Mixtures of classifiers (a.k.a. randomized ensembles) have been proposed as a
way to improve robustness against adversarial attacks. However, it has been
shown that existing attacks are not well suited for this kind of classifiers.
In this paper, we discuss the problem of attacking a mixture in a principled
way and introduce two desirable properties of attacks based on a geometrical
analysis of the problem (effectiveness and maximality). We then show that
existing attacks do not meet both of these properties. Finally, we introduce a
new attack called lattice climber attack with theoretical guarantees on the
binary linear setting, and we demonstrate its performance by conducting
experiments on synthetic and real datasets.

对混合分类器的攻击进行了几何分析，介绍了两个理想的攻击属性（有效性和最大性），并证明了现有的攻击方法不满足这两个属性。最后，介绍了一种具有理论保证的新攻击方法称为格攀攻击，并通过对合成和真实数据集的实验展示了其性能。

混合分类器的对抗攻击

Adversarial attacks for mixtures of classifiers

Microscopy images are usually analyzed qualitatively or manually and there is
a need for autonomous quantitative analysis of objects. In this paper, we
present a physics-based computational model for accurate segmentation and
geometrical analysis of one-dimensional irregular and deformable objects from
microscopy images. This model, named Nano1D, has four steps of preprocessing,
segmentation, separating overlapped objects and geometrical measurements. The
model is tested on Ag nanowires, and successfully segments and analyzes their
geometrical characteristics including length, width and distributions. The
function of the algorithm is not undermined by the size, number, density,
orientation and overlapping of objects in images. The main strength of the
model is shown to be its ability to segment and analyze overlapping objects
successfully with more than 99% accuracy, while current machine learning and
computational models suffer from inaccuracy and inability to segment
overlapping objects. Nano1D can analyze one-dimensional (1D) nanoparticles
including nanowires, nanotubes, nanorods in addition to other 1D features of
microstructures like microcracks, dislocations etc.

本文介绍了一种基于物理的计算模型，用于对来自显微镜图像的一维不规则和可变形物体进行准确的分割和几何分析，该模型已成功地应用于银纳米线的分割和分析。

Nano1D：一种用于低维目标分割与分析的精确计算机视觉模型

Nano1D: An accurate Computer Vision model for segmentation and analysis  of low-dimensional objects

Colorectal polyps are important precursors to colon cancer, a major health
problem. Colon capsule endoscopy (CCE) is a safe and minimally invasive
examination procedure, in which the images of the intestine are obtained via
digital cameras on board of a small capsule ingested by a patient. The video
sequence is then analyzed for the presence of polyps. We propose an algorithm
that relieves the labor of a human operator analyzing the frames in the video
sequence. The algorithm acts as a binary classifier, which labels the frame as
either containing polyps or not, based on the geometrical analysis and the
texture content of the frame. The geometrical analysis is based on a
segmentation of an image with the help of a mid-pass filter. The features
extracted by the segmentation procedure are classified according to an
assumption that the polyps are characterized as protrusions that are mostly
round in shape. Thus, we use a best fit ball radius as a decision parameter of
a binary classifier. We present a statistical study of the performance of our
approach on a data set containing over 18,900 frames from the endoscopic video
sequences of five adult patients. The algorithm demonstrates a solid
performance, achieving 47% sensitivity per frame and over 81% sensitivity per
polyp at a specificity level of 90%. On average, with a video sequence length
of 3747 frames, only 367 false positive frames need to be inspected by a human
operator.

使用几何分析和纹理内容的二元分类器进行结肠胶囊内镜图像诊断，结果表明算法在具有 47% 的每帧敏感度和 90% 特异度的情况下，对肿瘤的诊断表现良好。