现有的对抗示例研究重点是在现有自然图像数据集之上进行数字插入的扰动。这种对抗性例子的构造是不现实的,因为攻击者由于感应和环境影响而在现实世界中部署这种攻击可能是困难的,甚至是不可能的。为了更好地理解针对网络物理系统的对抗性示例,我们提出了通过模拟近似现实世界的。在本文中,我们描述了我们的合成数据集生成工具,该工具可以可扩展收集具有现实的对抗示例的合成数据集。我们使用Carla模拟器收集此类数据集并演示与现实世界图像相同的环境变换和处理的模拟攻击。我们的工具已用于收集数据集以帮助评估对抗性示例的功效,并可以在https://github.com/carla-simulator/carla/pull/4992上找到。
translated by 谷歌翻译
对抗性示例代表了对几个应用程序域中深层神经网络的严重威胁,并且已经产生了大量工作来调查它们并减轻其效果。然而,没有太多的工作专门用于专门设计的数据集来评估神经模型的对抗性鲁棒性。本文介绍了Carla-Gear,这是一种自动生成照片真实合成数据集的工具,可用于系统评估神经模型的对抗性鲁棒性,以防止身体对抗斑块,并比较不同的对抗防御的性能/检测方法。该工具是在Carla模拟器上构建的,使用其Python API,并允许在自动驾驶的背景下生成有关几个视觉任务的数据集。生成的数据集中包含的对抗贴片连接到广告牌或卡车的背面,并通过使用最先进的白色盒子攻击策略来制作,以最大程度地提高测试模型的预测错误。最后,本文提出了一项实验研究,以评估某些防御方法针对此类攻击的性能,以表明如何在将来的工作中使用Carla-Gear生成的数据集作为现实世界中对抗性防御的基准。本文中使用的所有代码和数据集可在http://carlagear.retis.santannapisa.it上获得。
translated by 谷歌翻译
Machine learning models are known to be susceptible to adversarial perturbation. One famous attack is the adversarial patch, a sticker with a particularly crafted pattern that makes the model incorrectly predict the object it is placed on. This attack presents a critical threat to cyber-physical systems that rely on cameras such as autonomous cars. Despite the significance of the problem, conducting research in this setting has been difficult; evaluating attacks and defenses in the real world is exceptionally costly while synthetic data are unrealistic. In this work, we propose the REAP (REalistic Adversarial Patch) benchmark, a digital benchmark that allows the user to evaluate patch attacks on real images, and under real-world conditions. Built on top of the Mapillary Vistas dataset, our benchmark contains over 14,000 traffic signs. Each sign is augmented with a pair of geometric and lighting transformations, which can be used to apply a digitally generated patch realistically onto the sign. Using our benchmark, we perform the first large-scale assessments of adversarial patch attacks under realistic conditions. Our experiments suggest that adversarial patch attacks may present a smaller threat than previously believed and that the success rate of an attack on simpler digital simulations is not predictive of its actual effectiveness in practice. We release our benchmark publicly at https://github.com/wagner-group/reap-benchmark.
translated by 谷歌翻译
Although Deep Neural Networks (DNNs) have achieved impressive results in computer vision, their exposed vulnerability to adversarial attacks remains a serious concern. A series of works has shown that by adding elaborate perturbations to images, DNNs could have catastrophic degradation in performance metrics. And this phenomenon does not only exist in the digital space but also in the physical space. Therefore, estimating the security of these DNNs-based systems is critical for safely deploying them in the real world, especially for security-critical applications, e.g., autonomous cars, video surveillance, and medical diagnosis. In this paper, we focus on physical adversarial attacks and provide a comprehensive survey of over 150 existing papers. We first clarify the concept of the physical adversarial attack and analyze its characteristics. Then, we define the adversarial medium, essential to perform attacks in the physical world. Next, we present the physical adversarial attack methods in task order: classification, detection, and re-identification, and introduce their performance in solving the trilemma: effectiveness, stealthiness, and robustness. In the end, we discuss the current challenges and potential future directions.
translated by 谷歌翻译
在过去的十年中,深度学习急剧改变了传统的手工艺特征方式,具有强大的功能学习能力,从而极大地改善了传统任务。然而,最近已经证明了深层神经网络容易受到对抗性例子的影响,这种恶意样本由小型设计的噪音制作,误导了DNNs做出错误的决定,同时仍然对人类无法察觉。对抗性示例可以分为数字对抗攻击和物理对抗攻击。数字对抗攻击主要是在实验室环境中进行的,重点是改善对抗性攻击算法的性能。相比之下,物理对抗性攻击集中于攻击物理世界部署的DNN系统,这是由于复杂的物理环境(即亮度,遮挡等),这是一项更具挑战性的任务。尽管数字对抗和物理对抗性示例之间的差异很小,但物理对抗示例具有特定的设计,可以克服复杂的物理环境的效果。在本文中,我们回顾了基于DNN的计算机视觉任务任务中的物理对抗攻击的开发,包括图像识别任务,对象检测任务和语义细分。为了完整的算法演化,我们将简要介绍不涉及身体对抗性攻击的作品。我们首先提出一个分类方案,以总结当前的物理对抗攻击。然后讨论现有的物理对抗攻击的优势和缺点,并专注于用于维持对抗性的技术,当应用于物理环境中时。最后,我们指出要解决的当前身体对抗攻击的问题并提供有前途的研究方向。
translated by 谷歌翻译
对抗贴片是旨在欺骗其他表现良好的基于​​神经网络的计算机视觉模型的图像。尽管这些攻击最初是通过数字方式构想和研究的,但由于图像的原始像素值受到干扰,但最近的工作表明,这些攻击可以成功地转移到物理世界中。可以通过打印补丁并将其添加到新捕获的图像或视频素材的场景中来实现。在这项工作中,我们进一步测试了在更具挑战性的条件下物理世界中对抗斑块攻击的功效。我们考虑通过空中或卫星摄像机获得的高架图像训练的对象检测模型,并测试插入沙漠环境场景中的物理对抗斑块。我们的主要发现是,在这些条件下成功实施对抗贴片攻击要比在先前考虑的条件下更难。这对AI安全具有重要意义,因为可能被夸大了对抗性例子所带来的现实世界威胁。
translated by 谷歌翻译
具有丰富注释的高质量结构化数据是处理道路场景的智能车辆系统中的关键组件。但是,数据策展和注释需要大量投资并产生低多样性的情况。最近对合成数据的兴趣日益增长,提出了有关此类系统改进范围的问题,以及产生大量和变化的模拟数据所需的手动工作量。这项工作提出了一条合成数据生成管道,该管道利用现有数据集(如Nuscenes)来解决模拟数据集中存在的困难和域间隙。我们表明,使用现有数据集的注释和视觉提示,我们可以促进自动化的多模式数据生成,模仿具有高保真性的真实场景属性,以及以物理意义的方式使样本多样化的机制。我们通过提供定性和定量实验,并通过使用真实和合成数据来证明MIOU指标的改进,以实现CityScapes和Kitti-Step数据集的语义分割。所有相关代码和数据均在GitHub(https://github.com/shubham1810/trove_toolkit)上发布。
translated by 谷歌翻译
已经证明了现代自动驾驶感知系统在处理互补输入之类的利用图像时,已被证明可以改善互补投入。在孤立中,已发现2D图像非常容易受到对抗性攻击的影响。然而,有有限的研究与图像特征融合的多模态模型的对抗鲁棒性。此外,现有的作品不考虑跨输入方式一致的物理上可实现的扰动。在本文中,我们通过将对抗物体放在主车辆的顶部上展示多传感器检测的实际敏感性。我们专注于身体上可实现的和输入 - 不可行的攻击,因为它们是在实践中执行的可行性,并且表明单个通用对手可以隐藏来自最先进的多模态探测器的不同主机。我们的实验表明,成功的攻击主要是由易于损坏的图像特征引起的。此外,我们发现,在将图像特征中的现代传感器融合方法中,对抗攻击可以利用投影过程来在3D中跨越区域产生误报。朝着更强大的多模态感知系统,我们表明,具有特征剥夺的对抗训练可以显着提高对这种攻击的鲁棒性。然而,我们发现标准的对抗性防御仍然努力防止由3D LIDAR点和2D像素之间不准确的关联引起的误报。
translated by 谷歌翻译
深度学习大大提高了单眼深度估计(MDE)的性能,这是完全基于视觉的自主驾驶(AD)系统(例如特斯拉和丰田)的关键组成部分。在这项工作中,我们对基于学习的MDE产生了攻击。特别是,我们使用基于优化的方法系统地生成隐形的物理对象贴片来攻击深度估计。我们通过面向对象的对抗设计,敏感的区域定位和自然风格的伪装来平衡攻击的隐身和有效性。使用现实世界的驾驶场景,我们评估了对并发MDE模型的攻击和AD的代表下游任务(即3D对象检测)。实验结果表明,我们的方法可以为不同的目标对象和模型生成隐形,有效和健壮的对抗贴片,并在物体检测中以1/1/的斑点检测到超过6米的平均深度估计误差和93%的攻击成功率(ASR)车辆后部9个。具有实际车辆的三个不同驾驶路线上的现场测试表明,在连续视频帧中,我们导致超过6米的平均深度估计误差,并将对象检测率从90.70%降低到5.16%。
translated by 谷歌翻译
现实世界的对抗例(通常以补丁形式)对安全关键计算机视觉任务中的深度学习模型(如在自动驾驶中的视觉感知)中使用深度学习模型构成严重威胁。本文涉及用不同类型的对抗性斑块攻击时,对语义分割模型的稳健性进行了广泛的评价,包括数字,模拟和物理。提出了一种新的损失功能,提高攻击者在诱导像素错误分类方面的能力。此外,提出了一种新的攻击策略,提高了在场景中放置补丁的转换方法的期望。最后,首先扩展用于检测对抗性补丁的最先进的方法以应对语义分割模型,然后改进以获得实时性能,并最终在现实世界场景中进行评估。实验结果表明,尽管具有数字和真实攻击的对抗效果,其影响通常在空间上限制在补丁周围的图像区域。这将打开关于实时语义分段模型的空间稳健性的进一步疑问。
translated by 谷歌翻译
深度神经网络容易受到来自对抗性投入的攻击,并且最近,特洛伊木马误解或劫持模型的决定。我们通过探索有界抗逆性示例空间和生成的对抗网络内的自然输入空间来揭示有界面的对抗性实例 - 通用自然主义侵害贴片的兴趣类 - 我们呼叫TNT。现在,一个对手可以用一个自然主义的补丁来手臂自己,不太恶意,身体上可实现,高效 - 实现高攻击成功率和普遍性。 TNT是普遍的,因为在场景中的TNT中捕获的任何输入图像都将:i)误导网络(未确定的攻击);或ii)迫使网络进行恶意决定(有针对性的攻击)。现在,有趣的是,一个对抗性补丁攻击者有可能发挥更大的控制水平 - 选择一个独立,自然的贴片的能力,与被限制为嘈杂的扰动的触发器 - 到目前为止只有可能与特洛伊木马攻击方法有可能干扰模型建设过程,以嵌入风险发现的后门;但是,仍然意识到在物理世界中部署的补丁。通过对大型视觉分类任务的广泛实验,想象成在其整个验证集50,000张图像中进行评估,我们展示了TNT的现实威胁和攻击的稳健性。我们展示了攻击的概括,以创建比现有最先进的方法实现更高攻击成功率的补丁。我们的结果表明,攻击对不同的视觉分类任务(CIFAR-10,GTSRB,PUBFIG)和多个最先进的深神经网络,如WieredEnet50,Inception-V3和VGG-16。
translated by 谷歌翻译
Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input. Given that that emerging physical systems are using DNNs in safety-critical situations, adversarial examples could mislead these systems and cause dangerous situations. Therefore, understanding adversarial examples in the physical world is an important step towards developing resilient learning algorithms. We propose a general attack algorithm, Robust Physical Perturbations (RP 2 ), to generate robust visual adversarial perturbations under different physical conditions. Using the real-world case of road sign classification, we show that adversarial examples generated using RP 2 achieve high targeted misclassification rates against standard-architecture road sign classifiers in the physical world under various environmental conditions, including viewpoints. Due to the current lack of a standardized testing method, we propose a two-stage evaluation methodology for robust physical adversarial examples consisting of lab and field tests. Using this methodology, we evaluate the efficacy of physical adversarial manipulations on real objects. With a perturbation in the form of only black and white stickers, we attack a real stop sign, causing targeted misclassification in 100% of the images obtained in lab settings, and in 84.8% of the captured video frames obtained on a moving vehicle (field test) for the target classifier.
translated by 谷歌翻译
由于缺乏对AI模型的安全性和鲁棒性的信任,近年来,深度学习模型(尤其是针对安全至关重要的系统)中的对抗性攻击正在越来越受到关注。然而,更原始的对抗性攻击可能是身体上不可行的,或者需要一些难以访问的资源,例如训练数据,这激发了斑块攻击的出现。在这项调查中,我们提供了全面的概述,以涵盖现有的对抗贴片攻击技术,旨在帮助感兴趣的研究人员迅速赶上该领域的进展。我们还讨论了针对对抗贴片的检测和防御措施的现有技术,旨在帮助社区更好地了解该领域及其在现实世界中的应用。
translated by 谷歌翻译
计算机图形技术的最新进展可以使汽车驾驶环境更现实。它们使自动驾驶汽车模拟器(例如DeepGTA-V和Carla(学习采取行动))能够生成大量的合成数据,这些数据可以补充现有的现实世界数据集中,以培训自动驾驶汽车感知。此外,由于自动驾驶汽车模拟器可以完全控制环境,因此它们可以产生危险的驾驶场景,而现实世界中数据集缺乏恶劣天气和事故情况。在本文中,我们将证明将从现实世界收集的数据与模拟世界中生成的数据相结合的有效性,以训练对象检测和本地化任务的感知系统。我们还将提出一个多层次的深度学习感知框架,旨在效仿人类的学习经验,其中在某个领域中学习了一系列从简单到更困难的任务。自动驾驶汽车感知器可以从易于驱动的方案中学习,以通过模拟软件定制的更具挑战性的方案。
translated by 谷歌翻译
Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the recent progress in computer graphics to generate fully labeled, dynamic, and photo-realistic proxy virtual worlds. We propose an efficient real-to-virtual world cloning method, and validate our approach by building and publicly releasing a new video dataset, called "Virtual KITTI" 1 , automatically labeled with accurate ground truth for object detection, tracking, scene and instance segmentation, depth, and optical flow. We provide quantitative experimental evidence suggesting that (i) modern deep learning algorithms pre-trained on real data behave similarly in real and virtual worlds, and (ii) pre-training on virtual data improves performance. As the gap between real and virtual worlds is small, virtual worlds enable measuring the impact of various weather and imaging conditions on recognition performance, all other things being equal. We show these factors may affect drastically otherwise high-performing deep models for tracking.
translated by 谷歌翻译
Computer vision applications in intelligent transportation systems (ITS) and autonomous driving (AD) have gravitated towards deep neural network architectures in recent years. While performance seems to be improving on benchmark datasets, many real-world challenges are yet to be adequately considered in research. This paper conducted an extensive literature review on the applications of computer vision in ITS and AD, and discusses challenges related to data, models, and complex urban environments. The data challenges are associated with the collection and labeling of training data and its relevance to real world conditions, bias inherent in datasets, the high volume of data needed to be processed, and privacy concerns. Deep learning (DL) models are commonly too complex for real-time processing on embedded hardware, lack explainability and generalizability, and are hard to test in real-world settings. Complex urban traffic environments have irregular lighting and occlusions, and surveillance cameras can be mounted at a variety of angles, gather dirt, shake in the wind, while the traffic conditions are highly heterogeneous, with violation of rules and complex interactions in crowded scenarios. Some representative applications that suffer from these problems are traffic flow estimation, congestion detection, autonomous driving perception, vehicle interaction, and edge computing for practical deployment. The possible ways of dealing with the challenges are also explored while prioritizing practical deployment.
translated by 谷歌翻译
智能城市应用程序(例如智能交通路由或事故预防)依赖计算机视觉方法来确切的车辆定位和跟踪。由于精确标记的数据缺乏,从多个摄像机中检测和跟踪3D的车辆被证明是探索挑战的。我们提出了一个庞大的合成数据集,用于多个重叠和非重叠摄像头视图中的多个车辆跟踪和分割。与现有的数据集不同,该数据集仅为2D边界框提供跟踪地面真实,我们的数据集还包含适用于相机和世界坐标中的3D边界框的完美标签,深度估计以及实例,语义和泛型细分。该数据集由17个小时的标记视频材料组成,从64个不同的一天,雨,黎明和夜幕播放的340张摄像机录制,使其成为迄今为止多目标多型多相机跟踪的最广泛数据集。我们提供用于检测,车辆重新识别以及单摄像机跟踪的基准。代码和数据公开可用。
translated by 谷歌翻译
在本文中,我们描述了如何利用明亮的调制光源(例如,廉价,离心激光器)来利用CMOS图像传感器中的电子滚动快门。我们展示了七种不同CMOS相机的攻击,从IoT廉价到半专业监控摄像机,以突出滚动快门攻击的广泛适用性。我们模拟了影响不受控制的设置中滚动快门攻击的基本因素。然后,我们对对象检测任务的攻击作用进行了详尽的评估,研究了攻击参数的效果。我们验证了我们对两个独立相机收集的经验数据的模型,表明通过简单地使用来自相机数据表的信息,对手可以准确地预测注入的失真大小并相应地优化它们的攻击。我们发现,通过选择适当的攻击参数,对手可以通过最先进的探测器隐藏高达75%的物体。我们还调查了与NA \“{i} vers致盲攻击相比攻击的隐秘,表明常见的图像失真度量无法检测到攻击存在。因此,我们向骨干展示了一种新的,准确和轻巧的增强对象检测器的网络识别滚动快门攻击。总体而言,我们的结果表明,滚动快门攻击可以大大降低基于视觉智能系统的性能和可靠性。
translated by 谷歌翻译
对象攻击是对象检测的现实世界中可行的。然而,大多数以前的作品都试图学习应用于对象的本地“补丁”到愚蠢的探测器,这在斜视视角变得较低。为了解决这个问题,我们提出了致密的提案攻击(DPA)来学习探测器的单件,物理和针对性的对抗性伪装。伪装是一体的,因为它们是作为一个物体的整体生成的,因为当在任意观点和不同的照明条件下拍摄时,它们保持对抗性,并且由于它们可能导致探测器被定义为特定目标类别的检测器。为了使生成的伪装在物理世界中稳健,我们介绍了改造的组合来模拟物理现象。此外,为了改善攻击,DPA同时攻击固定建议中的所有分类。此外,我们使用Unity Simulation Engine构建虚拟3D场景,以公平地和可重复地评估不同的物理攻击。广泛的实验表明,DPA优于最先进的方法,并且对于任何物体而言,它是通用的,并且对现实世界的广泛性良好,对安全关键的计算机视觉系统构成潜在的威胁。
translated by 谷歌翻译
Harnessing the benefits of drones for urban innovation at scale requires reliable aerial autonomy. One major barrier to advancing aerial autonomy has been collecting large-scale aerial datasets for training machine learning models. Due to costly and time-consuming real-world data collection through deploying drones, there has been an increasing shift towards using synthetic data for training models in drone applications. However, to increase generalizability of trained policies on synthetic data, incorporating domain randomization into the data generation workflow for addressing the sim-to-real problem becomes crucial. Current synthetic data generation tools either lack domain randomization or rely heavily on manual workload or real samples for configuring and generating diverse realistic simulation scenes. These dependencies limit scalability of the data generation workflow. Accordingly, there is a major challenge in balancing generalizability and scalability in synthetic data generation. To address these gaps, we introduce a modular scalable data generation workflow tailored to aerial autonomy applications. To generate realistic configurations of simulation scenes while increasing diversity, we present an adaptive layered domain randomization approach that creates a type-agnostic distribution space for assets over the base map of the environments before pose generation for drone trajectory. We leverage high-level scene structures to automatically place assets in valid configurations and then extend the diversity through obstacle generation and global parameter randomization. We demonstrate the effectiveness of our method in automatically generating diverse configurations and datasets and show its potential for downstream performance optimization. Our work contributes to generating enhanced benchmark datasets for training models that can generalize better to real-world situations.
translated by 谷歌翻译