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 24 for “"Inference Attack"”.

  1. Defending against inference attack in online social networks

    … the public awareness since it is possible for attackers to launch several kinds of attacks to obtain users' sensitive and private information by exploiting the massive data obtained from the networks. Even if users conceal their sensitive information, attackers can infer their secrets by …

    uvic Repository record for Defending against inference attack in online social networks (opens in a new tab)

  2. Incorporating Obfuscation Techniques in Privacy Preserving Database-Driven Dynamic Spectrum Access Systems

    … be compromised if SAS is the target of a cyber attack or an inference attack executed by a secondary user (SU). In this thesis, we explore the operational security of IUs in SAS-based DSA systems and propose a novel privacy-preserving SAS-based DSA framework, Suspicion Zone SAS (SZ-SAS), the …

    vt Repository record for Incorporating Obfuscation Techniques in Privacy Preserving Database-Driven Dynamic Spectrum Access Systems (opens in a new tab)

  3. Privacy and security in crowdsensing

    … and incentive mechanisms raised by the inference attack in which a user is able to infer other users' sensitive information according to published information. We propose two task allocation algorithms which defend against location-inference attack. To protect users' bid privacy from …

    colo-mines Repository record for Privacy and security in crowdsensing (opens in a new tab)

  4. Exploring the Privacy Dimension of Wearables Through Machine Learning-Enabled Inference

    … the privacy dimension of wearables through inference attacks facilitated by machine learning approaches. We start our investigation by exploring the attack surface introduced by fitness trackers. We propose an inference attack that breaches location privacy through the elevation profiles …

    ucf Repository record for Exploring the Privacy Dimension of Wearables Through Machine Learning-Enabled Inference (opens in a new tab)

  5. On Identifying and Mitigating Against Vulnerabilities of Machine Learning Models

    … vulnerability of ML models using membership inference (MI) attacks to facilitate the design and training of privacy- preserving models. An MI attack is a fundamental attack that has been widely considered the simplest attack to evaluate the privacy of the training data of ML models because it …

    auckland-ms Repository record for On Identifying and Mitigating Against Vulnerabilities of Machine Learning Models (opens in a new tab)

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

    … 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) → {0, 1}, …

    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)

  7. 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)

  8. Privacy Vulnerabilities in Marginals-based Synthetic Data

    … this by conducting a novel membership inference attack, MAMA-MIA, on three state-of-the-art differentially private SDG algorithms: MST, PrivBayes, and RAP. We present the heuristic for our attack on marginals-based SDG algorithms here. It assumes knowledge of auxiliary "population" …

    washington Repository record for Privacy Vulnerabilities in Marginals-based Synthetic Data (opens in a new tab)

  9. Application of deep learning for predicting schedules in real-time systems

    … However, such determinism is prone to timing inference attacks. Using an analytical approach, an inference attack can be launched with a priori knowledge about the task-set. However, the advancements in deep learning opens new methods that can be used to carry out such attacks. We believe that …

    uiuc Repository record for Application of deep learning for predicting schedules in real-time systems (opens in a new tab)

  10. Towards Privacy-Preserving Federated Recommendation for Transportation Services

    … as location and behavioral tracking, identity inference, etc. Various AI-based personalized recommendation systems for transportation services have been introduced recently. These systems allow for large-scale data integration while providing better personalized recommendations. However, these …

    unsw Repository record for Towards Privacy-Preserving Federated Recommendation for Transportation Services (opens in a new tab)

  11. 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)

  12. Building trustworthy machine learning systems in adversarial environments

    … These adversarial scenarios, known as poisoning attack, adversarial example attack, and inference attack, have demonstrated that security, privacy, and robustness have become more important than ever for AI to gain wider adoption and societal trust. To address these problems, we proposed the …

    vt Repository record for Building trustworthy machine learning systems in adversarial environments (opens in a new tab)

  13. DeepClean: a robust deep learning approach for autonomous vehicle camera data privacy

    … self-driving applications. However, location inference attacks, which involve extracting knowledge from camera data to track and estimate user locations are potential privacy threats to AV-generated camera data. Recently, a few studies investigated privacy-preserving approaches for …

    salford Download PDF for DeepClean: a robust deep learning approach for autonomous vehicle camera data privacy (opens in a new tab)

  14. Towards Secure and Privacy-Preserving Machine Learning Systems

    … From the capability perspective, I examine attacks launched by both cyber and physical domain adversaries. From the goal perspective, I explore attacks targeting three critical security properties: integrity, availability, and confidentiality. First, in the cyber domain, I investigate …

    wustl Repository record for Towards Secure and Privacy-Preserving Machine Learning Systems (opens in a new tab)

  15. Understanding Machine Learning Models through a Data-Centric Lens

    … create. First, we develop a practical membership inference attack against large-scale multi-modal models under realistic constraints that preclude shadow training or access to the target training pipeline. Second, we identify a sustained spike in token-level prediction entropy as a precursor to …

    vt Repository record for Understanding Machine Learning Models through a Data-Centric Lens (opens in a new tab)

  16. Privacy Protection via Adversarial Examples

    <p>Machine learning is increasingly exploited 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 …

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

  17. ENCRYPTED DATA MANAGEMENT SYSTEMS WITH TUNABLE PRIVACY

    … Specifically, we first present a new type of attack, namely, the stake inference attack that exploits permissible leakages present in state-of-the-art (SOTA) private Proof-of-Stake (PoS) blockchains, enabling the inference of precise stake values owned by each honest participant. Afterward, we …

    duke Repository record for ENCRYPTED DATA MANAGEMENT SYSTEMS WITH TUNABLE PRIVACY (opens in a new tab)

  18. Preventing encrypted traffic analysis

    … networks and the increasing feasibility of attacks on these services represent a considerable risk to communications security. Existing mechanisms for preventing traffic analysis focus on re-routing and padding. These prevention techniques have considerable resource and overhead …

    uiuc Repository record for Preventing encrypted traffic analysis (opens in a new tab)

  19. Enhancing Security and Performance of Deep Neural Networks

    … around specific topics such as adversarial attacks. However, due to the remarkable success of ML models, they are now being utilized in highly sensitive domains, raising concerns about potential vulnerabilities. ML models have gained popularity in areas such as healthcare, finance, and the …

    clemson Repository record for Enhancing Security and Performance of Deep Neural Networks (opens in a new tab)

  20. Privacy Protection in Machine Learning: Methods for Structured and Unstructured Data

    … unlearning of specific training examples at inference time without pre-trained parameters. 4. We formulate an evaluation framework for textual unlearning methods to quantify true forgetting. Our white-box evaluation implements a membership inference attack by constructing meaningful features …

    arkansas Repository record for Privacy Protection in Machine Learning: Methods for Structured and Unstructured Data (opens in a new tab)

Page 1 of 2