65 citations · 114 across the 7 of their papers we have counts for
7 papers · 1 filter
Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers
Wencong You, Zayd Hammoudeh, Daniel Lowd
Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where…
Provable Robustness Against a Union of Adversarial Attacks
Zayd Hammoudeh, Daniel Lowd
Sparse or adversarial attacks arbitrarily perturb an unknown subset of the features. robustness analysis is particularly well-suited for heterogeneous (tabular) d…
Training Data Influence Analysis and Estimation: A Survey
Zayd Hammoudeh, Daniel Lowd
Good models require good training data. For overparameterized deep models, the causal relationship between training data and model predictions is increasingly opaque and poorly und…
Reducing Certified Regression to Certified Classification for General Poisoning Attacks
Zayd Hammoudeh, Daniel Lowd
Adversarial training instances can severely distort a model's behavior. This work investigates certified regression defenses, which provide guaranteed limits on how much a regresso…
Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees
Jonathan Brophy, Zayd Hammoudeh, Daniel Lowd
Influence estimation analyzes how changes to the training data can lead to different model predictions; this analysis can help us better understand these predictions, the models ma…
Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation
Zayd Hammoudeh, Daniel Lowd
Targeted training-set attacks inject malicious instances into the training set to cause a trained model to mislabel one or more specific test instances. This work proposes the task…
Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
Zayd Hammoudeh, Daniel Lowd
Positive-unlabeled (PU) learning trains a binary classifier using only positive and unlabeled data. A common simplifying assumption is that the positive data is representative of t…