increases.
  arXiv  Detail & Related papers  (2023-05-20T05:27:41Z)
• Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling [0.0]
  We present Ankh, the first general-purpose protein language model trained on Google's TPU-v4. Ankh succeeds in learning protein evolutionary conservation-mutation trends and introducing functional diversity while retaining key structural-functional characteristics.
  arXiv  Detail & Related papers  (2023-01-16T19:04:45Z)
• Graph Backdoor [53.70971502299977]
  We present GTA, the first backdoor attack on graph neural networks (GNNs) GTA departs in significant ways: it defines triggers as specific subgraphs, including both topological structures and descriptive features. It can be instantiated for both transductive (e.g., node classification) and inductive (e.g., graph classification) tasks.
  arXiv  Detail & Related papers  (2020-06-21T19:45:30Z)

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.