# Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Prediction

arXiv: https://arxiv.org/abs/1904.07370 · HTML: https://mlsanity.com/paper/1904.07370/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2019.

## Built on by (most cited first, 16 of 16)

- [Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers](https://mlsanity.com/paper/2203.07983/) (2022)
- [Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness](https://mlsanity.com/paper/2106.02734/) (2021)
- [Rolling Colors: Adversarial Laser Exploits against Traffic Light Recognition](https://mlsanity.com/paper/2204.02675/) (2022)
- [Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perception](https://mlsanity.com/paper/2401.03582/) (2024)
- [Do Deep Networks Transfer Invariances Across Classes?](https://mlsanity.com/paper/2203.09739/) (2022)
- [Pruning Adversarially Robust Neural Networks without Adversarial Examples](https://mlsanity.com/paper/2210.04311/) (2022)
- [Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks](https://mlsanity.com/paper/2106.07141/) (2021)
- [New Adversarial Image Detection Based on Sentiment Analysis](https://mlsanity.com/paper/2305.03173/) (2023)
- [A Large-Scale Study of Model Integration in ML-Enabled Software Systems](https://mlsanity.com/paper/2408.06226/) (2024)
- [A direct proof of a unified law of robustness for Bregman divergence losses](https://mlsanity.com/paper/2405.16639/) (2024)
- [On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving](https://mlsanity.com/paper/2107.02488/) (2021)
- [Adversarially Robust Video Perception by Seeing Motion](https://mlsanity.com/paper/2212.07815/) (2022)
- [Exact Feature Collisions in Neural Networks](https://mlsanity.com/paper/2205.15763/) (2022)
- [Explaining Deep Face Algorithms through Visualization: A Survey](https://mlsanity.com/paper/2309.14715/) (2023)
- [General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothing](https://mlsanity.com/paper/2309.16710/) (2023)
- [Robust Vision Systems for Connected and Autonomous Vehicles: Security Challenges and Attack Vectors](https://mlsanity.com/paper/2602.09740/) (2026)

## Abstract (arXiv)

Deep Neural Networks (DNNs) have tremendous potential in advancing the vision for self-driving cars. However, the security of DNN models in this context leads to major safety implications and needs to be better understood. We consider the case study of steering angle prediction from camera images, using the dataset from the 2014 Udacity challenge. We demonstrate for the first time adversarial testing-time attacks for this application for both classification and regression settings. We show that minor modifications to the camera image (an L2 distance of 0.82 for one of the considered models) result in mis-classification of an image to any class of attacker's choice. Furthermore, our regression attack results in a significant increase in Mean Square Error (MSE) by a factor of 69 in the worst case.