← Search

Keane Lucas

2 accepted papers

2023

RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion

NeurIPS 2023poster

Randomized smoothing is a leading approach for constructing classifiers that are certifiably robust against adversarial examples. Existing work on randomized smoothing has focused on classifiers with continuous inputs, such as images, where $\ell_p$-norm bounded adversaries are commonly studied. How…

2022

Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks

ICML 2022spotlight

We propose new, more efficient targeted white-box attacks against deep neural networks. Our attacks better align with the attacker’s goal: (1) tricking a model to assign higher probability to the target class than to any other class, while (2) staying within an $\epsilon$-distance of the attacked in…