ID 原文 译文
45176 该方法根据信息泄露模型的特征对聚类期望最大值（EM）算法进行改造， The clustering EM algorithm was modified according to the characteristics of information leakage model in the method.
45177 使改造后的聚类方法能够较为准确地拟合出泄露信息的概率模型，在未知密钥的情况下，即可确定信息泄露的位置。 The modified clustering methods accurately fitted the leaked information probability model in the case of unknown key, the location of information leakage could be determined.
45178 该方法通过建模进行模板匹配， Then implemented template matching.
45179 消除了传统模板攻击对已知密钥建模等前置条件的依赖，从而扩大了模板攻击的应用范围。 The proposed method eliminates the dependence of traditional template attacks on per-conditions and expand the application scenario of template attack.
45180 目前，Android 平台重打包应用检测方法依赖于专家定义特征，不但耗时耗力，而且其特征容易被攻击者猜测。 The state-of-art techniques in Android repackaging detection relied on experts to define features, however,these techniques were not only labor-intensive and time-consuming, but also the features were easily guessed by attackers.
45181 另外，现有的应用特征表示难以在常见的重打包应用类型检测中取得良好的效果，导致在实际检测中存在漏报率较高的现象。 Moreover, the feature representation of applications which defined by experts cannot perform well to the common types of repackaging detection, which caused a high false negative rate in the real detection scenario.
45182 针对以上 2 个问题，提出了一种基于深度学习的重打包应用检测方法，自动地学习程序的语义特征表示。 A deep learning-based repackaged applications detection approach was proposed to learn the program semantic features automatically for ad-dressing the above two issues.
45183 首先，对应用程序进行控制流与数据流分析形成序列特征表示； Firstly, control and data flow analysis were taken for applications to form a sequence feature representation.
45184 然后，根据词向量嵌入模型将序列特征转变为特征向量表示，输入孪生网络长短期记忆（LSTM, long short term memory）网络中进行程序特征自学习； Secondly, the sequence features were transformed into vectors based on word embedding model to train a Siamese LSTM network for automatically program feature learning.
45185 最后，将学习到的程序特征通过相似性度量实现重打包应用的检测。 Finally, repackaged applications were detected based on the similarity measurement of learned program features.