尽管最近在不同的应用程序方案中广泛部署了3D点云分类，但它仍然非常容易受到对抗攻击的影响。面对对抗性攻击，这增加了对3D模型的强大训练的重要性。基于我们对现有对抗性攻击的性能的分析，在输入数据的中和高频组件中发现了更多的对抗性扰动。因此，通过抑制训练阶段的高频含量，改善了针对对抗性示例的模型。实验表明，提出的防御方法降低了对PointNet，PointNet ++和DGCNN模型的六次攻击的成功率。特别是，与最先进的方法相比，Drop100攻击的平均分类精度在Drop100攻击中平均提高3.8％，而Drop200攻击的平均分类精度提高了3.8％。与其他可用方法相比，该方法还提高了原始数据集的模型精度。

随着各种3D安全关键应用的关注，点云学习模型已被证明容易受到对抗性攻击的影响。尽管现有的3D攻击方法达到了很高的成功率，但它们会以明显的扰动来深入研究数据空间，这可能会忽略几何特征。取而代之的是，我们从新的角度提出了点云攻击 - 图谱域攻击，旨在在光谱域中扰动图形转换系数，该系数对应于改变某些几何结构。具体而言，利用图形信号处理，我们首先通过图形傅立叶变换（GFT）自适应地将点的坐标转换为光谱域，以进行紧凑的表示。然后，我们基于我们建议通过可学习的图形光谱滤波器扰动GFT系数的几何结构的影响。考虑到低频组件主要有助于3D对象的粗糙形状，我们进一步引入了低频约束，以限制不察觉到的高频组件中的扰动。最后，通过将扰动的光谱表示形式转换回数据域，从而生成对抗点云。实验结果证明了拟议攻击的有效性，这些攻击既有易经性和攻击成功率。

Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. Robust training and defend-by-denoise are typical strategies for defending adversarial perturbations, including adversarial training and statistical filtering, respectively. However, they either induce massive computational overhead or rely heavily upon specified noise priors, limiting generalized robustness against attacks of all kinds. This paper introduces a new defense mechanism based on denoising diffusion models that can adaptively remove diverse noises with a tailored intensity estimator. Specifically, we first estimate adversarial distortions by calculating the distance of the points to their neighborhood best-fit plane. Depending on the distortion degree, we choose specific diffusion time steps for the input point cloud and perform the forward diffusion to disrupt potential adversarial shifts. Then we conduct the reverse denoising process to restore the disrupted point cloud back to a clean distribution. This approach enables effective defense against adaptive attacks with varying noise budgets, achieving accentuated robustness of existing 3D deep recognition models.

最近，3D深度学习模型已被证明易于对其2D对应物的对抗性攻击影响。大多数最先进的（SOTA）3D对抗性攻击对3D点云进行扰动。为了在物理场景中再现这些攻击，需要重建生成的对抗3D点云以网状，这导致其对抗效果显着下降。在本文中，我们提出了一个名为Mesh攻击的强烈的3D对抗性攻击，通过直接对3D对象的网格进行扰动来解决这个问题。为了利用最有效的基于梯度的攻击，介绍了一种可差异化的样本模块，其反向传播点云梯度以网格传播。为了进一步确保没有异常值和3D可打印的对抗性网状示例，采用了三种网格损耗。广泛的实验表明，所提出的方案优于SOTA 3D攻击，通过显着的保证金。我们还在各种防御下实现了SOTA表现。我们的代码可用于：https：//github.com/cuge1995/mesh-attack。

3D动态点云提供了现实世界中的对象或运动场景的离散表示，这些对象已被广泛应用于沉浸式触发，自主驾驶，监视，\ textit {etc}。但是，从传感器中获得的点云通常受到噪声的扰动，这会影响下游任务，例如表面重建和分析。尽管为静态点云降级而做出了许多努力，但很少有作品解决动态点云降级。在本文中，我们提出了一种新型的基于梯度的动态点云降解方法，利用了梯度场估计的时间对应关系，这也是动态点云处理和分析中的基本问题。梯度场是嘈杂点云的对数概况函数的梯度，我们基于我们执行梯度上升，以使每个点收敛到下面的清洁表面。我们通过利用时间对应关系来估计每个表面斑块的梯度，在该时间对应关系中，在经典力学中搜索了在刚性运动的情况下搜索的时间对应贴片。特别是，我们将每个贴片视为一个刚性对象，它通过力在相邻框架的梯度场中移动，直到达到平衡状态，即当贴片上的梯度总和到达0时。由于梯度在该点更接近下面的表面，平衡贴片将适合下层表面，从而导致时间对应关系。最后，沿贴片中每个点的位置沿相邻帧中相应的贴片平均的梯度方向更新。实验结果表明，所提出的模型优于最先进的方法。

Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their powerful capabilities, their robustness against adversarial attacks, which have been proven to be fatally malicious towards deep neural networks, remains unknown. In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes. In order to evaluate the robustness of the completion models, we propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones, while being completed as another object with totally different semantic information. Specifically, we minimize the representation discrepancy between the adversarial example and the target point set to jointly explore the adversarial point clouds in the geometry space and the feature space. Furthermore, to launch a stealthier attack, we innovatively employ the neighbourhood density information to tailor the perturbation constraint, leading to geometry-aware and distribution-adaptive modifications for each point. Extensive experiments against different premier point cloud completion networks show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01. We conclude that existing completion models are severely vulnerable to adversarial examples, and state-of-the-art defenses for point cloud classification will be partially invalid when applied to incomplete and uneven point cloud data.

虽然近年来，在2D图像领域的攻击和防御中，许多努力已经探讨了3D模型的脆弱性。现有的3D攻击者通常在点云上执行点明智的扰动，从而导致变形的结构或异常值，这很容易被人类察觉。此外，它们的对抗示例是在白盒设置下产生的，当转移到攻击远程黑匣子型号时经常遭受低成功率。在本文中，我们通过提出一种新的难以察觉的转移攻击（ITA）：1）难以察觉的3D点云攻击来自两个新的和具有挑战性的观点：1）难以察觉：沿着邻域表面的正常向量限制每个点的扰动方向，导致产生具有类似几何特性的示例，从而增强了难以察觉。 2）可转移性：我们开发了一个对抗性转变模型，以产生最有害的扭曲，并强制实施对抗性示例来抵抗它，从而提高其对未知黑匣子型号的可转移性。此外，我们建议通过学习更辨别的点云表示来培训更强大的黑盒3D模型来防御此类ITA攻击。广泛的评估表明，我们的ITA攻击比最先进的人更令人无法察觉和可转让，并验证我们的国防战略的优势。

Deep learning-based 3D object detectors have made significant progress in recent years and have been deployed in a wide range of applications. It is crucial to understand the robustness of detectors against adversarial attacks when employing detectors in security-critical applications. In this paper, we make the first attempt to conduct a thorough evaluation and analysis of the robustness of 3D detectors under adversarial attacks. Specifically, we first extend three kinds of adversarial attacks to the 3D object detection task to benchmark the robustness of state-of-the-art 3D object detectors against attacks on KITTI and Waymo datasets, subsequently followed by the analysis of the relationship between robustness and properties of detectors. Then, we explore the transferability of cross-model, cross-task, and cross-data attacks. We finally conduct comprehensive experiments of defense for 3D detectors, demonstrating that simple transformations like flipping are of little help in improving robustness when the strategy of transformation imposed on input point cloud data is exposed to attackers. Our findings will facilitate investigations in understanding and defending the adversarial attacks against 3D object detectors to advance this field.

利用3D点云数据已经成为在面部识别和自动驾驶等许多领域部署人工智能的迫切需要。然而，3D点云的深度学习仍然容易受到对抗的攻击，例如迭代攻击，点转换攻击和生成攻击。这些攻击需要在严格的界限内限制对抗性示例的扰动，导致不切实际的逆势3D点云。在本文中，我们提出了对普遍的图形 - 卷积生成的对抗网络（ADVGCGAN）从头开始产生视觉上现实的对抗3D点云。具体地，我们使用图形卷积发电机和带有辅助分类器的鉴别器来生成现实点云，从真实3D数据学习潜在分布。不受限制的对抗性攻击损失纳入GaN的特殊逆势训练中，使得发电机能够产生对抗实例来欺骗目标网络。与现有的最先进的攻击方法相比，实验结果表明了我们不受限制的对抗性攻击方法的有效性，具有更高的攻击成功率和视觉质量。此外，拟议的Advgcan可以实现更好的防御模型和比具有强烈伪装的现有攻击方法更好的转移性能。

尽管基于3D点云表示的基于自我监督的对比度学习模型最近取得了成功，但此类预训练模型的对抗性鲁棒性引起了人们的关注。对抗性对比学习（ACL）被认为是改善预训练模型的鲁棒性的有效方法。相比之下，投影仪被认为是在对比度预处理过程中删除不必要的特征信息的有效组成部分，并且大多数ACL作品还使用对比度损失，与预测的功能表示形式相比损失，在预处理中产生对抗性示例，而“未转移”的功能表征用于发电的对抗性输入。在推理期间。由于投影和“未投影”功能之间的分布差距，其模型受到限制，以获取下游任务的可靠特征表示。我们介绍了一种新方法，通过利用虚拟对抗性损失在对比度学习框架中使用“未重新注射”功能表示，以生成高质量的3D对抗示例，以进行对抗训练。我们介绍了强大的意识损失功能，以对抗自我监督对比度学习框架。此外，我们发现选择具有正常操作员（DON）操作员差异的高差异作为对抗性自学对比度学习的附加输入，可以显着提高预训练模型的对抗性鲁棒性。我们在下游任务上验证我们的方法，包括3D分类和使用多个数据集的3D分割。它在最先进的对抗性学习方法上获得了可比的鲁棒精度。

3D点云正在成为许多现实世界应用中的关键数据表示形式，例如自动驾驶，机器人技术和医学成像。尽管深度学习的成功进一步加速了物理世界中3D点云的采用，但深度学习因其易受对抗性攻击的脆弱性而臭名昭著。在这项工作中，我们首先确定最先进的经验防御，对抗性训练，由于梯度混淆，在适用于3D点云模型方面有一个重大限制。我们进一步提出了PointDP，这是一种纯化策略，利用扩散模型来防御3D对抗攻击。我们对六个代表性3D点云体系结构进行了广泛的评估，并利用10+强和适应性攻击来证明其较低的稳健性。我们的评估表明，在强烈攻击下，PointDP比最新的纯化方法实现了明显更好的鲁棒性。在不久的将来将包括与PointDP合并的随机平滑验证结果的结果。

尽管在各种应用中取得了突出的性能，但点云识别模型经常遭受自然腐败和对抗性扰动的困扰。在本文中，我们深入研究了点云识别模型的一般鲁棒性，并提出了点云对比对抗训练（PointCat）。 PointCat的主要直觉是鼓励目标识别模型缩小清洁点云和损坏点云之间的决策差距。具体而言，我们利用有监督的对比损失来促进识别模型提取的超晶体特征的对齐和均匀性，并设计一对带有动态原型指南的集中式损失，以避免这些特征与其属于其属于其归属类别群的偏离。为了提供更具挑战性的损坏点云，我们对噪声生成器以及从头开始的识别模型进行了对手训练，而不是将基于梯度的攻击用作内部循环，例如以前的对手训练方法。全面的实验表明，在包括各种损坏的情况下，所提出的PointCat优于基线方法，并显着提高不同点云识别模型的稳健性，包括各向同性点噪声，LIDAR模拟的噪声，随机点掉落和对抗性扰动。

Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even if malicious attackers cannot obtain all the underlying model parameters, they can use adversarial examples to attack various DNN-based task systems. Researchers have proposed various defense methods to protect DNNs, such as reducing the aggressiveness of adversarial examples by preprocessing or improving the robustness of the model by adding modules. However, some defense methods are only effective for small-scale examples or small perturbations but have limited defense effects for adversarial examples with large perturbations. This paper assigns different defense strategies to adversarial perturbations of different strengths by grading the perturbations on the input examples. Experimental results show that the proposed method effectively improves defense performance. In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications.

随着神经网络的命题点云，深入学习已经开始在3D对象识别领域发光，而研究人员则对普遍攻击进行了增长的兴趣来调查点云网络的可靠性。然而，大多数现有研究旨在欺骗人类或防御算法，而少数几个地解决了模型本身的操作原理就在关键点选择方面保持缺陷。在这项工作中，我们提出了两个对抗方法：一个点攻击（OPA）和临界遍历攻击（CTA），它包含可解释的技术，并旨在探讨点云网络的内在工作原理及其对关键点扰动的敏感性。我们的结果表明，流行点云网络可以通过从输入实例转换一个点来欺骗近100美元的成功率。此外，我们展示了不同点归因分布对点云网络的对抗鲁棒性的有趣影响。最后，我们讨论了我们的方法如何促进点云网络的解释性研究。据我们所知，这是一个关于解释性的第一个基于云的对抗方法。我们的代码可在https://github.com/explain3d/exp-one-point-atk-pc上获得。

长期以来，3D面部识别因其抵抗当前的物理对抗攻击（例如对抗斑块）而被认为是安全的。但是，本文表明，3D面部识别系统很容易受到攻击，从而导致逃避和模仿攻击。我们是第一个针对3D面部识别系统（称为结构化光成像攻击（SLIA）的）提出可实现的攻击的人，该系统利用了基于结构化的3D扫描设备的弱点。 Slia在结构化的光成像系统中利用投影仪来创建对抗性照明，以污染重建的点云。首先，我们提出了一个3D变换不变的损耗函数（3D-TI），以生成对逆动力的对抗扰动，这对头部运动更强大。然后，我们将3D成像过程集成到攻击优化中，从而最大程度地减少了流条纹模式的总像素转移。我们意识到对现实世界3D面部识别系统的躲避和模仿攻击。与倒角和基于倒角+KNN的方法相比，我们的方法对预计模式的修改需要较少，并且达到0.47（模拟）和0.89（躲避）的平均攻击成功率。本文揭示了当前结构化的光成像技术的不安全感，并阐明了设计安全的3D面部识别身份验证系统。

深度神经网络（DNN）受到对抗的示例攻击的威胁。对手可以通过将小型精心设计的扰动添加到输入来容易地改变DNN的输出。对手示例检测是基于强大的DNNS服务的基本工作。对手示例显示了人类和DNN在图像识别中的差异。从以人为本的角度来看，图像特征可以分为对人类可易于理解的主导特征，并且对人类来说是不可理解的隐性特征，但是被DNN利用。在本文中，我们揭示了难以察觉的对手实例是隐性特征误导性神经网络的乘积，并且对抗性攻击基本上是一种富集图像中的这些隐性特征的方法。对手实例的难以察觉表明扰动丰富了隐性特征，但几乎影响了主导特征。因此，对抗性实例对滤波偏离隐性特征敏感，而良性示例对这种操作免疫。受到这个想法的启发，我们提出了一种仅称为特征过滤器的标签的侵略性检测方法。功能过滤器利用离散余弦变换到占主导地位的大约单独的隐性功能，并获得默认隐性功能的突变图像。只有在输入和其突变体上进行DNN的预测标签，特征过滤器可以实时检测高精度和少量误报的难以察觉的对抗性示例。

尽管机器学习系统的效率和可扩展性，但最近的研究表明，许多分类方法，尤其是深神经网络（DNN），易受对抗的例子;即，仔细制作欺骗训练有素的分类模型的例子，同时无法区分从自然数据到人类。这使得在安全关键区域中应用DNN或相关方法可能不安全。由于这个问题是由Biggio等人确定的。 （2013）和Szegedy等人。（2014年），在这一领域已经完成了很多工作，包括开发攻击方法，以产生对抗的例子和防御技术的构建防范这些例子。本文旨在向统计界介绍这一主题及其最新发展，主要关注对抗性示例的产生和保护。在数值实验中使用的计算代码（在Python和R）公开可用于读者探讨调查的方法。本文希望提交人们将鼓励更多统计学人员在这种重要的令人兴奋的领域的产生和捍卫对抗的例子。

Video compression plays a crucial role in video streaming and classification systems by maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this paper, we conduct the first systematic study for adversarial attacks on deep learning-based video compression and downstream classification systems. Our attack framework, dubbed RoVISQ, manipulates the Rate-Distortion ($\textit{R}$-$\textit{D}$) relationship of a video compression model to achieve one or both of the following goals: (1) increasing the network bandwidth, (2) degrading the video quality for end-users. We further devise new objectives for targeted and untargeted attacks to a downstream video classification service. Finally, we design an input-invariant perturbation that universally disrupts video compression and classification systems in real time. Unlike previously proposed attacks on video classification, our adversarial perturbations are the first to withstand compression. We empirically show the resilience of RoVISQ attacks against various defenses, i.e., adversarial training, video denoising, and JPEG compression. Our extensive experimental results on various video datasets show RoVISQ attacks deteriorate peak signal-to-noise ratio by up to 5.6dB and the bit-rate by up to $\sim$ 2.4$\times$ while achieving over 90$\%$ attack success rate on a downstream classifier. Our user study further demonstrates the effect of RoVISQ attacks on users' QoE.

Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by adversarial examples that are generated by adding small but purposeful distortions to natural examples. Previous studies to defend against adversarial examples mostly focused on refining the DNN models, but have either shown limited success or required expensive computation. We propose a new strategy, feature squeezing, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. By comparing a DNN model's prediction on the original input with that on squeezed inputs, feature squeezing detects adversarial examples with high accuracy and few false positives.This paper explores two feature squeezing methods: reducing the color bit depth of each pixel and spatial smoothing. These simple strategies are inexpensive and complementary to other defenses, and can be combined in a joint detection framework to achieve high detection rates against state-of-the-art attacks.

Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete. We demonstrate that thirteen defenses recently published at ICLR, ICML and NeurIPS-and which illustrate a diverse set of defense strategies-can be circumvented despite attempting to perform evaluations using adaptive attacks. While prior evaluation papers focused mainly on the end result-showing that a defense was ineffective-this paper focuses on laying out the methodology and the approach necessary to perform an adaptive attack. Some of our attack strategies are generalizable, but no single strategy would have been sufficient for all defenses. This underlines our key message that adaptive attacks cannot be automated and always require careful and appropriate tuning to a given defense. We hope that these analyses will serve as guidance on how to properly perform adaptive attacks against defenses to adversarial examples, and thus will allow the community to make further progress in building more robust models.