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 2 of 2 for “"Adversarial Data Corruption"”.

  1. Scalable Robust Models Under Adversarial Data Corruption

    The presence of noise and corruption in real-world data can be inevitably caused by accidental outliers, transmission loss, or even adversarial data attacks. Unlike traditional random noise usually assume a specific distribution with low corruption ratio, the data collected from crowdsourcing or …

    vt Repository record for Scalable Robust Models Under Adversarial Data Corruption (opens in a new tab)

  2. Algorithm robustness and its applications : Frank-Wolfe and factorized gradient

    … or truncate the gradient information to preserve data privacy, build resilience to outliers, and so on. As a consequence, we can view the trajectories these iterative algorithms follow as having perturbations introduced at each step – perturbations that may be persistent (non zero-mean or neutral) …

    texas Repository record for Algorithm robustness and its applications : Frank-Wolfe and factorized gradient (opens in a new tab)