Heap overflow attack is one of the major memory corruption attacks that have become prevalent for decades. To defeat this attack,many protection methods are proposed in recent years. However,most of these existing met...Heap overflow attack is one of the major memory corruption attacks that have become prevalent for decades. To defeat this attack,many protection methods are proposed in recent years. However,most of these existing methods focus on user-level heap overflow detection. Only a few methods are proposed for kernel heap protection. Moreover,all these kernel protection methods need modifying the existing OS kernel so that they may not be adopted in practice. To address this problem,we propose a lightweight virtualization-based solution that can protect the kernel heap buffers allocated for the target kernel modules. The key idea of our approach is to combine the static binary analysis and virtualization technology to trap a memory allocation operation of the target kernel module,and then add one secure canary word to the end of the allocated buffer. After that,a monitor process is launched to check the integrity of the canaries. The evaluations show that our system can detect kernel heap overflow attacks effectively with minimal performance cost.展开更多
This paper is concerned with the dimension of the space of the homomorphisms between the Verma modules over a basic classical Lie superalgebra and the kernel of such homomorphism.
Let R be a ring with an identity and C（R） be the category of right R-modules. In this paper we introduce the notion of semi-McCoy module. With this notion we show that McCoy modules of C（R） are closed under kernel...Let R be a ring with an identity and C（R） be the category of right R-modules. In this paper we introduce the notion of semi-McCoy module. With this notion we show that McCoy modules of C（R） are closed under kernels of epimorphisms, and they are also closed under extensions and direct sums with certain conditions. We also get some results on the subcategories of McCoy modules of C（R[x]） and C（R[x; x（-1）]）.展开更多
Aiming at acquiring and processing requirements of temperature sensor signal on the industrial control spot, it designs a RTD module based on ADuCM361 microprocessor. It integrates two types of processors including A ...Aiming at acquiring and processing requirements of temperature sensor signal on the industrial control spot, it designs a RTD module based on ADuCM361 microprocessor. It integrates two types of processors including A -Y ADC with 24 bites high precision and ARM Cortex -M3 kernel with 32bites. Besides, it designs the hardware circuit and software flowchart of RTD temperature acquisition module. Programming practice proves that the model has many advantages concluding simple construction, strong practicability, low cost, wide measuring range, high precision, high reliability and so on.展开更多
A security kernel architeclrne built on trusted computing platform in thelight of thinking about trusted computing is presented According to this architecture,a newsecurity module TCB(Trusted Computing Base)is added t...A security kernel architeclrne built on trusted computing platform in thelight of thinking about trusted computing is presented According to this architecture,a newsecurity module TCB(Trusted Computing Base)is added to the operation system kerneland twooperation interface modes are provided for the sake of self-protection.The security kernel isdivided into two parts and trusted mechanism Is separated from security functionality.Ihe TCBmodule implements the trusted mechanism such as measurement and attestation,while the othercomponents of security kernel provide security functionality based on these mechanisms.Thisarchitecture takes full advantage of functions provided by trusted platform and clearly defines thesecurity perimeter of TCB so as to assure stlf-securily from architcetmal vision.We also presentfunction description of TCB and discuss the strengths and limitations comparing with other relatedresearches.展开更多
【目的】跨视角对象级地理定位(CVOGL)旨在卫星影像上精确定位地面街景或无人机影像所观测目标的地理位置。现有方法多聚焦于图像级匹配,通过对整张影像全局处理实现跨视角关联,缺乏对特定目标的位置编码研究,导致无法将模型的注意力引...【目的】跨视角对象级地理定位(CVOGL)旨在卫星影像上精确定位地面街景或无人机影像所观测目标的地理位置。现有方法多聚焦于图像级匹配,通过对整张影像全局处理实现跨视角关联,缺乏对特定目标的位置编码研究,导致无法将模型的注意力引导到感兴趣目标。并且由于参考图像覆盖范围的变化,查询目标在对应卫星图像中的像素占比极低,精确定位较为困难。【方法】针对以上问题,本文提出了一种基于高斯核函数与异构空间对比损失的跨视角对象级地理定位方法(Cross-View Object-Level Geo-Localization Method with Gaussian Kernel Function and Heterogeneous Spatial Contrastive Loss,GHGeo),用于精确定位感兴趣目标位置。该方法首先通过高斯核函数对查询目标进行精确位置编码,实现了对目标中心点及其分布特征的精细化建模;此外还提出了动态注意力精细化融合模块来动态加权交叉感知全局上下文与局部几何特征的空间相似性,以概率密度预测查询目标在卫星影像中的精确位置;最后通过异构空间对比损失函数来约束其训练过程,缓解跨视角特征差异。【结果】本文在CVOGL数据集进行了实验,实验结果显示:GHGeo在该数据集的“无人机-卫星”任务中,当交并比(IoU)≥25%和≥50%时定位准确率分别达到67.73%和63.00%,相较于基准方法DetGeo分别提升了5.76%和5.34%;在“街景-卫星”定位任务中,对应IoU阈值下的定位准确率分别为48.41%和45.43%的定位准确率,相较于基准方法DetGeo分别提升了2.98%和3.19%。同时与TransGeo,SAFA和VAGeo等方法在CVOGL数据集上进行对比,GHGeo则展现出了更高的定位准确性。【结论】本文方法有效提升了跨视角对象级地理定位方法的精度,为城市规划监测,应急救援调度等应用领域提供关键技术支持和精确位置信息支撑。展开更多
基金supported in part by National Natural Science Foundation of China (NSFC) under Grant No.61602035the National Key Research and Development Program of China under Grant No.2016YFB0800700+1 种基金the Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information SecurityOpen Found of Key Laboratory of IOT Application Technology of Universities in Yunnan Province under Grant No.2015IOT03
文摘Heap overflow attack is one of the major memory corruption attacks that have become prevalent for decades. To defeat this attack,many protection methods are proposed in recent years. However,most of these existing methods focus on user-level heap overflow detection. Only a few methods are proposed for kernel heap protection. Moreover,all these kernel protection methods need modifying the existing OS kernel so that they may not be adopted in practice. To address this problem,we propose a lightweight virtualization-based solution that can protect the kernel heap buffers allocated for the target kernel modules. The key idea of our approach is to combine the static binary analysis and virtualization technology to trap a memory allocation operation of the target kernel module,and then add one secure canary word to the end of the allocated buffer. After that,a monitor process is launched to check the integrity of the canaries. The evaluations show that our system can detect kernel heap overflow attacks effectively with minimal performance cost.
文摘This paper is concerned with the dimension of the space of the homomorphisms between the Verma modules over a basic classical Lie superalgebra and the kernel of such homomorphism.
基金Supported by the National Natural Science Foundation of China(Grant No.11471017)the Natural Science Foundation of Anhui Higher Education Institutions of China(Grant No.KJ2018A0304)the Doctoral Research Foundation and the Research Culture Foundation of Anhui Normal University(Grant No.2014xmpy11)
文摘Let R be a ring with an identity and C（R） be the category of right R-modules. In this paper we introduce the notion of semi-McCoy module. With this notion we show that McCoy modules of C（R） are closed under kernels of epimorphisms, and they are also closed under extensions and direct sums with certain conditions. We also get some results on the subcategories of McCoy modules of C（R[x]） and C（R[x; x（-1）]）.
基金The project has been supported by Chinese National Natural Science Foundation(No.5 l177099)Shahghai City Committee of science and technology project(No.10160501700).
文摘Aiming at acquiring and processing requirements of temperature sensor signal on the industrial control spot, it designs a RTD module based on ADuCM361 microprocessor. It integrates two types of processors including A -Y ADC with 24 bites high precision and ARM Cortex -M3 kernel with 32bites. Besides, it designs the hardware circuit and software flowchart of RTD temperature acquisition module. Programming practice proves that the model has many advantages concluding simple construction, strong practicability, low cost, wide measuring range, high precision, high reliability and so on.
基金Supported by the National Basic Research Programof China(G1999035801)
文摘A security kernel architeclrne built on trusted computing platform in thelight of thinking about trusted computing is presented According to this architecture,a newsecurity module TCB(Trusted Computing Base)is added to the operation system kerneland twooperation interface modes are provided for the sake of self-protection.The security kernel isdivided into two parts and trusted mechanism Is separated from security functionality.Ihe TCBmodule implements the trusted mechanism such as measurement and attestation,while the othercomponents of security kernel provide security functionality based on these mechanisms.Thisarchitecture takes full advantage of functions provided by trusted platform and clearly defines thesecurity perimeter of TCB so as to assure stlf-securily from architcetmal vision.We also presentfunction description of TCB and discuss the strengths and limitations comparing with other relatedresearches.
文摘【目的】跨视角对象级地理定位(CVOGL)旨在卫星影像上精确定位地面街景或无人机影像所观测目标的地理位置。现有方法多聚焦于图像级匹配,通过对整张影像全局处理实现跨视角关联,缺乏对特定目标的位置编码研究,导致无法将模型的注意力引导到感兴趣目标。并且由于参考图像覆盖范围的变化,查询目标在对应卫星图像中的像素占比极低,精确定位较为困难。【方法】针对以上问题,本文提出了一种基于高斯核函数与异构空间对比损失的跨视角对象级地理定位方法(Cross-View Object-Level Geo-Localization Method with Gaussian Kernel Function and Heterogeneous Spatial Contrastive Loss,GHGeo),用于精确定位感兴趣目标位置。该方法首先通过高斯核函数对查询目标进行精确位置编码,实现了对目标中心点及其分布特征的精细化建模;此外还提出了动态注意力精细化融合模块来动态加权交叉感知全局上下文与局部几何特征的空间相似性,以概率密度预测查询目标在卫星影像中的精确位置;最后通过异构空间对比损失函数来约束其训练过程,缓解跨视角特征差异。【结果】本文在CVOGL数据集进行了实验,实验结果显示:GHGeo在该数据集的“无人机-卫星”任务中,当交并比(IoU)≥25%和≥50%时定位准确率分别达到67.73%和63.00%,相较于基准方法DetGeo分别提升了5.76%和5.34%;在“街景-卫星”定位任务中,对应IoU阈值下的定位准确率分别为48.41%和45.43%的定位准确率,相较于基准方法DetGeo分别提升了2.98%和3.19%。同时与TransGeo,SAFA和VAGeo等方法在CVOGL数据集上进行对比,GHGeo则展现出了更高的定位准确性。【结论】本文方法有效提升了跨视角对象级地理定位方法的精度,为城市规划监测,应急救援调度等应用领域提供关键技术支持和精确位置信息支撑。
文摘作为计算机视觉的基础任务,单幅图像超分辨率(Single Image Super-Resolution,SISR)长期以来一直是一个备受关注的研究课题。近期的研究表明,Transformer的成功不仅归功于其自注意力(Self-Attention,SA)机制,还体现在其宏观框架和先进组件的整体设计上。空间池化、位移、多层感知机(Multi-Layer Perception,MLP)、傅里叶变换和常数矩阵等方法,具有与SA机制相似的空间信息编码能力,能够替代并实现与其相当的效果。基于这一发现,本文的目标是利用Transformer中优越的宏观架构与高效的空间信息编码技术结合,改进复杂度较高的SA机制,以提升SISR性能。具体而言,本文重新审视了空间卷积的设计,旨在通过卷积调制技术实现更高效的空间特征编码,并通过动态调制方法表达特征。提出的高效空间信息编码(Efficient Spatial Information Encoding,ESIE)层,采用大核卷积和Hadamard积的方式,模仿查询与键之间的点积操作,并实现与SA机制中值表示再校准类似的效果。因此,ESIE层不仅能够捕捉长程依赖和自适应行为,还能够保持线性计算复杂度。另一方面,针对传统前馈网络(Feed-Forward Network,FFN)在处理空间信息时的次优表现,本文在提出的高效通道信息编码(Efficient Channel Information Encoding,ECIE)层中引入了空间感知和动态自适应机制。该方法有助于增强特征的多样性,并有效地调节层间的信息流动。实验结果表明,本文提出的高效空间-通道信息编码网络(Efficient Spatial-Channel Information Encoding,ESCIEN)在定量和定性评估上均优于现有模型。
