Daniel Lowd

activity

20122025

most citedNeural-Symbolic Learning and Reasoning: A Survey and Interpretation

241 citations · 272 across the 11 of their papers we have counts for

collaborators

Showing 2023 · cs.LGShow all

2 papers · 2 filters

cs.LG2023★ 3 cited

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…

cs.LG2023

Provable Robustness Against a Union of $ℓ_{0}$ Adversarial Attacks

Zayd Hammoudeh, Daniel Lowd

Sparse or $ℓ_{0}$ adversarial attacks arbitrarily perturb an unknown subset of the features. $ℓ_{0}$ robustness analysis is particularly well-suited for heterogeneous (tabular) d…

Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers

Provable Robustness Against a Union of ℓ0​ Adversarial Attacks

Provable Robustness Against a Union of $ℓ_{0}$ Adversarial Attacks