Search Results for author:
Found 8 papers, 6 papers with code
What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations
Adversarial attacks curated against NLP models are increasingly becoming practical threats.
Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers
Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data.
Provable Robustness Against a Union of $\ell_0$ Adversarial Attacks
Sparse or $\ell_0$ adversarial attacks arbitrarily perturb an unknown subset of the features.
Reducing Certified Regression to Certified Classification for General Poisoning Attacks
We also show that the assumptions made by existing state-of-the-art certified classifiers are often overly pessimistic.
Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees
In the pursuit of better understanding GBDT predictions and generally improving these models, we adapt recent and popular influence-estimation methods designed for deep learning models to GBDTs.
Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation
This work proposes the task of target identification, which determines whether a specific test instance is the target of a training-set attack.
Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
A common simplifying assumption is that the positive data is representative of the target positive class.
