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 45 for “"Backdoor Attacks"”.

  1. Towards More Realistic and Practical Graph Backdoor Attacks

    … shown that they are highly vulnerable to graph backdoor attacks (GBAs), where adversaries implant malicious triggers to induce targeted misclassification during inference. Despite their effectiveness, existing GBAs are often developed under unrealistic assumptions, such as focusing exclusively …

    odu Repository record for Towards More Realistic and Practical Graph Backdoor Attacks (opens in a new tab)

  2. Un-fair trojan: Targeted backdoor attacks against model fairness

    … have been shown to be vulnerable against various backdoor and data poisoning attacks that adversely affect model behavior. Additionally, these attacks have been shown to make unfair predictions with respect to certain protected features. In federated learning, multiple local models contribute to a …

    njit Repository record for Un-fair trojan: Targeted backdoor attacks against model fairness (opens in a new tab)

  3. 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)

  4. Certified and Forensic Defenses against Poisoning and Backdoor Attacks

    Data poisoning and backdoor attacks manipulate model predictions by inserting malicious instances into the training set. Most existing defenses against poisoning and backdoor attacks are empirical and easily evaded by an adaptive attacker. In addition, existing empirical defenses provide, at best, …

    oregon Repository record for Certified and Forensic Defenses against Poisoning and Backdoor Attacks (opens in a new tab)

  5. Enhancing Robustness of Graph Neural Networks Against Evasive Backdoor Attacks

    … manipulation has become a key concern. Backdoor attacks pose a significant security risk, as they can introduce subtle vulnerabilities during training that may later compromise model predictions in deployment. This thesis investigates methods for defending against such attacks through …

    brock Repository record for Enhancing Robustness of Graph Neural Networks Against Evasive Backdoor Attacks (opens in a new tab)

  6. Investigation of Backdoor Attacks and Design of Effective Countermeasures in Federated Learning

    … of FL increases its vulnerability to adversarial attacks. These include backdoor attacks, which subtly alter classification in some categories, and byzantine attacks, aimed at degrading the overall model accuracy. Detecting and defending against such attacks is challenging, as adversaries can …

    iupui Repository record for Investigation of Backdoor Attacks and Design of Effective Countermeasures in Federated Learning (opens in a new tab)

  7. The Dual Game of Clean-Label Backdoor Attacks and Defenses in NLP

    Textual backdoor attacks are a growing security threat for natural language processing (NLP) systems. These attacks compromise language models by inserting specific ``\textit{triggers}'' into the training data. At inference time, the model misclassifies inputs that contain the trigger, …

    oregon Repository record for The Dual Game of Clean-Label Backdoor Attacks and Defenses in NLP (opens in a new tab)

  8. Beyond the Security of Deep Learning: An Exploration of Stealthy Backdoor Attacks in Computer Vision

    … learning systems, with a particular focus on backdoor attacks—a form of data poisoning where models behave normally under typical inputs but produce attacker-controlled outputs when a specific trigger is present. The research systematically analyzes the effectiveness and stealthiness of such …

    radboud Repository record for Beyond the Security of Deep Learning: An Exploration of Stealthy Backdoor Attacks in Computer Vision (opens in a new tab) Download PDF for Beyond the Security of Deep Learning: An Exploration of Stealthy Backdoor Attacks in Computer Vision (opens in a new tab)

  9. On the Security and Adaptation of Neural Networks: A Study of Adversarial Robustness, Backdoor Attacks, and Transfer Learning

    … models are vulnerable to various adversarial attacks, including evasion, data poisoning, and backdoor attacks, which can compromise their performance and reliability. On the other hand, when these models are deployed as prebuilt solutions, pretrained on tasks different from their intended …

    jhu Repository record for On the Security and Adaptation of Neural Networks: A Study of Adversarial Robustness, Backdoor Attacks, and Transfer Learning (opens in a new tab)

  10. Triggered-Feature Sample Selection for Ultra-Low-Budget Dirty-Label Backdoor Attacks: Prototypicality Ranking and Redundancy-Aware Refinement

    … important concern. Among training-time threats, backdoor attacks are particularly challenging because a compromised model can retain normal predictive behaviour on clean inputs while responding to an attacker-specified trigger with targeted misclassification. Although backdoor research has …

    auckland-tech Repository record for Triggered-Feature Sample Selection for Ultra-Low-Budget Dirty-Label Backdoor Attacks: Prototypicality Ranking and Redundancy-Aware Refinement (opens in a new tab)

  11. Understanding and Extending Backdoor Attacks on Deep Neural Networks: From Behavioural and Mechanistic Analysis to Concept-Level Triggers

    Backdoor attacks pose a serious security threat to deep neural networks by implanting hidden attacker-specified behaviours that are activated only when a trigger is present. Although many attacks and defenses have been evaluated using aggregate metrics such as clean accuracy, attack success rate, …

    calgary Repository record for Understanding and Extending Backdoor Attacks on Deep Neural Networks: From Behavioural and Mechanistic Analysis to Concept-Level Triggers (opens in a new tab)

  12. Towards a Robust Defense: A Multifaceted Approach to the Detection and Mitigation of Neural Backdoor Attacks through Feature Space Exploration and Analysis

    … systems a desirable target for cyberattacks, such as generating adversarial examples to fool a deep learning system to make wrong decisions. In particular, many recent studies have revealed that attackers can corrupt the training of a deep learning model, e.g., through data poisoning, …

    odu Repository record for Towards a Robust Defense: A Multifaceted Approach to the Detection and Mitigation of Neural Backdoor Attacks through Feature Space Exploration and Analysis (opens in a new tab)

  13. Backdoors in contemporary artificial intelligence: the good and the bad

    … AI techniques are vulnerable to adversarial attacks, raising significant safety concerns about their use. Backdoor attacks have gained particular attention among various adversarial attacks against AI due to their stealthy nature. A backdoor attack refers to a generic class of attacks (from …

    umn Repository record for Backdoors in contemporary artificial intelligence: the good and the bad (opens in a new tab)

  14. 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)

  15. Adversarial Attack and Defense in Time Series Classification

    … of security threats, including adversarial and backdoor attacks, and face limitations in certified defense and architectural robustness. This thesis addresses four interrelated challenges in robust and secure TSC, with each contributing to a deeper understanding of vulnerabilities and solutions …

    adelaide Repository record for Adversarial Attack and Defense in Time Series Classification (opens in a new tab)

  16. Training Phase Specific Backdoor Defences For Federated Learning

    … devices. Such manipulations can lead to backdoor attacks that embed undesirable behaviors into the joint model. This serious security issue needs to be addressed before FL systems can be deployed into critical infrastructure. This thesis proposes strategies to protect FL systems from …

    unsw Repository record for Training Phase Specific Backdoor Defences For Federated Learning (opens in a new tab)

  17. A Multi-Domain Trojan Detector for Deep Neural Networks

    Backdoor attacks have been demonstrated to compromise the functioning of machine learning models that utilize deep neural networks (DNNs). An adversary carrying out a backdoor attack embeds a predefined perturbation called a Trojan trigger into a small subset of input samples. The DNN can then be …

    washington Repository record for A Multi-Domain Trojan Detector for Deep Neural Networks (opens in a new tab)

  18. Towards Securing AI Systems: Investigating Threats in Multimodal Autonomous Driving & RAG Systems

    … Among the most stealthy and potent threats are backdoor attacks, where models behave as expected under normal conditions but exhibit malicious behavior when triggered by specific inputs, either digital or physical. This thesis investigates novel backdoor and adversarial vulnerabilities across …

    clemson Repository record for Towards Securing AI Systems: Investigating Threats in Multimodal Autonomous Driving & RAG Systems (opens in a new tab)

Page 1 of 3