Siwei Lyu

Fast Local Attack: Generating Local Adversarial Examples for Object Detectors

2020 · arXiv (Cornell University)

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object detectors, but they …

Differentially Private SGDA for Minimax Problems

2022 · arXiv (Cornell University)

Stochastic gradient descent ascent (SGDA) and its variants have been the workhorse for solving minimax problems. However, in contrast to the well-studied stochastic gradient descent (SGD) with differential privacy (DP) constraints, there is little work …

Outlier Robust Adversarial Training

2023 · arXiv (Cornell University)

Supervised learning models are challenged by the intrinsic complexities of training data such as outliers and minority subpopulations and intentional attacks at inference time with adversarial samples. While traditional robust learning methods and the recent …