捍卫深层神经网络免受对抗性示例是AI安全的关键挑战。为了有效地提高鲁棒性，最近的方法集中在对抗训练中的决策边界附近的重要数据点上。但是，这些方法容易受到自动攻击的影响，这是无参数攻击的合奏，可用于可靠评估。在本文中，我们通过实验研究了其脆弱性的原因，发现现有方法会减少真实标签和其他标签的逻辑之间的利润，同时保持其梯度规范非微小值。减少的边缘和非微小梯度规范会导致其脆弱性，因为最大的logit可以轻松地被扰动翻转。我们的实验还表明，logit边缘的直方图具有两个峰，即小和大的logit边缘。从观察结果来看，我们提出了切换单重损失（SOVR），当数据具有较小的logit rumgins时，它会使用单重损失，从而增加边缘。我们发现，SOVR比现有方法增加了logit的利润率，同时使梯度规范保持较小，并且在针对自动攻击的鲁棒性方面超越了它们。

Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-to-text retrieval. However, such zero-shot performance of CLIP-based models does not realize in tasks that require a finer-grained correspondence between vision and language, such as Visual Question Answering (VQA). We investigate why this is the case, and report an interesting phenomenon of CLIP, which we call the Concept Association Bias (CAB), as a potential cause of the difficulty of applying CLIP to VQA and similar tasks. CAB is especially apparent when two concepts are present in the given image while a text prompt only contains a single concept. In such a case, we find that CLIP tends to treat input as a bag of concepts and attempts to fill in the other missing concept crossmodally, leading to an unexpected zero-shot prediction. For example, when asked for the color of a lemon in an image, CLIP predicts ``purple'' if the image contains a lemon and an eggplant. We demonstrate the Concept Association Bias of CLIP by showing that CLIP's zero-shot classification performance greatly suffers when there is a strong concept association between an object (e.g. lemon) and an attribute (e.g. its color). On the other hand, when the association between object and attribute is weak, we do not see this phenomenon. Furthermore, we show that CAB is significantly mitigated when we enable CLIP to learn deeper structure across image and text embeddings by adding an additional Transformer on top of CLIP and fine-tuning it on VQA. We find that across such fine-tuned variants of CLIP, the strength of CAB in a model predicts how well it performs on VQA.

A practical issue of edge AI systems is that data distributions of trained dataset and deployed environment may differ due to noise and environmental changes over time. Such a phenomenon is known as a concept drift, and this gap degrades the performance of edge AI systems and may introduce system failures. To address this gap, a retraining of neural network models triggered by concept drift detection is a practical approach. However, since available compute resources are strictly limited in edge devices, in this paper we propose a lightweight concept drift detection method in cooperation with a recently proposed on-device learning technique of neural networks. In this case, both the neural network retraining and the proposed concept drift detection are done by sequential computation only to reduce computation cost and memory utilization. Evaluation results of the proposed approach shows that while the accuracy is decreased by 3.8%-4.3% compared to existing batch-based detection methods, it decreases the memory size by 88.9%-96.4% and the execution time by 1.3%-83.8%. As a result, the combination of the neural network retraining and the proposed concept drift detection method is demonstrated on Raspberry Pi Pico that has 264kB memory.

To simulate bosons on a qubit- or qudit-based quantum computer, one has to regularize the theory by truncating infinite-dimensional local Hilbert spaces to finite dimensions. In the search for practical quantum applications, it is important to know how big the truncation errors can be. In general, it is not easy to estimate errors unless we have a good quantum computer. In this paper we show that traditional sampling methods on classical devices, specifically Markov Chain Monte Carlo, can address this issue with a reasonable amount of computational resources available today. As a demonstration, we apply this idea to the scalar field theory on a two-dimensional lattice, with a size that goes beyond what is achievable using exact diagonalization methods. This method can be used to estimate the resources needed for realistic quantum simulations of bosonic theories, and also, to check the validity of the results of the corresponding quantum simulations.

Climate change is becoming one of the greatest challenges to the sustainable development of modern society. Renewable energies with low density greatly complicate the online optimization and control processes, where modern advanced computational technologies, specifically quantum computing, have significant potential to help. In this paper, we discuss applications of quantum computing algorithms toward state-of-the-art smart grid problems. We suggest potential, exponential quantum speedup by the use of the Harrow-Hassidim-Lloyd (HHL) algorithms for sparse matrix inversions in power-flow problems. However, practical implementations of the algorithm are limited by the noise of quantum circuits, the hardness of realizations of quantum random access memories (QRAM), and the depth of the required quantum circuits. We benchmark the hardware and software requirements from the state-of-the-art power-flow algorithms, including QRAM requirements from hybrid phonon-transmon systems, and explicit gate counting used in HHL for explicit realizations. We also develop near-term algorithms of power flow by variational quantum circuits and implement real experiments for 6 qubits with a truncated version of power flows.

研究过程包括许多决定，例如如何应有资格以及在何处发表论文。在本文中，我们介绍了一个一般框架，以调查此类决策的影响。研究效果的主要困难是我们需要了解反事实结果，而实际上并非现实。我们框架的主要见解是灵感来自现有的反事实分析，其中研究人员将双胞胎视为反事实单位。提出的框架将一对彼此引用为双胞胎的论文。这些论文往往是平行的作品，在类似的主题和类似社区中。我们调查了采用不同决策的双论文，观察这些研究带来的研究影响的进展，并通过这些研究的影响来估算决策的影响。我们发布了我们的代码和数据，我们认为由于数据集缺乏反事实研究，因此这是非常有益的。

三维（3D）医学图像的产生可能具有巨大的应用潜力，因为它考虑了3D解剖结构。但是，有两个问题可以防止有效培训3D医疗生成模型：（1）3D医学图像的获取和注释非常昂贵，导致培训图像不足，（2）大量参数是参与3D卷积。为了解决这两个问题，我们提出了一种名为3D Split＆Shuffle-Gan的新型GAN模型。为了解决3D数据稀缺问题，我们首先使用丰富的图像切片预先培训二维（2D）GAN模型，并夸大2D卷积权重以改善3D GAN的初始化。为GAN模型的生成器和鉴别器提出了新型的3D网络体系结构，以显着减少参数的数量，同时保持图像生成的质量。研究了许多体重通胀策略和参数有效的3D架构。对心脏（Stanford Aimi冠状动脉钙）和大脑（阿尔茨海默氏病神经成像计划）的实验表明，所提出的方法会导致改善的3D图像产生质量，参数较少。

自我监督学习的最新发展使我们有可能进一步减少人类干预的多步管道中的干预，其中重点围绕着特定感兴趣的对象而发展。在本文中，焦点在组织病理学图像中的细胞核中放置。特别是，我们旨在以无监督的方式提取蜂窝信息，以完成下游任务。随着核以各种尺寸表现出来，我们提出了一个新的依赖量表卷积层来绕过调整核时尺寸的问题。在三个核数据集上，我们基准了以下方法：手工制作的，预先训练的重新系统，有监督的重新系统和自我监督的特征。我们表明，所提出的卷积层提高了性能，并且与Barlows-Twins结合使用，与低样本设置中的监督范式相比，该层可以更好地编码核编码，并且胜过所有其他建议的无监督方法。此外，我们将现有的TNBC数据集扩展到合并核类别的注释，以丰富和公开释放一个小样本设置数据集以进行核分割和分类。

开放式对象检测（OSOD）最近引起了广泛的关注。它是在正确检测/分类已知对象的同时检测未知对象。我们首先指出，最近的研究中考虑的OSOD方案，该方案考虑了类似于开放式识别（OSR）的无限种类的未知物体，这是一个基本问题。也就是说，我们无法确定要检测到的内容，而对于这种无限的未知对象，这是检测任务所必需的。这个问题导致了对未知对象检测方法的性能的评估困难。然后，我们介绍了OSOD的新颖方案，该方案仅处理与已知对象共享超级类别的未知对象。它具有许多真实的应用程序，例如检测越来越多的细粒对象。这个新环境摆脱了上述问题和评估困难。此外，由于已知和未知对象之间的视觉相似性，它使检测到未知对象更加现实。我们通过实验结果表明，基于标准检测器类别预测的不确定性的简单方法优于先前设置中测试的当前最新OSOD方法。

图像字幕的当前最新方法采用基于区域的特征，因为它们提供了对象级信息，对于描述图像的内容至关重要；它们通常由对象检测器（例如更快的R-CNN）提取。但是，他们有几个问题，例如缺乏上下文信息，不准确检测的风险以及高计算成本。可以通过使用基于网格的功能来解决前两个。但是，如何提取和融合这两种功能是未知的。本文提出了一种仅使用变压器的神经结构，称为砂砾（基于网格和区域的图像字幕变压器），该构建物有效地利用了两个视觉特征来生成更好的字幕。粒度用基于DITR的方法代替了以前方法中使用的基于CNN的检测器，从而使其更快地计算。此外，它的整体设计仅由变压器组成，可以对模型进行端到端的训练。这种创新的设计和双重视觉功能的集成带来了重大的性能提高。几个图像字幕基准的实验结果表明，砂砾的推论准确性和速度优于先前的方法。