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 “"imperceptible perturbations"”.

  1. Deception and defense from machine learning to supply chains

    … have traditionally involved conspicuous perturbations compared to the subtle changes of the more continuous visual and auditory domains. Instead, we propose imperceptible perturbations: techniques that manipulate text encodings without affecting the text in its rendered form. We use these …

    cambridge Repository record for Deception and defense from machine learning to supply chains (opens in a new tab)

  2. Building Trustworthy Artificial Intelligence of Things Systems in Adversarial Environments

    … diffusion models. Our attack adds customized imperceptible perturbations to the image prompts and can mislead the diffusion model from generating any attacker-chosen content, including NSFW content. We hope this work can offer insights into the fundamental security and privacy research of the …

    vt Repository record for Building Trustworthy Artificial Intelligence of Things Systems in Adversarial Environments (opens in a new tab)

  3. Energy Efficient Deep Spiking Recurrent Neural Networks: A Reservoir Computing-Based Approach

    … respectively. Adversarial attacks are small and imperceptible perturbations of the input data, which have shown to be able to fool deep learning (DL) models. So far, many adversarial attack and defense mechanisms have been introduced for DL models. Compromising the security and reliability of …

    vt Repository record for Energy Efficient Deep Spiking Recurrent Neural Networks: A Reservoir Computing-Based Approach (opens in a new tab)

  4. Towards robust and domain invariant feature representations in Deep Learning

    … some vulnerabilities of deep networks to small imperceptible changes that occur in the given input. The research problems that comprise this dissertation lie in the cross section of two open topics: (1) Studying and developing methods that enable neural networks learn robust representations (2) …

    maryland Repository record for Towards robust and domain invariant feature representations in Deep Learning (opens in a new tab)