Search Results for author: Zhongyuan Hau

Found 4 papers, 0 papers with code

Jacobian Ensembles Improve Robustness Trade-offs to Adversarial Attacks

no code implementations19 Apr 2022 Kenneth T. Co, David Martinez-Rego, Zhongyuan Hau, Emil C. Lupu

In this work, we propose a novel approach, Jacobian Ensembles-a combination of Jacobian regularization and model ensembles to significantly increase the robustness against UAPs whilst maintaining or improving model accuracy.

Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perception

no code implementations15 Jun 2021 Chengzeng You, Zhongyuan Hau, Soteris Demetriou

In particular, model-level LiDAR spoofing attacks aim to inject fake depth measurements to elicit ghost objects that are erroneously detected by 3D Object Detectors, resulting in hazardous driving decisions.

Autonomous Vehicles motion prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.