Apple最近透露了它的深度感知散列系统的神经枢纽，以检测文件在文件上传到其iCloud服务之前的用户设备上的儿童性滥用材料（CSAM）。关于保护用户隐私和系统可靠性的公众批评很快就会出现。本文基于神经枢纽的深度感知哈希展示了第一综合实证分析。具体而言，我们表明当前深度感知散列可能不具有稳健性。对手可以通过应用图像的略微变化来操纵散列值，或者通过基于梯度的方法或简单地执行标准图像转换，强制或预防哈希冲突来操纵。这种攻击允许恶意演员轻松利用检测系统：从隐藏滥用材料到框架无辜的用户，一切都是可能的。此外，使用散列值，仍然可以对存储在用户设备上的数据进行推断。在我们的观点中，根据我们的结果，其目前形式的深度感知散列通常不适用于强大的客户端扫描，不应从隐私角度使用。

Content scanning systems employ perceptual hashing algorithms to scan user content for illegal material, such as child pornography or terrorist recruitment flyers. Perceptual hashing algorithms help determine whether two images are visually similar while preserving the privacy of the input images. Several efforts from industry and academia propose to conduct content scanning on client devices such as smartphones due to the impending roll out of end-to-end encryption that will make server-side content scanning difficult. However, these proposals have met with strong criticism because of the potential for the technology to be misused and re-purposed. Our work informs this conversation by experimentally characterizing the potential for one type of misuse -- attackers manipulating the content scanning system to perform physical surveillance on target locations. Our contributions are threefold: (1) we offer a definition of physical surveillance in the context of client-side image scanning systems; (2) we experimentally characterize this risk and create a surveillance algorithm that achieves physical surveillance rates of >40% by poisoning 5% of the perceptual hash database; (3) we experimentally study the trade-off between the robustness of client-side image scanning systems and surveillance, showing that more robust detection of illegal material leads to increased potential for physical surveillance.

模型反转攻击（MIAS）旨在创建合成图像，通过利用模型的学习知识来反映目标分类器的私人培训数据中的班级特征。先前的研究开发了生成的MIA，该MIA使用生成的对抗网络（GAN）作为针对特定目标模型的图像先验。这使得攻击时间和资源消耗，不灵活，并且容易受到数据集之间的分配变化的影响。为了克服这些缺点，我们提出了插头攻击，从而放宽了目标模型和图像之前的依赖性，并启用单个GAN来攻击广泛的目标，仅需要对攻击进行少量调整。此外，我们表明，即使在公开获得的预训练的gan和强烈的分配转变下，也可以实现强大的MIA，而先前的方法无法产生有意义的结果。我们的广泛评估证实了插头攻击的鲁棒性和灵活性，以及​​它们创建高质量图像的能力，揭示了敏感的类特征。

感知哈希映射图像具有相同语义内容与相同的$ n $ bit Hash值相同的图像，同时将语义不同的图像映射到不同的哈希。这些算法在网络安全方面具有重要的应用，例如版权侵权检测，内容指纹和监视。苹果的神经哈什（Neuralhash）就是这样一种系统，旨在检测用户设备上非法内容的存在，而不会损害消费者的隐私。我们提出了令人惊讶的发现，即神经锤差是线性的，这激发了新型黑盒攻击的发展，该攻击可以（i）逃避对“非法”图像的检测，（ii）产生近乎收集，以及（iii）有关哈希德的泄漏信息。图像，全部无访问模型参数。这些脆弱性对神经哈什的安全目标构成了严重威胁；为了解决这些问题，我们建议使用经典加密标准提出一个简单的修复程序。

Existing integrity verification approaches for deep models are designed for private verification (i.e., assuming the service provider is honest, with white-box access to model parameters). However, private verification approaches do not allow model users to verify the model at run-time. Instead, they must trust the service provider, who may tamper with the verification results. In contrast, a public verification approach that considers the possibility of dishonest service providers can benefit a wider range of users. In this paper, we propose PublicCheck, a practical public integrity verification solution for services of run-time deep models. PublicCheck considers dishonest service providers, and overcomes public verification challenges of being lightweight, providing anti-counterfeiting protection, and having fingerprinting samples that appear smooth. To capture and fingerprint the inherent prediction behaviors of a run-time model, PublicCheck generates smoothly transformed and augmented encysted samples that are enclosed around the model's decision boundary while ensuring that the verification queries are indistinguishable from normal queries. PublicCheck is also applicable when knowledge of the target model is limited (e.g., with no knowledge of gradients or model parameters). A thorough evaluation of PublicCheck demonstrates the strong capability for model integrity breach detection (100% detection accuracy with less than 10 black-box API queries) against various model integrity attacks and model compression attacks. PublicCheck also demonstrates the smooth appearance, feasibility, and efficiency of generating a plethora of encysted samples for fingerprinting.

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.

The authors thank Nicholas Carlini (UC Berkeley) and Dimitris Tsipras (MIT) for feedback to improve the survey quality. We also acknowledge X. Huang (Uni. Liverpool), K. R. Reddy (IISC), E. Valle (UNICAMP), Y. Yoo (CLAIR) and others for providing pointers to make the survey more comprehensive.

会员推理攻击（MIS）旨在确定特定样本是否用于培训预测模型。知道这可能确实导致隐私违约。可以说，大多数MIS利用模型的预测分数 - 每个输出的概率给出一些输入 - 在其训练的模型趋于不同地在其训练数据上表现不同。我们认为这是许多现代深度网络架构的谬论，例如，Relu型神经网络几乎总是远离训练数据的高预测分数。因此，MIS将误会失败，因为这种行为不仅导致高伪率，不仅在已知的域名上，而且对分发数据外，并且隐含地作为针对偏心的防御。具体地，使用生成的对抗网络，我们能够产生虚假分类为培训数据的一部分的潜在无限数量的样本。换句话说，MIS的威胁被高估，并且泄漏的信息较少地假设。此外，在分类器的过度自信和对偏话的易感性之间实际上有一个权衡：更频率越多，他们不知道，对远离训练数据的低信任预测，他们越远，他们越多，揭示了训练数据。

已知深度学习系统容易受到对抗例子的影响。特别是，基于查询的黑框攻击不需要深入学习模型的知识，而可以通过提交查询和检查收益来计算网络上的对抗示例。最近的工作在很大程度上提高了这些攻击的效率，证明了它们在当今的ML-AS-A-Service平台上的实用性。我们提出了Blacklight，这是针对基于查询的黑盒对抗攻击的新防御。推动我们设计的基本见解是，为了计算对抗性示例，这些攻击在网络上进行了迭代优化，从而在输入空间中产生了非常相似的图像查询。 Blacklight使用在概率内容指纹上运行的有效相似性引擎来检测高度相似的查询来检测基于查询的黑盒攻击。我们根据各种模型和图像分类任务对八次最先进的攻击进行评估。 Blacklight通常只有几次查询后，都可以识别所有这些。通过拒绝所有检测到的查询，即使攻击者在帐户禁令或查询拒绝之后持续提交查询，Blacklight也可以防止任何攻击完成。 Blacklight在几个强大的对策中也很强大，包括最佳的黑盒攻击，该攻击近似于效率的白色框攻击。最后，我们说明了黑光如何推广到其他域，例如文本分类。

与令人印象深刻的进步触动了我们社会的各个方面，基于深度神经网络（DNN）的AI技术正在带来越来越多的安全问题。虽然在考试时间运行的攻击垄断了研究人员的初始关注，但是通过干扰培训过程来利用破坏DNN模型的可能性，代表了破坏训练过程的可能性，这是破坏AI技术的可靠性的进一步严重威胁。在后门攻击中，攻击者损坏了培训数据，以便在测试时间诱导错误的行为。然而，测试时间误差仅在存在与正确制作的输入样本对应的触发事件的情况下被激活。通过这种方式，损坏的网络继续正常输入的预期工作，并且只有当攻击者决定激活网络内隐藏的后门时，才会发生恶意行为。在过去几年中，后门攻击一直是强烈的研究活动的主题，重点是新的攻击阶段的发展，以及可能对策的提议。此概述文件的目标是审查发表的作品，直到现在，分类到目前为止提出的不同类型的攻击和防御。指导分析的分类基于攻击者对培训过程的控制量，以及防御者验证用于培训的数据的完整性，并监控DNN在培训和测试中的操作时间。因此，拟议的分析特别适合于参考他们在运营的应用方案的攻击和防御的强度和弱点。

Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input x and any target classification t, it is possible to find a new input x that is similar to x but classified as t. This makes it difficult to apply neural networks in security-critical areas. Defensive distillation is a recently proposed approach that can take an arbitrary neural network, and increase its robustness, reducing the success rate of current attacks' ability to find adversarial examples from 95% to 0.5%.In this paper, we demonstrate that defensive distillation does not significantly increase the robustness of neural networks by introducing three new attack algorithms that are successful on both distilled and undistilled neural networks with 100% probability. Our attacks are tailored to three distance metrics used previously in the literature, and when compared to previous adversarial example generation algorithms, our attacks are often much more effective (and never worse). Furthermore, we propose using high-confidence adversarial examples in a simple transferability test we show can also be used to break defensive distillation. We hope our attacks will be used as a benchmark in future defense attempts to create neural networks that resist adversarial examples.

As automated face recognition applications tend towards ubiquity, there is a growing need to secure the sensitive face data used within these systems. This paper presents a survey of biometric template protection (BTP) methods proposed for securing face templates (images/features) in neural-network-based face recognition systems. The BTP methods are categorised into two types: Non-NN and NN-learned. Non-NN methods use a neural network (NN) as a feature extractor, but the BTP part is based on a non-NN algorithm, whereas NN-learned methods employ a NN to learn a protected template from the unprotected template. We present examples of Non-NN and NN-learned face BTP methods from the literature, along with a discussion of their strengths and weaknesses. We also investigate the techniques used to evaluate these methods in terms of the three most common BTP criteria: recognition accuracy, irreversibility, and renewability/unlinkability. The recognition accuracy of protected face recognition systems is generally evaluated using the same (empirical) techniques employed for evaluating standard (unprotected) biometric systems. However, most irreversibility and renewability/unlinkability evaluations are found to be based on theoretical assumptions/estimates or verbal implications, with a lack of empirical validation in a practical face recognition context. So, we recommend a greater focus on empirical evaluations to provide more concrete insights into the irreversibility and renewability/unlinkability of face BTP methods in practice. Additionally, an exploration of the reproducibility of the studied BTP works, in terms of the public availability of their implementation code and evaluation datasets/procedures, suggests that it would be difficult to faithfully replicate most of the reported findings. So, we advocate for a push towards reproducibility, in the hope of advancing face BTP research.

Vertical federated learning is a trending solution for multi-party collaboration in training machine learning models. Industrial frameworks adopt secure multi-party computation methods such as homomorphic encryption to guarantee data security and privacy. However, a line of work has revealed that there are still leakage risks in VFL. The leakage is caused by the correlation between the intermediate representations and the raw data. Due to the powerful approximation ability of deep neural networks, an adversary can capture the correlation precisely and reconstruct the data. To deal with the threat of the data reconstruction attack, we propose a hashing-based VFL framework, called \textit{HashVFL}, to cut off the reversibility directly. The one-way nature of hashing allows our framework to block all attempts to recover data from hash codes. However, integrating hashing also brings some challenges, e.g., the loss of information. This paper proposes and addresses three challenges to integrating hashing: learnability, bit balance, and consistency. Experimental results demonstrate \textit{HashVFL}'s efficiency in keeping the main task's performance and defending against data reconstruction attacks. Furthermore, we also analyze its potential value in detecting abnormal inputs. In addition, we conduct extensive experiments to prove \textit{HashVFL}'s generalization in various settings. In summary, \textit{HashVFL} provides a new perspective on protecting multi-party's data security and privacy in VFL. We hope our study can attract more researchers to expand the application domains of \textit{HashVFL}.

Alphazero，Leela Chess Zero和Stockfish Nnue革新了计算机国际象棋。本书对此类引擎的技术内部工作进行了完整的介绍。该书分为四个主要章节 - 不包括第1章（简介）和第6章（结论）：第2章引入神经网络，涵盖了所有用于构建深层网络的基本构建块，例如Alphazero使用的网络。内容包括感知器，后传播和梯度下降，分类，回归，多层感知器，矢量化技术，卷积网络，挤压网络，挤压和激发网络，完全连接的网络，批处理归一化和横向归一化和跨性线性单位，残留层，剩余层，过度效果和底漆。第3章介绍了用于国际象棋发动机以及Alphazero使用的经典搜索技术。内容包括minimax，alpha-beta搜索和蒙特卡洛树搜索。第4章展示了现代国际象棋发动机的设计。除了开创性的Alphago，Alphago Zero和Alphazero我们涵盖Leela Chess Zero，Fat Fritz，Fat Fritz 2以及有效更新的神经网络（NNUE）以及MAIA。第5章是关于实施微型α。 Shexapawn是国际象棋的简约版本，被用作为此的示例。 Minimax搜索可以解决六ap峰，并产生了监督学习的培训位置。然后，作为比较，实施了类似Alphazero的训练回路，其中通过自我游戏进行训练与强化学习结合在一起。最后，比较了类似α的培训和监督培训。

联合学习已被提议作为隐私的机器学习框架，该框架使多个客户能够在不共享原始数据的情况下进行协作。但是，在此框架中，设计并不能保证客户隐私保护。先前的工作表明，联邦学习中的梯度共享策略可能容易受到数据重建攻击的影响。但是，实际上，考虑到高沟通成本或由于增强隐私要求，客户可能不会传输原始梯度。实证研究表明，梯度混淆，包括通过梯度噪声注入和通过梯度压缩的无意化混淆的意图混淆，可以提供更多的隐私保护，以防止重建攻击。在这项工作中，我们提出了一个针对联合学习中图像分类任务的新数据重建攻击框架。我们表明，通常采用的梯度后处理程序，例如梯度量化，梯度稀疏和梯度扰动，可能会在联合学习中具有错误的安全感。与先前的研究相反，我们认为不应将隐私增强视为梯度压缩的副产品。此外，我们在提出的框架下设计了一种新方法，以在语义层面重建图像。我们量化语义隐私泄漏，并根据图像相似性分数进行比较。我们的比较挑战了文献中图像数据泄漏评估方案。结果强调了在现有联合学习算法中重新审视和重新设计对客户数据的隐私保护机制的重要性。

Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5.59 to 2.42.

While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-trained text encoders from external sources, and their users trust that the retrieved models will behave as promised. Unfortunately, this might not be the case. We introduce backdoor attacks against text-guided generative models and demonstrate that their text encoders pose a major tampering risk. Our attacks only slightly alter an encoder so that no suspicious model behavior is apparent for image generations with clean prompts. By then inserting a single non-Latin character into the prompt, the adversary can trigger the model to either generate images with pre-defined attributes or images following a hidden, potentially malicious description. We empirically demonstrate the high effectiveness of our attacks on Stable Diffusion and highlight that the injection process of a single backdoor takes less than two minutes. Besides phrasing our approach solely as an attack, it can also force an encoder to forget phrases related to certain concepts, such as nudity or violence, and help to make image generation safer.

即使机器学习算法已经在数据科学中发挥了重要作用，但许多当前方法对输入数据提出了不现实的假设。由于不兼容的数据格式，或数据集中的异质，分层或完全缺少的数据片段，因此很难应用此类方法。作为解决方案，我们提出了一个用于样本表示，模型定义和培训的多功能，统一的框架，称为“ Hmill”。我们深入审查框架构建和扩展的机器学习的多个范围范式。从理论上讲，为HMILL的关键组件的设计合理，我们将通用近似定理的扩展显示到框架中实现的模型所实现的所有功能的集合。本文还包含有关我们实施中技术和绩效改进的详细讨论，该讨论将在MIT许可下发布供下载。该框架的主要资产是其灵活性，它可以通过相同的工具对不同的现实世界数据源进行建模。除了单独观察到每个对象的一组属性的标准设置外，我们解释了如何在框架中实现表示整个对象系统的图表中的消息推断。为了支持我们的主张，我们使用框架解决了网络安全域的三个不同问题。第一种用例涉及来自原始网络观察结果的IoT设备识别。在第二个问题中，我们研究了如何使用以有向图表示的操作系统的快照可以对恶意二进制文件进行分类。最后提供的示例是通过网络中实体之间建模域黑名单扩展的任务。在所有三个问题中，基于建议的框架的解决方案可实现与专业方法相当的性能。

Federated learning is a collaborative method that aims to preserve data privacy while creating AI models. Current approaches to federated learning tend to rely heavily on secure aggregation protocols to preserve data privacy. However, to some degree, such protocols assume that the entity orchestrating the federated learning process (i.e., the server) is not fully malicious or dishonest. We investigate vulnerabilities to secure aggregation that could arise if the server is fully malicious and attempts to obtain access to private, potentially sensitive data. Furthermore, we provide a method to further defend against such a malicious server, and demonstrate effectiveness against known attacks that reconstruct data in a federated learning setting.

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.