# Resilience of Autonomous Vehicle Object Category Detection to Universal Adversarial Perturbations

arXiv: https://arxiv.org/abs/2107.04749 · HTML: https://mlsanity.com/paper/2107.04749/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 10 Jul 2021.

## Builds on (most cited first, 13 of 13)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Universal Adversarial Perturbations Against Semantic Image Segmentation](https://mlsanity.com/paper/1704.05712/) (2017)
- [An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Models](https://mlsanity.com/paper/2002.02175/) (2020)
- [DARTS: Deceiving Autonomous Cars with Toxic Signs](https://mlsanity.com/paper/1802.06430/) (2018)
- [Universal Adversarial Perturbations: A Survey](https://mlsanity.com/paper/2005.08087/) (2020)
- [Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses](https://mlsanity.com/paper/1904.00979/) (2019)
- [Double Targeted Universal Adversarial Perturbations](https://mlsanity.com/paper/2010.03288/) (2020)

## Abstract (arXiv)

Due to the vulnerability of deep neural networks to adversarial examples, numerous works on adversarial attacks and defenses have been burgeoning over the past several years. However, there seem to be some conventional views regarding adversarial attacks and object detection approaches that most researchers take for granted. In this work, we bring a fresh perspective on those procedures by evaluating the impact of universal perturbations on object detection at a class-level. We apply it to a carefully curated data set related to autonomous driving. We use Faster-RCNN object detector on images of five different categories: person, car, truck, stop sign and traffic light from the COCO data set, while carefully perturbing the images using Universal Dense Object Suppression algorithm. Our results indicate that person, car, traffic light, truck and stop sign are resilient in that order (most to least) to universal perturbations. To the best of our knowledge, this is the first time such a ranking has been established which is significant for the security of the data sets pertaining to autonomous vehicles and object detection in general.