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 4 of 4 for “"Adversarial robust"”.

  1. Asymptotic Graph Neural Networks Improve Adversarial Robustness in Machine Vision

    … architectural constraints---that produce adversarial robustness in machine vision. This theory proposes a new form of Graph Neural Network (GNN), called an asymptotic GNN, that uses a non-linearity with a vertical asymptote to constrain where the network should be sensitive and insensitive …

    carleton Repository record for Asymptotic Graph Neural Networks Improve Adversarial Robustness in Machine Vision (opens in a new tab)

  2. Adversarial LLM-GANS For Robust Synthetic Pharmaceutical Data in Self-Emulsifying Drug Delivery Systems

    … powered by Large Language Models (LLMs) and a robust, constraint-driven Generative Adversarial Networks (GAN) architecture. First, the DFA integrates the generative capabilities of LLMs with rule-based pharmaceutical validation to generate feasible datasets, which feed into a dual-task machine …

    mississippi Repository record for Adversarial LLM-GANS For Robust Synthetic Pharmaceutical Data in Self-Emulsifying Drug Delivery Systems (opens in a new tab)

  3. An adversarially robust multi-view multi-kernel framework for IoT malware threat hunting

    … task that requires security analysts to design a robust security posture against attackers' tactics, techniques, and procedures (TTPs). However, timely threat hunting is difficult as security mechanisms face new malicious payloads that do not have a single behavior. Moreover, threat actors use …

    guelph Repository record for An adversarially robust multi-view multi-kernel framework for IoT malware threat hunting (opens in a new tab)

  4. Towards adversarial robustness with 01 lossmodels, and novel convolutional neural netsystems for ultrasound images

    This dissertation investigates adversarial robustness with 01 loss models and a novel convolutional neural net systems for vascular ultrasound images. In the first part, the dissertation presents stochastic coordinate descent for 01 loss and its sensitivity to adversarial attacks. The study here …

    njit Repository record for Towards adversarial robustness with 01 lossmodels, and novel convolutional neural netsystems for ultrasound images (opens in a new tab)