# 2022-09-21 更新

### Adversarial Driving: Attacking End-to-End Autonomous Driving

Authors:Han Wu, Syed Yunas, Sareh Rowlands, Wenjie Ruan, Johan Wahlstrom

As research in deep neural networks has advanced, deep convolutional networks have become feasible for automated driving tasks. In particular, there is an emerging trend of employing end-to-end neural network models for the automation of driving tasks. However, previous research has shown that deep neural network classifiers are vulnerable to adversarial attacks. For regression tasks, however, the effect of adversarial attacks is not as well understood. In this paper, we devise two white-box targeted attacks against end-to-end autonomous driving systems. The driving systems use a regression model that takes an image as input and outputs a steering angle. Our attacks manipulate the behavior of the autonomous driving system by perturbing the input image. Both attacks can be initiated in real-time on CPUs without employing GPUs. The efficiency of the attacks is illustrated using experiments conducted in Udacity. Demo video: https://youtu.be/I0i8uN2oOP0.
PDF 7 pages, 6 figures

### GAMA: Generative Adversarial Multi-Object Scene Attacks

Authors:Abhishek Aich, Calvin Khang-Ta, Akash Gupta, Chengyu Song, Srikanth V. Krishnamurthy, M. Salman Asif, Amit K. Roy-Chowdhury

The majority of methods for crafting adversarial attacks have focused on scenes with a single dominant object (e.g., images from ImageNet). On the other hand, natural scenes include multiple dominant objects that are semantically related. Thus, it is crucial to explore designing attack strategies that look beyond learning on single-object scenes or attack single-object victim classifiers. Due to their inherent property of strong transferability of perturbations to unknown models, this paper presents the first approach of using generative models for adversarial attacks on multi-object scenes. In order to represent the relationships between different objects in the input scene, we leverage upon the open-sourced pre-trained vision-language model CLIP (Contrastive Language-Image Pre-training), with the motivation to exploit the encoded semantics in the language space along with the visual space. We call this attack approach Generative Adversarial Multi-object scene Attacks (GAMA). GAMA demonstrates the utility of the CLIP model as an attacker’s tool to train formidable perturbation generators for multi-object scenes. Using the joint image-text features to train the generator, we show that GAMA can craft potent transferable perturbations in order to fool victim classifiers in various attack settings. For example, GAMA triggers ~16% more misclassification than state-of-the-art generative approaches in black-box settings where both the classifier architecture and data distribution of the attacker are different from the victim. Our code will be made publicly available soon.
PDF Accepted at NeurIPS 2022; First two authors contributed equally; Includes Supplementary Material

### Adversarial Detection: Attacking Object Detection in Real Time

Authors:Han Wu, Syed Yunas, Sareh Rowlands, Wenjie Ruan, Johan Wahlstrom

Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. Therefore, it is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. This paper bridges this gap by presenting the first real-time online attack against object detection models. We devise three attacks that fabricate bounding boxes for nonexistent objects at desired locations. The attacks achieve a success rate of about 90% within about 20 iterations. The demo video is available at: https://youtu.be/zJZ1aNlXsMU.
PDF 7 pages, 10 figures

### Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks

Authors:Abhishek Aich, Shasha Li, Chengyu Song, M. Salman Asif, Srikanth V. Krishnamurthy, Amit K. Roy-Chowdhury

State-of-the-art generative model-based attacks against image classifiers overwhelmingly focus on single-object (i.e., single dominant object) images. Different from such settings, we tackle a more practical problem of generating adversarial perturbations using multi-object (i.e., multiple dominant objects) images as they are representative of most real-world scenes. Our goal is to design an attack strategy that can learn from such natural scenes by leveraging the local patch differences that occur inherently in such images (e.g. difference between the local patch on the object person' and the objectbike’ in a traffic scene). Our key idea is: to misclassify an adversarial multi-object image, each local patch in the image should confuse the victim classifier. Based on this, we propose a novel generative attack (called Local Patch Difference or LPD-Attack) where a novel contrastive loss function uses the aforesaid local differences in feature space of multi-object scenes to optimize the perturbation generator. Through various experiments across diverse victim convolutional neural networks, we show that our approach outperforms baseline generative attacks with highly transferable perturbations when evaluated under different white-box and black-box settings.
PDF Accepted at WACV 2023 (Round 1)

目录