The purpose of white-box implementation of a cipher is to protect the secret key of the cipher against a white-box attack, where the white-box adversary has full control over the execution environment and total visibility of internal details of the implementation. In 2015, Shi et al. proposed a lightweight white-box SMS4 implementation and claimed that the implementation is secure against known white-box attacks and known side-channel attacks. Based on the affine equivalence algorithm proposed by Biryukov et al., this paper presents an adjusted version of the affine equivalence algorithm and uses it as an attack against the white-box symmetric encryption algorithm proposed by Shi et al. With our attack, one byte of a round key of SMS4 can be recovered with worst time complexity of O(249) and the full cipher key of SMS4 can be recovered with time complexity of O(253)⁠. Moreover, we present a simple way to improve the white-box SMS4 implementation, which will make the time complexity of recovering one byte key increase to O(292)⁠.

In this paper, we propose a new variant of supervised Latent Dirichlet Allocation(sLDA): mixture of soft max sLDA, for image classification. Ensemble classification methods can combine multiple weak classifiers to construct a strong classifier. Inspired by the ensemble idea, we try to improve sLDA model using the idea. The mixture of soft max model is a probabilistic ensemble classification model, it can fit the training data and class label well. We embed the mixture of soft max model into LDA model under the framwork of sLDA, and construct an ensemble supervised topic model for image classification. Meanwhile, we derive an elegant parameters estimation algorithm based on variational EM method, and give a simple and efficient approximation method for classifying a new image. Finally, we demonstrate the effectiveness of our model by comparing with some existing approaches on two real world datasets. The results show that our model enhances classification accuracy by 7% on the 1600-image Label Me dataset and 9% on the 1791-image UIUC-Sport dataset.

The spatial relations representation modeling is a basic task of computer graphics comprehension, however, previous modeling is usually aimed at a certain kind of relations such as direction, topology and distance. The models are relatively independent and inconsistent with human's cognitive logic, thus building a unified spatial relations representation modeling based on different reference frames is required. In this paper we first discuss the importance of a reference frame for building a spatial relations representation modeling, then introduce the feasibility of histogram modeling for building a unified spatial relations representation modeling, and then describe the construction of spatial relations representation modeling based on visual area histogram under the deictic reference frame, in order to testify the correctness of the modeling, two typical examples are given, finally point out the advantages of this modeling, as well as the future work.

In this paper, we combined a group of local regression predictors using a novel unbiased and normalized linear ensemble model (UNLEM) for the design of multiple predictor systems. In the UNLEM, the optimization of the ensemble weights is formulated equivalently to a constrained quadratic programming problem, which can be solved with the Lagrange multiplier. In our simulation experiments of data regression, the proposed multiple predictor system is composed of three different types of local regression predictors, and the effectiveness evaluation of the UNLEM was carried out on eight synthetic and four benchmark data sets. Results of the UNLEM’s performance in terms of mean-squared error are significantly lower, in comparison with the popular simple average ensemble method. Moreover, the UNLEM is able to provide the regression predictions with a relatively higher normalized correlation coefficient than the results obtained with the simple average approach.

The theory of and a universal algorithm for matching and replacing templates with an arbitrary number of invariables (constants) and variables are outlined, and their remarkable advantages and attractive prospects are demonstrated for applications in machine translation. Moreover, it is indicated that the translation quality could be further improved and may theoretically achieve an accuracy of 94% when the universal algorithm is combined with some statistical methods.

Grammatical category disambiguation is an important field because of its basis in many applications, for example, parsing, machine translation, phrase recognition and so on. We put forward an improved second-order hidden Markov model that can capture more context information and develop one part-of-speech tagging system based on the model. In order to reduce the number of model parameters, word equivalence classes are used. The parameters of model are achieved by the Baum-Welch algorithm using untagged text. Results show that it improves the accuracy of tagging.