Browsing Scholarly Works by Author "Lowd, Daniel"

Navigation

Display Options

Results

  • Automated Attacks on Compression-Based Classifiers 
    Burago, Igor (University of Oregon, 2014-09-29)
    Methods of compression-based text classification have proven their usefulness for various applications. However, in some classification problems, such as spam filtering, a classifier confronts one or many adversaries willing ...
  • Certified and Forensic Defenses against Poisoning and Backdoor Attacks 
    Hammoudeh, Zayd (University of Oregon, 2024-03-25)
    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 ...
  • Collective Classification of Social Network Spam 
    Brophy, Jonathan (University of Oregon, 2017-09-06)
    Unsolicited messages affects virtually every popular social media website, and spammers have become increasingly proficient at bypassing conventional filters, prompting a stronger effort to develop new methods. First, we ...
  • Exploiting Domain Structure with Hybrid Generative-Discriminative Models 
    Kelly, Austen (University of Oregon, 2020-02-27)
    Machine learning methods often face a tradeoff between the accuracy of discriminative models and the lower sample complexity of their generative counterparts. This inspires a need for hybrid methods. In this paper we present ...
  • Learning Tractable Graphical Models 
    Rooshenas, Amirmohammad (University of Oregon, 2017-09-27)
    Probabilistic graphical models have been successfully applied to a wide variety of fields such as computer vision, natural language processing, robotics, and many more. However, for large scale problems represented using ...
  • LEARNING-BASED LANDMARK ESTIMATION OF 3D BODY SCANS 
    Baruwa, Ahmed (University of Oregon, 2024-03-25)
    The use of anatomical landmarks spans a diverse set of applications because they are essential for understanding the human body. Several research studies have examined the correlation between body shape variations and human ...
  • Methods for Analyzing the Evolution of Email Spam 
    Nachenahalli Bhuthegowda, Bharath Kumar (University of Oregon, 2019-01-11)
    Email spam has steadily grown and has become a major problem for users, email service providers, and many other organizations. Many adversarial methods have been proposed to combat spam and various studies have been made ...
  • Robust Large Margin Approaches for Machine Learning in Adversarial Settings 
    Torkamani, MohamadAli (University of Oregon, 2016-11-21)
    Machine learning algorithms are invented to learn from data and to use data to perform predictions and analyses. Many agencies are now using machine learning algorithms to present services and to perform tasks that used ...
  • Robustness of Neural Networks for Discrete Input: An Adversarial Perspective 
    Ebrahimi, Javid (University of Oregon, 2019-04-30)
    In the past few years, evaluating on adversarial examples has become a standard procedure to measure robustness of deep learning models. Literature on adversarial examples for neural nets has largely focused on image ...
  • Understanding and Adapting Tree Ensembles: A Training Data Perspective 
    Brophy, Jonathan (University of Oregon, 2023-03-24)
    Despite the impressive success of deep-learning models on unstructured data (e.g., images, audio, text), tree-based ensembles such as random forests and gradient-boosted trees are hugely popular and remain the preferred ...
  • Vision Transformers Under Data Poisoning Attacks 
    Peery, Gabriel (University of Oregon, 2023)
    Owing to state-of-the-art performance and parallelizability, the Vision Transformer architecture is growing in prevalence for security-critical computer vision tasks. Designers may collect training images from public ...

Search Scholars' Bank


Advanced Search

Browse

My Account

Statistics