Adversarial Driving: Attacking End-to-End Autonomous Driving

Han, Wei; Syed, Yunas,; Rowlands, Sareh; Ruan, Wenjie; Wahlström, Johan

doi:10.48550/arxiv.2103.09151

Cited by 8 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They devise two white-box targeted attacks against end-to-end autonomous driving systems. The behavior of the driving model can be manipulated by adding perturbations to the input image [10].…”

Section: B Physical Attacksmentioning

confidence: 99%

A3D: Physical Adversarial Attack on Visual Perception Module of Self-driving Cars

Abideen

Bute

Khalid

et al. 2022

Preprint

View full text Add to dashboard Cite

Advancements in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception. While deep learning for perception has been shown to be vulnerable to a host of subtle adversarial manipulations of images, end-to-end demonstrations of successful attacks, which manipulate the physical environment and result in physical consequences, are scarce. We demonstrate the first end-to-end attacks on autonomous driving in simulation, using simple physically realizable attacks: the painting of black lines on the road. These attacks target deep neural network models for end-to-end autonomous driving control. A systematic investigation shows that such attacks are surprisingly easy to engineer, and we describe scenarios (e.g., right turns) in which they are highly effective, and others that are less vulnerable Our result shows how that physical adversarial attack decreased the accuracy of the state of the art network by up to 30%.

show abstract

Section: B Physical Attacksmentioning

confidence: 99%

A3D: Physical Adversarial Attack on Visual Perception Module of Self-driving Cars

Abideen

Bute

Khalid

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…• Introduction to adversarial robustness: this part will introduce the concept of adversarial robustness by showing some examples from computer vision [45], natural language processing [13], medical systems [35], and autonomous systems [34]. Specifically, we will demonstrate the vulnerabilities of various types of deep learning models to different adversarial examples.…”

Section: Content Detailsmentioning

confidence: 99%

Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications

Ruan

Huang

2021

Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning, presenting a well-structured review of up-to-date techniques to assess the vulnerability of various types of deep learning models to adversarial examples. This tutorial will particularly highlight state-of-the-art techniques in adversarial attacks and robustness verification of deep neural networks (DNNs). We will also introduce some effective countermeasures to improve robustness of deep learning models, with a particular focus on adversarial training. We aim to provide a comprehensive overall picture about this emerging direction and enable the community to be aware of the urgency and importance of designing robust deep learning models in safety-critical data analytical applications, ultimately enabling the end-users to trust deep learning classifiers. We will also summarize potential research directions concerning the adversarial robustness of deep learning, and its potential benefits to enable accountable and trustworthy deep learning-based data analytical systems and applications.

show abstract

“…Furthermore, different research works have shown the ability to generate universal perturbations that can fool any neural network [14]. The inherited weaknesses of DNN models against adversarial attacks raise many security concerns especially for critical applications such as the robustness of deep learning algorithms used for autonomous vehicles [15]. Hence, different studies propose various countermeasure methods against adversarial attacks.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Deep Learning: A Survey on Adversarial Attacks and Defense Mechanisms on Image Classification

et al. 2022

View full text Add to dashboard Cite

The popularity of adapting deep neural networks (DNNs) in solving hard problems has increased substantially. Specifically, in the field of computer vision, DNNs are becoming a core element in developing many image and video classification and recognition applications. However, DNNs are vulnerable to adversarial attacks, in which, given a well-trained image classification model, a malicious input can be crafted by adding mere perturbations to misclassify the image. This phenomena raise many security concerns in utilizing DNNs in critical life applications which attracts the attention of academic and industry researchers. As a result, multiple studies have proposed discussing novel attacks that can compromise the integrity of state-of-the-art image classification neural networks. The raise of these attacks urges the research community to explore countermeasure methods to mitigate these attacks and increase the reliability of adapting DDNs in different major applications. Hence, various defense strategies have been proposed to protect DNNs against adversarial attacks. In this paper, we thoroughly review the most recent and state-of-the-art adversarial attack methods by providing an in-depth analysis and explanation of the working process of these attacks. In our review, we focus on explaining the mathematical concepts and terminologies of the adversarial attacks, which provide a comprehensive and solid survey to the research community. Additionally, we provide a comprehensive review of the most recent defense mechanisms and discuss their effectiveness in defending DNNs against adversarial attacks. Finally, we highlight the current challenges and open issues in this field as well as future research directions.

show abstract

Adversarial Driving: Attacking End-to-End Autonomous Driving

Cited by 8 publications

References 0 publications

A3D: Physical Adversarial Attack on Visual Perception Module of Self-driving Cars

A3D: Physical Adversarial Attack on Visual Perception Module of Self-driving Cars

Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications

Adversarial Deep Learning: A Survey on Adversarial Attacks and Defense Mechanisms on Image Classification

Contact Info

Product

Resources

About