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 731 for “"Adversarial"”.

  1. Evaluating Adversarial Robustness of Detection-based Defenses against Adversarial Examples

    … it has been shown that they are vulnerable to adversarial attacks, a set of techniques that violate the integrity, confidentiality, or availability of such systems. In particular, one of the most studied phenomena concerns adversarial examples, i.e., input samples that are carefully manipulated …

    cagliari Repository record for Evaluating Adversarial Robustness of Detection-based Defenses against Adversarial Examples (opens in a new tab)

  2. Adversarial Attack and Defense

    M.S.

    buffalo Repository record for Adversarial Attack and Defense (opens in a new tab)

  3. Adversarial robustness without perturbations

    Models resistant to adversarial perturbations are stable around the neighbourhoods of input images, such that small changes, known as adversarial attacks, cannot dramatically change the prediction. Currently, this stability is obtained with Adversarial Training, which directly teaches models to be …

    mit Repository record for Adversarial robustness without perturbations (opens in a new tab)

  4. Generative modelling and adversarial learning

    … data, such as natural images. Generative adversarial networks (GAN), which are based on the adversarial learning paradigm, are one of the main types of methods for deriving generative models from complicated real-world data. GAN and its variants use a generator to synthesise semantic data …

    uts Repository record for Generative modelling and adversarial learning (opens in a new tab)

  5. Belief propagation generative adversarial networks

    Generative adversarial networks (GANs) are a class of generative models based on a minimax game. They have led to significant improvement in the field of unsupervised learning, especially image generation. However, most works in GANs are based on learning the distribution of the input dataset …

    uiuc Repository record for Belief propagation generative adversarial networks (opens in a new tab)

  6. Layered Unlearning for Adversarial Relearning

    … We find that LU improves robustness to adversarial relearning for several different unlearning methods. Our results contribute to the state-of-the-art of machine unlearning and provide insight into the effect of post-training updates.

    mit Repository record for Layered Unlearning for Adversarial Relearning (opens in a new tab)

  7. Adversarial Examples in Simpler Settings

    In this thesis we explore adversarial examples for simple model families and simple data distributions, focusing in particular on linear and kernel classifiers. On the theoretical front we find evidence that natural accuracy and robust accuracy are more likely than not to be misaligned. We conclude …

    mit Repository record for Adversarial Examples in Simpler Settings (opens in a new tab)

  8. Network optimization in adversarial environments

    … First, we investigate network optimization under adversarial dynamics, where the evolution of network conditions follows some non-stationary and possibly adversarial process. Such an adversarial network dynamics model can be used to capture many real-world scenarios, such as networks under …

    mit Repository record for Network optimization in adversarial environments (opens in a new tab)

  9. Multishot Capacity of Adversarial Networks

    Adversarial network coding studies the transmission of data over networks affected by adversarial noise. In this realm, the noise is modeled by an omniscient adversary who is restricted to corrupting a proper subset of the network edges. In 2018, Ravagnani and Kschischang established a …

    vt Repository record for Multishot Capacity of Adversarial Networks (opens in a new tab)

  10. Understanding Adversarial Robustness in Deep Learning

    This thesis studies the adversarial robustness of deep learning models. Our investigation covers various aspects of this phenomenon, including the development of two new defense algorithms, two new attack algorithms, a novel definition of hierarchical adversarial robustness, and an analysis of how …

    toronto-retro Repository record for Understanding Adversarial Robustness in Deep Learning (opens in a new tab)

  11. Domain Adaptation using Deep Adversarial Models

    … three algorithms and designed a number of deep adversarial models which learn an embedding subspace. The mapped domains were semantically aligned and maximally separated. To maximize model performance through the use of high-risk high-reward learning techniques and to mitigate some difficulties …

    houston Repository record for Domain Adaptation using Deep Adversarial Models (opens in a new tab)

  12. Generative adversarial modeling of 3D shapes

    … thesis, we propose two models, 3D Generative Adversarial Network and ShapeHD, to learn shape priors from existing 3D shapes via generative-adversarial modeling, pushing the limits of shape generation, single-view shape completion and reconstruction. For shape generation, we demonstrate that …

    mit Repository record for Generative adversarial modeling of 3D shapes (opens in a new tab)

  13. Understanding the landscape of adversarial robustness

    … models are pervasively vulnerable to adversarial examples. Adversarial examples are inputs that have been slightly perturbed--such that the semantic content is the same--as to cause malicious behavior in a classifier. The study of adversarial robustness has so far largely focused on …

    mit Repository record for Understanding the landscape of adversarial robustness (opens in a new tab)

  14. Adversarial Resilient and Privacy Preserving Deep learning

    … model inversion during the training phase and adversarial evasion attacks during model inference phase, aiming to cause the well-trained model to misbehave randomly or purposefully. This dissertation research addresses these problems with dual focuses: First, it aims to provide a fundamental …

    gatech Repository record for Adversarial Resilient and Privacy Preserving Deep learning (opens in a new tab)

  15. Adversarial Inverse Reinforcement Learning with Noisy Observations

    … a popular and widely applied IRL method, called Adversarial IRL (AIRL). To render AIRL robust to noise, we formulate the problem of reward inference as one of log-likelihood optimization that accommodates noisy input. We adopt two techniques from the literature on learning hidden representations …

    usm Repository record for Adversarial Inverse Reinforcement Learning with Noisy Observations (opens in a new tab)

  16. MDEA : malware detection with evolutionary adversarial learning

    … at test time. In this paper, I propose MDEA, an Adversarial Malware Detection model that combines a neural network and evolutionary optimization attack samples to make the network robust against evasion attacks. By retraining the model with the evolved malware samples, network performance …

    texas Repository record for MDEA : malware detection with evolutionary adversarial learning (opens in a new tab)

  17. Adversarial Bandits and which Leader to Follow

    L'abstract è presente nell'allegato / the abstract is in the attachment

    poli-torino Repository record for Adversarial Bandits and which Leader to Follow (opens in a new tab)

  18. ASSET PRICING OPTIMIZATION THROUGH GENERATIVE ADVERSARIAL NETWORKS

    … asset pricing optimisation through Generative Adversarial Networks (GAN). We have demonstrated that shallow learning can deliver similar performance for test data as compared to deep learning considered in the literature, with the added benefit of mitigating common challenges such as …

    nus Repository record for ASSET PRICING OPTIMIZATION THROUGH GENERATIVE ADVERSARIAL NETWORKS (opens in a new tab)

  19. Multi-Domain Text Classification with Adversarial Training

    … domains. In particular, these methods adopt adversarial training and shared-private paradigm to implement domain alignment, yielding state-of-the-art performance. Adversarial learning can reduce domain divergence through a minimax optimization to produce domain-invariant features. The …

    carleton Repository record for Multi-Domain Text Classification with Adversarial Training (opens in a new tab)

  20. Adversarial graph contrastive learning with information regularization

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms

    uiuc Repository record for Adversarial graph contrastive learning with information regularization (opens in a new tab)

Page 1 of 37