Chong Xiang (Princeton University), Chawin Sitawarin (University of California, Berkeley), Tong Wu (Princeton University), Prateek Mittal (Princeton University)

ETAS Best Short Paper Award Runner-Up!

The physical-world adversarial patch attack poses a security threat to AI perception models in autonomous vehicles. To mitigate this threat, researchers have designed defenses with certifiable robustness. In this paper, we survey existing certifiably robust defenses and highlight core robustness techniques that are applicable to a variety of perception tasks, including classification, detection, and segmentation. We emphasize the unsolved problems in this space to guide future research, and call for attention and efforts from both academia and industry to robustify perception models in autonomous vehicles.

View More Papers

SynthDB: Synthesizing Database via Program Analysis for Security Testing...

An Chen (University of Georgia), Jiho Lee (University of Virginia), Basanta Chaulagain (University of Georgia), Yonghwi Kwon (University of Virginia), Kyu Hyung Lee (University of Georgia)

Read More

A Robust Counting Sketch for Data Plane Intrusion Detection

Sian Kim (Ewha Womans University), Changhun Jung (Ewha Womans University), RhongHo Jang (Wayne State University), David Mohaisen (University of Central Florida), DaeHun Nyang (Ewha Womans University)

Read More

Adversarial Robustness for Tabular Data through Cost and Utility...

Klim Kireev (EPFL), Bogdan Kulynych (EPFL), Carmela Troncoso (EPFL)

Read More

Un-Rocking Drones: Foundations of Acoustic Injection Attacks and Recovery...

Jinseob Jeong (KAIST, Agency for Defense Development), Dongkwan Kim (Samsung SDS), Joonha Jang (KAIST), Juhwan Noh (KAIST), Changhun Song (KAIST), Yongdae Kim (KAIST)

Read More