Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 33 for “"Membership Inference Attacks"”.

  1. Honesty Is Not Always the Best Policy: Defending Against Membership Inference Attacks on Genomic Data

    … public. Several of these concerns revolve around membership-inference attacks, whereby an adversarial actor attempts to infer a target individual's presence in a given dataset. Membership-inference attacks pose a significant privacy risk, as genomic datasets often contain potentially sensitive …

    wustl Repository record for Honesty Is Not Always the Best Policy: Defending Against Membership Inference Attacks on Genomic Data (opens in a new tab)

  2. Semantically Aware Attacks on Text-based Models: An Extension of Context-aware and Neighbourhood Comparisonbased Membership Inference Attacks

    … can be extracted from the trained models. In a membership inference attack (MIA), an adversary is expected to have access to a trained model θ and a data sample d, sampled from the same distribution as the unknown training data. The objective of the adversary is to construct an algorithm A(θ, d) …

    chalmers Repository record for Semantically Aware Attacks on Text-based Models: An Extension of Context-aware and Neighbourhood Comparisonbased Membership Inference Attacks (opens in a new tab)

  3. Privacy and Robustness of Deep Neural Networks

    … discuss ap- proaches to defending models against membership inference attacks and adversarial attacks. Membership inference attacks attempt to infer the training set information from observing the model output, while adversarial attacks aim to alter the output of models via introducing minimal …

    duke Repository record for Privacy and Robustness of Deep Neural Networks (opens in a new tab)

  4. Privacy Protection via Adversarial Examples

    … by attackers to perform automated, large-scale inference attacks. For instance, in attribute inference attacks, an attacker can use a machine learning classifier to predict a target user's private, sensitive attributes (e.g., gender, political view) via the public data shared by the user (e.g., …

    duke Repository record for Privacy Protection via Adversarial Examples (opens in a new tab)

  5. PANORAMIA : privacy auditing of machine learning models without retraining

    … for machine learning models that relies on membership inference attacks using generated data as non-members. By relying on generated non-member data, PANORAMIA eliminates the common dependency of privacy measurement tools on in-distribution non-member data. As a result, PANORAMIA does not …

    ubc Repository record for PANORAMIA : privacy auditing of machine learning models without retraining (opens in a new tab) Download PDF for PANORAMIA : privacy auditing of machine learning models without retraining (opens in a new tab)

  6. TOWARD A BETTER UNDERSTANDING OF PRIVACY LEAKAGE IN MACHINE LEARNING, USING DATASET PRUNING ATTACK

    While membership inference attacks in machine learning setups have been studied for several years, the exact mechanisms leading to privacy leakage are only partially understood. We developed a dataset pruning attack, which is similar to a dataset poisoning attack, but that differs in that it …

    nus Repository record for TOWARD A BETTER UNDERSTANDING OF PRIVACY LEAKAGE IN MACHINE LEARNING, USING DATASET PRUNING ATTACK (opens in a new tab) Download file for TOWARD A BETTER UNDERSTANDING OF PRIVACY LEAKAGE IN MACHINE LEARNING, USING DATASET PRUNING ATTACK (opens in a new tab)

  7. PRIVACY-PRESERVING DATA GENERATION AND REMOVAL IN GENERATIVE MODELS

    … Differential privacy and privacy auditing via membership inference attacks are further incorporated, and the framework is extended to time-series data through VFLGAN-TS, which captures both temporal and attribute dependencies. For data deletion in diffusion models, the dissertation identifies …

    nus Repository record for PRIVACY-PRESERVING DATA GENERATION AND REMOVAL IN GENERATIVE MODELS (opens in a new tab) Download file for PRIVACY-PRESERVING DATA GENERATION AND REMOVAL IN GENERATIVE MODELS (opens in a new tab)

  8. Additive logistic mechanism for privacy-preserving self-supervised learning

    … learning algorithms are vulnerable to privacy attacks, especially in the stage in which a pre-trained model is fine-tuned for the actual task. We focus on self-supervised learning applied to neural networks and design a post-training privacy-protection algorithm for the neural networks. We …

    texas Repository record for Additive logistic mechanism for privacy-preserving self-supervised learning (opens in a new tab)

  9. Privacy Risks in Text Masking Models for Anonymization

    … models by evaluating their vulnerability to Membership Inference Attacks (MIAs) and extraction attacks. MIAs are attempting to identify whether or not a data point was part of the training dataset, knowledge of the membership can in certain scenarios be a breach of privacy. Two …

    chalmers Repository record for Privacy Risks in Text Masking Models for Anonymization (opens in a new tab)

  10. Privacy-preserving synthetic image data generation and classification

    … privacy is crucial due to its vulnerability to “membership inference attacks.” State-of-the-art (e.g., differential privacy, etc.) defenses compromised task accuracy to preserve privacy, and some methods reuse private data or require more public data, which is impractical in some domains. To …

    manitoba Repository record for Privacy-preserving synthetic image data generation and classification (opens in a new tab)

  11. Using Approximate Bayesian Neural Networks for Membership Inference

    … settings, evaluating their vulnerability to Membership Inference Attacks (MIA) has become an important security concern. These attacks aim to determine whether a given data point was part of a target model’s training set, thereby potentially revealing sensitive information about individuals …

    chalmers Repository record for Using Approximate Bayesian Neural Networks for Membership Inference (opens in a new tab)

  12. ON THE EMPIRICAL POINT-WISE PRIVACY DYNAMICS OF DEEP LEARNING MODELS

    … individual privacy accounting, or by performing Membership Inference Attacks that provide empirical lower bounds of privacy risk. However, while privacy accounting is limited to the realm of models trained on DP-SGD, MIAs commonly provides either model-specific metrics such as the area under the …

    nus Repository record for ON THE EMPIRICAL POINT-WISE PRIVACY DYNAMICS OF DEEP LEARNING MODELS (opens in a new tab) Download file for ON THE EMPIRICAL POINT-WISE PRIVACY DYNAMICS OF DEEP LEARNING MODELS (opens in a new tab)

  13. Perceptions and Practicalities for Private Machine Learning

    … for a thorough understanding of the risk form attacks in such applications. When training a machine learning model on private data, it is critical to understand the conditions under which that data can be protected; and when it cannot. For instance, membership inference attacks aim to violate …

    waterloo Repository record for Perceptions and Practicalities for Private Machine Learning (opens in a new tab)

  14. Data Centric Defenses for Privacy Attacks

    … learning algorithms are highly susceptible to attacks trying to extract sensitive information about the data used in model training. These attacks called privacy attacks, exploit the model training process. Contemporary defense techniques make alterations to the training algorithm. Such …

    vt Repository record for Data Centric Defenses for Privacy Attacks (opens in a new tab)

  15. Is This Data Point In your Training Set? Similarity-based Inference Attacks: Performance Evaluation of Range Membership Attacks to Audit Privacy Risks in Machine Learning Models

    Membership Inference Attacks (MIAs) pose a serious threat to the privacy of machine learning (ML) models by determining whether a specific data point was used during model training. A recent and powerful variant, the Range Membership Inference Attack (RaMIA), assesses privacy risks over a range of …

    chalmers Repository record for Is This Data Point In your Training Set? Similarity-based Inference Attacks: Performance Evaluation of Range Membership Attacks to Audit Privacy Risks in Machine Learning Models (opens in a new tab)

  16. Understanding and Connecting Fairness, Copyright, and Watermarking Through a Security Lens

    … models fundamentally vulnerable to adaptive attacks. For instance, we show that commonly used techniques—such as training data deduplication for preventing copyrighted content generation, and standard membership inference attacks (MIAs) for detecting copyright infringement—are insufficient, …

    maryland Repository record for Understanding and Connecting Fairness, Copyright, and Watermarking Through a Security Lens (opens in a new tab)

  17. Protecting Patient Privacy in Healthcare Analytics with Fully Homomorphic Encryption and Differential Privacy

    … Privacy (DP) protects individuals against inference attacks by introducing controlled noise into aggregate query results. This thesis investigates the combined use of FHE and DP for privacy-preserving healthcare analytics and evaluates the resulting privacy guarantees, performance, and …

    chalmers Repository record for Protecting Patient Privacy in Healthcare Analytics with Fully Homomorphic Encryption and Differential Privacy (opens in a new tab)

  18. Privacy Risks in Time Series Models: Membership Inference in Deep Learning-Based Time Series Forecasting Models

    … to leak sensitive data, for example through membership inference attacks (MIAs), raises serious privacy concerns. While MIAs are well-studied in domains like image classification, their implications for time series models remain underexplored. This thesis investigates the vulnerability of …

    chalmers Repository record for Privacy Risks in Time Series Models: Membership Inference in Deep Learning-Based Time Series Forecasting Models (opens in a new tab)

  19. Towards Understanding Security and Privacy Risks in the LLM Lifecycle

    … ingested to build or fine-tune models, and the inference time, where the final applications interact with users. A systematic methodology for privacy auditing must therefore encompass both the complex data dependencies forged during training and the attack surfaces exposed during inference. …

    jhu Repository record for Towards Understanding Security and Privacy Risks in the LLM Lifecycle (opens in a new tab) Embargoed until 2028-08-01

Page 1 of 2