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 12 of 12 for “"Backdoor Attacks"”.

  1. TextGuard: Provable defense against backdoor attacks on text classification

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-05-01

    uiuc Repository record for TextGuard: Provable defense against backdoor attacks on text classification (opens in a new tab)

  2. Towards machine learning models robust to adversarial examples and backdoor attacks

    … of such systems: adversarial examples and backdoor data poisoning attacks. Specifically, in the first part of the thesis, we build a methodology for defending against adversarial examples that is the first one to provide non-trivial adversarial robustness against an adaptive adversary. In …

    mit Repository record for Towards machine learning models robust to adversarial examples and backdoor attacks (opens in a new tab)

  3. Exploring the landscape of backdoor attacks on deep neural network models

    … recently been demonstrated to be vulnerable to backdoor attacks. Specifically, by introducing a small set of training inputs, an adversary is able to plant a backdoor in the trained model that enables them to fully control the model's behavior during inference. In this thesis, the landscape of …

    mit Repository record for Exploring the landscape of backdoor attacks on deep neural network models (opens in a new tab)

  4. Understanding and Mitigating Data-Centric Vulnerabilities in Modern AI Systems

    … vulnerabilities, including data poisoning, backdoor attacks, and subtle human-exploitation vectors. This thesis addresses these challenges through a comprehensive data-centric perspective on AI security. First, we examine backdoor attacks in the frequency domain, revealing that many triggers …

    vt Repository record for Understanding and Mitigating Data-Centric Vulnerabilities in Modern AI Systems (opens in a new tab)

  5. Trojan Detection in Large Language Models of Code

    … models of code (Code-LLMs) against trojan attacks. Code-LLMs are widely used in software development for tasks such as vulnerability detection, clone detection, code completion, and code summarization. Popular platforms that use AI-assisted software development include GitHub’s Copilot and …

    houston Repository record for Trojan Detection in Large Language Models of Code (opens in a new tab)

  6. Trustworthy Federated Learning Systems: From Secure Distributed Training to Reliable Fine-tuning

    … updates. This design enables the detection of backdoor attacks that are difficult to identify using conventional parameter-distance methods and improves the robustness of federated model adaptation. Third, it develops Behavioral Hard Probability Optimization (BHPO), a preference-based …

    exeter

  7. Evolving Threats and Defenses in Machine Learning: Focus on Model Inversion and Beyond

    … various emerging threats, model inversion (MI) attacks stand out due to their potential to compromise the confidentiality of training data. This dissertation investigates evolving threats in ML, centering on model inversion and its implications across image classification and natural language …

    vt Repository record for Evolving Threats and Defenses in Machine Learning: Focus on Model Inversion and Beyond (opens in a new tab)

  8. How Data Drives ML Models Performance

    … and consider two different threat models: backdoor attacks and malicious data editing. In this first threat model, an adversary injects a few doctered samples into the training set to control model predictions at inference time. We study the effect of these malicious samples on model …

    mit Repository record for How Data Drives ML Models Performance (opens in a new tab)

  9. Using Public and Private Blockchains for Secure Data Sharing and Analytics

    … hybrid blockchain architecture that discourages backdoor attacks by detecting and punishing the attackers. To further secure shared data, we show how we can use the Trusted Execution Environ- ments(TEEs) to enable efficient, privacy enhancing and secure applications by implementing oblivious …

    tdl Repository record for Using Public and Private Blockchains for Secure Data Sharing and Analytics (opens in a new tab)

  10. Defending Against Trojan Attacks on Neural Network-based Language Models

    Backdoor (Trojan) attacks are a major threat to the security of deep neural network (DNN) models. They are created by an attacker who adds a certain pattern to a portion of given training dataset, causing the DNN model to misclassify any inputs that contain the pattern. These infected classifiers …

    vt Repository record for Defending Against Trojan Attacks on Neural Network-based Language Models (opens in a new tab)

  11. Towards Robust Deep Neural Networks

    … tasks. Unfortunately, they are vulnerable to attacks, such as Trojans during training and Adversarial Examples at test time. Adversarial Examples are inputs with carefully crafted perturbations added to benign samples. In the Computer Vision domain, while the perturbations being imperceptible …

    adelaide Repository record for Towards Robust Deep Neural Networks (opens in a new tab)