基于深度学习的智能合约漏洞检测方法

以太坊是当下最流行的区块链平台之一,目前已部署数千万个智能合约,控制了价值数千亿美元的以太坊加密货币。由智能合约漏洞引起的安全事件层出不穷,资金损失尤为严重。针对当前智能合约漏洞检测率较低、检测性能不足的问题,提出了基于深度学习的智能合约漏洞检测方法。编译以太坊智能合约源码,解析其对应的字节码得到操作码数据流,根据以太坊黄皮书中操作码与16进制数的对应关系构建字典,将操作码数据流转化为用16进制数表示的操作码序列。通过对操作码序列进行分析,设计循环神经网络、长短期记忆神经网络和卷积神经网络-长短期记忆神经网络3种不同的深度学习网络结构进行漏洞检测。在真实环境中采集了47 527个智能合约,针对智能合约6种漏洞的检测,卷积神经网络-长短期记忆神经网络模型的Macro-F1达到了82.1%。大量的实验结果表明,所提出的模型和方法可实现高效的智能合约漏洞检测。     

模型检验技术在软件漏洞自动挖掘中的应用

将在工业设计领域应用很成功的模型检验技术引入到信息技术软件产品的安全漏洞挖掘中,提出了针对源码的漏洞挖掘系统原型,以开放源代码的操作系统Linux为例,建立了特权释放和文件创建的安全属性模型,并举例加以验证.研究结果表明:该方法是一种自动化挖掘软件安全漏洞并证明漏洞存在性的形式化方法,对挖掘已经确认机理类型的漏洞非常有效.     

京沪线客流和旅客快车开行方案的分析

客流是研究京沪高速客运专线运输组织模式的基础，在已有的研究报告中，一般都认为京沪线的跨线客流约占２／３，而本线客流占１／３左右。本文通过对京沪线实绩客流和现行旅客快车开行方案结构的深入分析，提出了＂跨线客流与本线客流各占５０％左右，而跨线旅客快车开行对数约占２／３，本线旅客快车开行对数占１／３左右＂的结论，它对研究京沪高速客运专线运输组织问题有重要参考价值。     

基于证据推理的高铁综合客运 枢纽客流图像背景建模

针对高铁综合客运枢纽客流图像特征,提出基于证据推理的客流图像背景建模方法. 利用均值背景模型和灰度分区处理提高背景模型的处理速度,通过引入证据推理构建合适的mass函数,提高背景灰度值的取值范围的置信度,从而提高背景图像的精确性. 结果表明,该方法原理正确,在高铁综合客运枢纽客流安全预警实际应用中,能够快速准确地生成客流背景图像,保证了客流信息提取的速度和精度.     

Megabase deletions of gene deserts result in viable mice

The functional importance of the roughly 98% of mammalian genomes not corresponding to protein coding sequences remains largely undetermined. Here we show that some large-scale deletions of the non-coding DNA referred to as gene deserts can be well tolerated by an organism. We deleted two large non-coding intervals, 1,511 kilobases and 845 kilobases in length, from the mouse genome. Viable mice homozygous for the deletions were generated and were indistinguishable from wild-type littermates with regard to morphology, reproductive fitness, growth, longevity and a variety of parameters assaying general homeostasis. Further detailed analysis of the expression of multiple genes bracketing the deletions revealed only minor expression differences in homozygous deletion and wild-type mice. Together, the two deleted segments harbour 1,243 non-coding sequences conserved between humans and rodents (more than 100 base pairs, 70% identity). Some of the deleted sequences might encode for functions unidentified in our screen; nonetheless, these studies further support the existence of potentially 'disposable DNA' in the genomes of mammals.     

An efficient algorithm to generate candidates in discovering frequent episodes

0 IntroductionData mining is widely used in many research fieldssuch as decision supporting systems[1], bio-informationanalysis[2]and knowledge engineering[3-5]. Most data col-lected from scientific experiments or telecommunicationnetworks have inherent sequential nature inthemand canthus be abstractly viewed as a sequence of events . Onebasic problemin miningsuchevent sequencesis discoveryof recurrent combinations of events , which are calledepisodes. Once frequent episodes are discovered,rul…     

道路客运服务技术创新

运用技术创新系统理论阐述了道路客运服务技术创新内涵,并从系统性、动态性和优化原理论证了道路客运服务技术创新的产生过程与思维模式,最后,结合江西长运客运服务技术创新的实例加以验证.     

A murine lung cancer co-clinical trial identifies genetic modifiers of therapeutic response

Targeted therapies have demonstrated efficacy against specific subsets of molecularly defined cancers. Although most patients with lung cancer are stratified according to a single oncogenic driver, cancers harbouring identical activating genetic mutations show large variations in their responses to the same targeted therapy. The biology underlying this heterogeneity is not well understood, and the impact of co-existing genetic mutations, especially the loss of tumour suppressors, has not been fully explored. Here we use genetically engineered mouse models to conduct a 'co-clinical' trial that mirrors an ongoing human clinical trial in patients with KRAS-mutant lung cancers. This trial aims to determine if the MEK inhibitor selumetinib (AZD6244) increases the efficacy of docetaxel, a standard of care chemotherapy. Our studies demonstrate that concomitant loss of either p53 (also known as Tp53) or Lkb1 (also known as Stk11), two clinically relevant tumour suppressors, markedly impaired the response of Kras-mutant cancers to docetaxel monotherapy. We observed that the addition of selumetinib provided substantial benefit for mice with lung cancer caused by Kras and Kras and p53 mutations, but mice with Kras and Lkb1 mutations had primary resistance to this combination therapy. Pharmacodynamic studies, including positron-emission tomography (PET) and computed tomography (CT), identified biological markers in mice and patients that provide a rationale for the differential efficacy of these therapies in the different genotypes. These co-clinical results identify predictive genetic biomarkers that should be validated by interrogating samples from patients enrolled on the concurrent clinical trial. These studies also highlight the rationale for synchronous co-clinical trials, not only to anticipate the results of ongoing human clinical trials, but also to generate clinically relevant hypotheses that can inform the analysis and design of human studies.     

一种问答式检索系统布尔查询生成方法

提出了一种基于简单语法分析的问答系统查询生成方法,利用对问题的词性标注,形成初始化布尔查询,根据查询结果文档集对查询迭代调整,最终产生合理的布尔查询. 通过TREC2004和TREC2005的QA TRACK数据集上的实验,表明该方法在没有增加很大复杂度（平均迭代2.5次）的情况下大大提高了平均查准率,覆盖率和重复率.     

铁路客车空调系统的自动调节

现行铁路客车空调系统的额定制冷量和采暖量是根据铁道部标准(TB1955—87)的客车采暖通风设计参数来计算的，考虑的是最不利的情况．为保证车内温度的稳定，建议根据外部温度的变化自动调节铁路客车空调系统，并提出了自动调节系统的设计思路．     

Single-nucleotide mutation rate increases close to insertions/deletions in eukaryotes

Mutation hotspots are commonly observed in genomic sequences and certain human disease loci, but general mechanisms for their formation remain elusive. Here we investigate the distribution of single-nucleotide changes around insertions/deletions (indels) in six independent genome comparisons, including primates, rodents, fruitfly, rice and yeast. In each of these genomic comparisons, nucleotide divergence (D) is substantially elevated surrounding indels and decreases monotonically to near-background levels over several hundred bases. D is significantly correlated with both size and abundance of nearby indels. In comparisons of closely related species, derived nucleotide substitutions surrounding indels occur in significantly greater numbers in the lineage containing the indel than in the one containing the ancestral (non-indel) allele; the same holds within species for single-nucleotide mutations surrounding polymorphic indels. We propose that heterozygosity for an indel is mutagenic to surrounding sequences, and use yeast genome-wide polymorphism data to estimate the increase in mutation rate. The consistency of these patterns within and between species suggests that indel-associated substitution is a general mutational mechanism.     

Synthetic chromosome arms function in yeast and generate phenotypic diversity by design

Recent advances in DNA synthesis technology have enabled the construction of novel genetic pathways and genomic elements, furthering our understanding of system-level phenomena. The ability to synthesize large segments of DNA allows the engineering of pathways and genomes according to arbitrary sets of design principles. Here we describe a synthetic yeast genome project, Sc2.0, and the first partially synthetic eukaryotic chromosomes, Saccharomyces cerevisiae chromosome synIXR, and semi-synVIL. We defined three design principles for a synthetic genome as follows: first, it should result in a (near) wild-type phenotype and fitness; second, it should lack destabilizing elements such as tRNA genes or transposons; and third, it should have genetic flexibility to facilitate future studies. The synthetic genome features several systemic modifications complying with the design principles, including an inducible evolution system, SCRaMbLE (synthetic chromosome rearrangement and modification by loxP-mediated evolution). We show the utility of SCRaMbLE as a novel method of combinatorial mutagenesis, capable of generating complex genotypes and a broad variety of phenotypes. When complete, the fully synthetic genome will allow massive restructuring of the yeast genome, and may open the door to a new type of combinatorial genetics based entirely on variations in gene content and copy number.     

粒子群优化算法在可供选择城市规划方案中的应用

运用改进的粒子群优化算法帮助规划者完成了城市用地规划方案.在算法中,增加了对惯性权重的选择,适应度的选取应用了各类用地单元的空间协调性,采用从左到右、从上到下顺序,依次计算每个用地单元的空间协调性的方法.由于用地单元之间的位置是离散的,所以算法中粒子速度采用了离散的粒子速度.利用此改进算法,在实验中能够快速地收敛到可行的规划方案,实验结果表明该算法是有效的.     

基于SOR-LS-SVM算法的公交站点客流量预测研究

公交站点客流量情况的及时准确预测对提供更可靠的公交服务和节省公交公司的运营成本是非常重要.首先对标准的LS-SVM算法进行了改进,得到一种新的SOR-LS-SVM学习算法.该算法不仅能减少计算的复杂性,提高学习速度;同时能提高函数估计的精确度.然后利用SOR-Ls-SVM算法对公交站点的客流量情况进行预测和模拟.实验结果表明改进的SOR-LS-SVM算法具有较高的预测精度,且实验取得了较好效果.     

香港行车隧道的两种营运模式

介绍了香港１１条行车隧道的两种不同营运模式（即ＢＯＴ模式和ＭＯＭ模式）；分析了这两种模式成功的因素。香港的成功经验，对内地基础设施的融资、建设和营运都极有借鉴价值。