基于PatchTracker的对抗补丁防御算法

基于深度神经网络的目标检测技术已经广泛应用于各领域,然而,通过对抗补丁攻击在图像中添加局部扰动,以此来误导深度神经网络,对基于目标检测技术的视觉系统构成了严重威胁。针对这一问题,利用对抗补丁和图像背景的语义差异性,提出了一种基于PatchTracker的对抗补丁防御算法,该算法由上游补丁检测器与下游数据增强模块组成。上游补丁检测器使用带有注意力机制的YOLOV5(you only look once-v5)确定对抗补丁所在位置,有助于提高对小尺度对抗补丁的检测精度;将检测区域用合适的像素值覆盖以抹除对抗补丁,上游补丁检测器不仅能够有效降低对抗样本的攻击性,而且不依赖大规模的训练数据;下游数据增强模块通过改进模型训练范式,提高下游目标检测器的鲁棒性;将抹除补丁后的图像输入经过数据增强的下游YOLOV5目标检测模型。在公开的TT100K交通标志数据集上进行了交叉验证,实验表明,与未采取防御措施相比,所提算法能够有效防御多种类型的通用对抗补丁攻击,在检测对抗补丁图像时的mAP(mean average precision)提高65%左右,有效地改善了小尺度对抗补丁的漏检情况。与现有算法比较,所提算法有效提高了神经网络在检测对抗样本时的准确率。此外,所提算法不涉及下游模型结构的修改,具有良好的兼容性。

Patch-Locator:一种基于排序学习的开源软件漏洞补丁定位方法

日益增多的开源软件漏洞对软件安全带来了巨大的风险,补丁在应对这一风险的过程中扮演了非常重要的角色.不幸的是,尽管大部分漏洞的补丁在被披露前就已经开发完毕,但仅有部分补丁会随漏洞同步公开.现有的研究发现了漏洞与其补丁之间存在一定的相关性,并基于这些相关性特征对提交进行了排序,以定位漏洞的补丁,但仍旧存在漏洞数据部分缺失、定位准确率不佳等问题.本文提出了Patch-Locator,一种新的基于排序学习的补丁定位方法,通过扩展漏洞数据源对漏洞数据进行补充,并根据漏洞与补丁文本的相似性、漏洞产生的原因和导致的结果等更能反映漏洞与补丁间关联的因素提取了更具有针对性的相关性特征,并使用LambdaMart排序学习模型对提交基于其具有的相关性特征进行排序以定位安全补丁.本文用来自10个开源软件项目的1669个漏洞来评估Patch-Locator.实验结果表明,Patch-Locator的Recall@1指标为92.22%,Recall@5指标为95.51%,Manual Effort@5指标为1.2455,均优于现有方法.

Formation and ecological response of sand patches in the protection system of Shapotou section of the Baotou-Lanzhou railway,China

The development of bare patches typically signifies a process of ecosystem degradation.Within the protection system of Shapotou section of the Baotou-Lanzhou railway,the extensive emergence of bare sand patches poses a threat to both stability and sustainability.However,there is limited knowledge regarding the morphology,dynamic changes,and ecological responses associated with these sand patches.Therefore,we analyzed the formation and development process of sand patches within the protection system and its effects on herbaceous vegetation growth and soil nutrients through field observation,survey,and indoor analysis methods.The results showed that sand patch development can be divided into three stages,i.e.,formation,expansion,and stabilization,which correspond to the initial,actively developing,and semi-fixed sand patches,respectively.The average dimensions of all sand patch erosional areas were found to be 7.72 m in length,3.91 m in width,and 0.32 m in depth.The actively developing sand patches were the largest,and the initial sand patches were the smallest.Throughout the stage of formation and expansion,the herbaceous community composition changed,and the plant density decreased by more than 50.95%.Moreover,the coverage and height of herbaceous plants decreased in the erosional area and slightly increased in the depositional lobe;and the fine particles and nutrients of soils in the erosional area and depositional lobe showed a decreasing trend.In the stabilization phases of sand patches,the area from the inlet to the bottom of sand patches becomes initially covered with crusts.Vegetation and 0-2 cm surface soil condition improved in the erosional area,but this improvement was not yet evident in the depositional lobe.Factors such as disturbance,climate change,and surface resistance to erosion exert notable influences on the formation and dynamics of sand patches.The results can provide evidence for the future treatment of sand patches and the management of the protection system of Shapotou section of the Baotou-Lanzhou railway.

Do brood parasitic Common Cuckoos develop brood patches during the breeding season?

Many birds develop brood patches on their ventral apterium under hormonal regulation to effectively transmit body heat to eggs during incubation.The developed patch has several characteristics,including de-feathering,vascularization,and edema.However,little is known about whether avian brood parasites that do not incubate their eggs exhibit brood patch development during the breeding season.In this study,we measured the size of the ventral apterium in 114 Common Cuckoos(Cuculus canorus)captured in the field throughout the breeding season and examined the appearance of the ventral apterium to confirm the development of brood patches.We also examined whether morphological traits and various factors correlated with the size of the ventral apterium(sternal apterium and abdominal apterium)and how it changed during the breeding season.We found no clear signs of brood patch development in Common Cuckoos captured throughout the breeding season,indicating that they likely did not develop brood patches on the ventral apterium during this period.We also found that ventral apterium size was positively correlated with wing length and body weight.In addition,Common Cuckoos with newly growing feathers on the boundary of the ventral apterium with pteryla were frequently observed as seasons progressed to the end.In conclusion,Common Cuckoos exhibit neither brood patch development nor the vestigial characteristics of ancestral brood patches,except for the growth of feathers on boundary the ventral apterium.Further studies examining brood patches across different groups of avian brood parasites are valuable for enhancing our understanding of the developmental and physiological adaptations of avian brood parasites.

Scheme Based on Multi-Level Patch Attention and Lesion Localization for Diabetic Retinopathy Grading

Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.

Treatment of 198 Cases of Thyroid Nodules with Sanying Capsule Combined with Xiaoying Patch

[Objectives]To observe the clinical efficacy of Sanying capsule combined with Xiaoying Patch in treating thyroid nodule(TN).[Methods]Two groups were treated similarly,with 200 cases in the control group undergoing basic treatment for 12 weeks and 198 cases in the observation group receiving Sanying capsule combined with Xiaoying patches for the same duration.The clinical symptoms,number of nodules,diameter of the largest nodule,and maximum reduction of nodules were observed before and after treatment.A control analysis was performed,and the underlying mechanisms were explored.[Results]The primary symptoms of the observation group exhibited a more favorable improvement than those of the control group.Additionally,the number of nodules decreased,the diameter of the largest nodule decreased,and the maximum reduction of nodules decreased in both groups following treatment.However,the observation group demonstrated a more pronounced improvement than the control group(P<0.05).[Conclusions]The combination of Sanying capsule and Xiaoying patch has been demonstrated to be an effective treatment for TN,with a high degree of reliability in terms of safety.

Ginger oil-loaded transdermal adhesive patch treats post-traumatic stress disorder

Objective:To find a viable alternative to reduce the number of doses required for the patients with post-traumatic stress disorder(PTSD),and to improve efficacy and patient compliance.Methods: In this study,we used ginger oil,a phytochemical with potential therapeutic properties,to prepare ginger oil patches.High-performance liquid chromatography(HPLC)was used to quantify the main active component of ginger oil,6-gingerol.Transdermal absorption experiments were conducted to optimize the various pressure-sensitive adhesives and permeation enhancers,including their type and concentration.Subsequently,the ginger oil patches were optimized and subjected to content determination and property evaluations.A PTSD mouse model was established using the foot-shock method.The therapeutic effect of ginger oil patches on PTSD was assessed through pathological sections,behavioral tests,and the evaluation of biomarkers such as tumor necrosis factor-α(TNF-α),interleukin-6(IL-6),brain-derived neurotrophic factor(BDNF),and melatonin(MT).Results: The results demonstrated that ginger oil patches exerted therapeutic effects against PTSD by inhibiting inflammatory responses and modulating MT and BDNF levels.Pharmacokinetic experiments revealed that ginger oil patches maintained a stable blood drug concentration for at least one day,addressing the rapid metabolism drawback of 6-gingerol and enhancing its therapeutic efficacy.Conclusions: Ginger oil can be prepared as a transdermal drug patch that meets these requirements,and the bioavailability of the prepared patch is better than that of oral administration.It can improve PTSD with good patient compliance and ease of administration.Therefore,it is a promising therapeutic formulation for the treatment of PTSD.

Unveiling the adaptation strategies of woody plants in remnant forest patches to spatiotemporal urban expansion through leaf trait networks

Background:With the expansion of urban areas,the remnants of forested areas play a crucial role in preserving biodiversity in urban environments.This study aimed to explore the impact of spatiotemporal urban expansion on the networks of leaf traits in woody plants within remnant forest patches,thereby enhancing our understanding of plant adaptive strategies and contributing to the conservation of urban biodiversity.Methods:Our study examined woody plants within 120 sample plots across 15 remnant forest patches in Guiyang,China.We constructed leaf trait networks (LTNs) based on 26 anatomical,structural,and compositional leaf traits and assessed the effects of the spatiotemporal dynamics of urban expansion on these LTNs.Results and conclusions:Our results indicate that shrubs within these patches have greater average path lengths and diameters than trees.With increasing urban expansion intensity,we observed a rise in the edge density of the LTN-shrubs.Additionally,modularity within the networks of shrubs decreased as road density and urban expansion intensity increased,and increases in the average path length and average clustering coefficient for shrubs were observed with a rise in the composite terrain complexity index.Notably,patches subjected to‘leapfrog’expansion exhibited greater average patch length and diameter than those experiencing edge growth.Stomatal traits were found to have high degree centrality within these networks,signifying their substantial contribution to multiple functions.In urban remnant forests,shrubs bolster their resilience to variable environmental pressures by augmenting the complexity of their leaf trait networks.

Deep Global Multiple-Scale and Local Patches Attention Dual-Branch Network for Pose-Invariant Facial Expression Recognition

Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inconsistent from one view to another.This study develops a deep global multiple-scale and local patches attention(GMS-LPA)dual-branch network for pose-invariant FER to weaken the influence of pose variation and selfocclusion on recognition accuracy.In this research,the designed GMS-LPA network contains four main parts,i.e.,the feature extraction module,the global multiple-scale(GMS)module,the local patches attention(LPA)module,and the model-level fusion model.The feature extraction module is designed to extract and normalize texture information to the same size.The GMS model can extract deep global features with different receptive fields,releasing the sensitivity of deeper convolution layers to pose-variant and self-occlusion.The LPA module is built to force the network to focus on local salient features,which can lower the effect of pose variation and self-occlusion on recognition results.Subsequently,the extracted features are fused with a model-level strategy to improve recognition accuracy.Extensive experimentswere conducted on four public databases,and the recognition results demonstrated the feasibility and validity of the proposed methods.

Observing eddy dye patches induced by shear instabilities in the surf zone on a plane beach

The effects of surf zone eddy generated by alongshore currents on the deformation and transport of dye are still poorly understood,and related tracer release experiments are lacking.Therefore,a tracer release laboratory experiment was conducted under monochromatic,unidirectional incident waves with a large incident angle(30°)on a plane beach with a 1:100 slope in a large wave basin.A charge-coupled device suspended above the basin recorded the dye patch image.The evolution of eddy dye patch was observed and the transport and diffusion were analyzed based on the collected images.Subsequently,a linear instability numerical model was adopted to calculate the perturbation velocity field at the initial stage.The observation and image processing results show that surf zone eddy patches occurred and were separated from the original dye patches.Our numerical analysis results demonstrate that the structure of the perturbation velocity field is consistent with the experimental observations,and that the ejection of eddy patches shoreward or offshore may be ascribed to the double vortex.

Evaluation of the Efficacy of Auricular Acupoint Pressure Patch Combined with Modified Huangqi Decoction in Treating Diabetic Nephropathy

Objective:To explore the efficacy of auricular acupoint pressure patch combined with modified Huangqi Decoction in treating diabetic nephropathy.Methods:60 patients with diabetic nephropathy treated in our hospital from January 2021 to December 2022 were selected for this study.The patients were randomly divided into two groups using the random number table method,with 30 patients in each group.Among them,the control group was treated with conventional Western medicine,while the experimental group was treated with auricular acupoint pressure patches combined with modified Huangqi Decoction.The patients’fasting blood glucose(FPG),2-hour postprandial blood glucose(2hPG),glycated hemoglobin(HbA1c),urinary protein quantification,urea nitrogen(BUN),serum creatinine(SCr),and other indicators were detected and recorded before and after treatment.Results:Before treatment,there was no statistically significant difference in the FPG,the 2hPG,and the HbA1c between the two groups of patients(P>0.05);after treatment,the FPG,the 2hPG,and the HbA1c of the patients in the experimental group were significantly lower than those in the control group(P<0.05).Before treatment,there was no statistically significant difference in the urinary protein quantification,the BUN,and the SCr between the two groups of patients(P>0.05);after treatment,the urinary protein quantification,BUN,and SCr of the patients in the experimental group were significantly lower than those in the control group(P<0.05).The experimental group showed better improvement in symptoms such as fatigue,backache,and frequency of nocturia(P<0.05).Conclusion:Auricular acupoint pressure patch combined with modified Huangqi Decoction effectively treats diabetic nephropathy and it helps control blood sugar and renal function indicators and improve clinical symptoms,therefore improving the patients’quality of life.

A Simple Egg Membrane Patch Bridging Method for Repairing Tympanic Membrane Perforation

Objective:To analyze the clinical effect of a simple egg membrane patch bridging method in repairing tympanic membrane perforation.Methods:A total of 93 tympanic membrane perforation patients admitted to the hospital between September 2022 and October 2023 were selected and divided into two groups according to the random number table method.The control group implemented the conventional treatment(n=46 cases),and the patch group adopted the simple egg membrane patch bridging method(n=47 cases).The healing rate of the tympanic membrane,the air-bone gap,the air conduction hearing threshold,the dry ear rate,and the incidence of complications in both groups were compared before and after treatment.Results:The healing rate of the tympanic membrane in the patch group was significantly higher than that of the control group(95.75%vs.76.09%),with P<0.05;there was no difference in the air-bone gap and air conduction hearing threshold levels between the two groups before treatment(P>0.05),and the hearing indexes of the patch group were significantly lower than those of the control group 3 months after treatment(P<0.05);the dry ear rate in the patch group was significantly higher than that of the control group after treatment(85.11%vs.67.39%),and the total incidence of complications was also significantly lower than that of the control group(6.38%vs.21.74%),with P<0.05.Conclusion:The simple egg membrane patch bridging method is effective in repairing tympanic membrane perforation,which can effectively improve patients’hearing levels and reduce the occurrence of post-treatment complications.Thus,it is worth popularizing and applying in the clinic.

一种基于图像patches分割的自监督生成对抗模型

近年来,通过将基于角度旋转的自监督模型引入到生成对抗网络中,一定程度上缓解了生成对抗模型稳定性不足与模式坍塌问题。但是,这种自监督模型基于全局信息对比,缺乏局部相关性,模型特征提取能力不足,导致生成图片的全局相似度较高而像素精度不足。因此,提出一种新型自监督生成对抗模型,将图像块(patches)引入到传统的角度旋转自监督模型中,通过对图像进行分块,将局部图像与整体图像作为输入,在旋转角度判别器的基础上新增位置判别器,在提高模型全局相似性的同时,增强了局部特征相关性。在CIFAR-10与STL-10数据集上进行测试,实验结果表明,基于图像patches分割的自监督生成模型比角度旋转自监督模型的效果更好。

Surface motion of a semi-elliptical hill for incident plane SH waves

A closed-form analytical solution of surface motion of a semi-elliptical cylindrical hill for incident plane SH waves is presented. Although some previous analytical work had already dealt with hill topography of semi-circular and shallow circular, our work aims at calculating surface motion of very prolate hill for high incident frequency, and explaining the special vibrating is checked by boundary conditions, numerical results for and some conclusions are obtained. properties of very prolate hill. Accuracy of the solution surface motion of oblate and prolate hills are calculated,

Simulation model of SAR remote sensing of turbulent wake of semi-elliptical submerged body

In terms of the 2-dimensional hydrodynamic simplified model of a semi-elliptical submerged body moving horizontally at high speed, by using the full-spectrum model of SAR（synthetic aperture radar） remote sensing and taking the effect of oceanic interior turbulence on surface gravity capillary waves into account, applying the k-ε model of turbulence with internal wave mixing, and adopthag the Nasmyth spectrum of oceanic turbulence, the 2-dimensional simulation model of SAR remote sensing of this semi-elliptical submerged body is built up. Simulation by using this model at X band and C band is made in the northeastern South China Sea （21°00＇ N, 119°00＇ E）. Satisfactory results of the delay time and delay distance of turbulent surface wake of this semi-elliptical submerged body, as well as the minimum submerged depth at which this submerged body which cannot be discovered by SAR, are obtained through simulation.

Comprehensive investigation of stress intensity factors in rotating disks containing three-dimensional semi-elliptical cracks

Initiation and propagation of cracks in rotating disks may cause catastrophic failures. Therefore, determination of fracture parameters under different working con- ditions is an essential issue. In this paper, a comprehensive study of stress intensity factors （SIFs） in rotating disks containing three-dimensional （3D） semi-elliptical cracks subjected to different working conditions is carried out. The effects of mechanical prop- erties, rotational velocity, and orientation of cracks on SIFs in rotating disks under cen- trifugal loading are investigated. Also, the effects of using composite patches to reduce SIFs in rotating disks are studied. The effects of patching design variables such as mechanical properties, thickness, and ply angle are investigated separately. The modeling and analytical procedure are verified in comparison with previously reported results in the literature.

A wearable sweat patch for non-invasive and wireless monitoring inflammatory status

Sweat diagnostics are being developed to provide insights into monitoring human health status using an accessi-bly non-invasive technique of sweat analysis[1-3].Abundant compositions,ranging from electrolytes and metabolites to large proteins,can be found in sweat,which have similar types of physiological biomarkers observed in the blood[1].Recent advances in flexible electronics[4-7]have transformed conventional laboratory tests into personalized sweat molecu-lar analysis that facilitates real-time sensing of target biomark-ers[3].

基于字体特征与多尺度PatchGAN的中文字体风格转换研究

针对现有中文字体风格转换方法生成字符图像质量低以及生成字体图像与目标字体图像风格不一致的问题,提出基于字体特征与多尺度patch生成对抗网络的中文字体风格转换方法.首先,根据字体特点设计两个特征提取网络,分别提取字体风格特征和字符内容特征;然后,将两个特征输入生成器,利用字体风格特征约束生成字符图像的风格,字符内容特征约束生成字符图像的字形;最后,将生成字符图像输入到多尺度patch判别器中,对生成结果的多尺度图像块判断真假.实验结果表明,所提方法有效提升了生成字符图像的质量以及与目标字体的风格一致性.

STOCHASTIC PROPAGATION OF SEMI-ELLIPTICAL SURFACE CRACK

The semi-elliptical surface crack growth of structural components with uncertain material resistance under random loading is studied by using the stochastic averaging principle.The FPK equation governing the transition probability density function of crack lengths is derived.The analytical solution of the FPK equation for the case of that the equations for the crack growth in the surface and depth directions are uncoupled is obtained.The effects of the parameters of the stress process and of the material property on the behavior of semi-elliptical fatigue crack growth of the components with deterministic resistance to crack growth in the stationary Gaussian stress process are examined.The comparison of the analytical result with digital simulation shows the effectiveness of the present method.

Evaluation of the Formula of Stress Intensity Factor K_1 for Semi-Elliptical Surface Crack

The stress intensity factor (SIF) of the semi elliptical surface crack in the finite body under extensional stress is sclculated by using the FEM software ANSYS release 5.5. The correction factor M f of SIF at different point along the front of the crack is determined.The relation between M f and the semi elliptical shape a/c , the relative crack depth a/b , the variation of angle θ , the relative crack width 2c/w and the relative height width ratio h/w are calculated respectively. Finally the application range and the modification of the engineering formula about SIF is proposed.