Label flipping attacks stand as a potent and practical threat to the integrity of machine learning models. While extensive research has focused on designing sophisticated attack and defense mechanisms, the underlying factors that govern a model's susceptibility remain underexplored. This paper reveals a critical phenomenon: the impact of label flipping attacks is highly differential across classes, strongly correlated with the intrinsic confusability between the source and target classes. We provide a rigorous theoretical analysis, demonstrating that a lower standardized separation between classes fundamentally leads to greater vulnerability. Grounded in this insight, we propose Confusability-Aware Contrastive Learning (CACL), a targeted defense that maximizes the feature-space separation for the most vulnerable class pairs. Extensive experiments validate the strong link between class separability and vulnerability, and show that CACL significantly mitigates the attack's impact while providing superior protection for the most susceptible classes. Our code is available at https://github.com/Pinlong-Zhao/Unequal-Vulnerability.

Logit perturbation refers to adding perturbation on logit, which has been shown to be capable of enhancing the robustness and generalization capabilities of deep neural networks in machine learning. However, studies on logit perturbation for multi-label learning are limited and they only consider the issue of class imbalance in the training data. Furthermore, the logit perturbation vectors in these methods are identical for negative classes containing different subclasses when multi-label learning is viewed as a multiple binary classification problem. This study investigates logit perturbation by exploring the characteristics of subclass-wise multi-label training data. First, the influence of the characteristics of multi-label training data on classification performance is analyzed in terms of the three data characteristics, namely, proportion, variance, and co-occurrence for each category (or subclass). Quantitative analyses reveal that variance differences among the subclasses in the negative class of a decomposed binary task also negatively impact the training performance, and if multiple characteristics affect simultaneously, the performance deterioration will be more severe. Second, theoretical analysis is performed for subclass-wise logit perturbation and a new subclass-wise logit perturbation method is proposed for multi-label learning. In our method, each class/subclass has a carefully designed perturbation implementation according to its proportion, variance, and co-occurrence. Finally, our proposed method is further explained through a regularization view. Extensive experiments demonstrate that our method consistently enhances the generalization performance of popular depth networks on multi-label benchmark datasets.

Large-scale, high-quality data are considered an essential factor for the successful application of many deep learning techniques. Meanwhile, numerous real-world deep learning tasks still have to contend with the lack of sufficient amounts of high-quality data. Additionally, issues such as model robustness, fairness, and trustworthiness are also closely related to training data. Consequently, a huge number of studies in the existing literature have focused on the data aspect in deep learning tasks. Some typical data optimization techniques include data augmentation, logit perturbation, sample weighting, and data condensation. These techniques usually come from different deep learning divisions and their theoretical inspirations or heuristic motivations may seem unrelated to each other. This study aims to organize a wide range of existing data optimization methodologies for deep learning from the previous literature, and makes the effort to construct a comprehensive taxonomy for them. The constructed taxonomy considers the diversity of split dimensions, and deep sub-taxonomies are constructed for each dimension. On the basis of the taxonomy, connections among the extensive data optimization methods for deep learning are built in terms of five aspects. We probe into rendering several promising and interesting future directions. The constructed taxonomy and the revealed connections will enlighten the better understanding of existing methods and the design of novel data optimization techniques. Furthermore, our aspiration for this survey is to promote data optimization as an independent subdivision of deep learning.

Weighting strategy prevails in machine learning. For example, a common approach in robust machine learning is to exert low weights on samples which are likely to be noisy or quite hard. This study summarizes another less-explored strategy, namely, perturbation. Various incarnations of perturbation have been utilized but it has not been explicitly revealed. Learning with perturbation is called perturbation learning and a systematic taxonomy is constructed for it in this study. In our taxonomy, learning with perturbation is divided on the basis of the perturbation targets, directions, inference manners, and granularity levels. Many existing learning algorithms including some classical ones can be understood with the constructed taxonomy. Alternatively, these algorithms share the same component, namely, perturbation in their procedures. Furthermore, a family of new learning algorithms can be obtained by varying existing learning algorithms with our taxonomy. Specifically, three concrete new learning algorithms are proposed for robust machine learning. Extensive experiments on image classification and text sentiment analysis verify the effectiveness of the three new algorithms. Learning with perturbation can also be used in other various learning scenarios, such as imbalanced learning, clustering, regression, and so on.

‘‘Easy/hard sample” is a popular parlance in machine learning. Learning difficulty of samples refers to how easy/hard a sample is during a learning procedure. An increasing need of measuring learning difficulty demonstrates its importance in machine learning (e.g., difficulty-based weighting learning strategies). Previous literature has proposed a number of learning difficulty measures. However, no comprehensive investigation for learning difficulty is available to date, resulting in that nearly all existing measures are heuristically defined without a rigorous theoretical foundation. This study attempts to conduct a pilot theoretical study for learning difficulty of samples. First, influential factors for learning difficulty are summarized. Under various situations conducted by summarized influential factors, correlations between learning difficulty and two vital criteria of machine learning, namely, generalization error and model complexity, are revealed. Second, a theoretical definition of learning difficulty is proposed on the basis of these two criteria. A practical measure of learning difficulty is proposed under the direction of the theoretical definition by importing the bias-variance trade-off theory. Subsequently, the rationality of theoretical definition and the practical measure are demonstrated, respectively, by analysis of several classical weighting methods and abundant experiments realized under all situations conducted by summarized influential factors. The mentioned weighting methods can be reasonably explained under the proposed theoretical definition and concerned propositions. The comparison in these experiments indicates that the proposed measure significantly outperforms the other measures throughout the experiments.

Imbalanced learning is a traditional yet hot research subarea in machine learning. There are a huge number of imbalanced learning methods proposed in previous literature. This study focuses on one of the most popular imbalanced learning strategies, namely, sample reweighting. The key issue is how to calculate the weights of samples in training. While most studies have relied on intuitive theoretical or heuristic inspirations, few studies have attempted to establish a comprehensive theoretical path for weight calculation. A recent study utilizes the effective number theory for random covering to construct a theoretical weighting framework. In this study, we conduct a deep analysis to theoretically reveal the defects in the existing effective number-based weighting theory. An enhanced effective number theory is established in which data scatter and covering offset among different categories are involved. Subsequently, a new weight calculation manner is proposed based on our new theory, yielding a new loss, namely, NENum loss. In this loss, weights are sample-wise instead of category-wise used in the existing effective number-based weighting. Furthermore, another novel loss that combines weighting and logit perturbation is designed inspired the limitations of the NENum loss. Meta learning is employed to optimize the concrete calculation based on sample-wise training dynamics. We conduct extensive experiments on benchmark imbalanced and standard data corpora. Results validate the reasonableness of our enhanced theory and the effectiveness of the proposed methodology.

Training deep learning models with unequal sample weights has been shown to enhance model performance in various typical learning scenarios, particularly for imbalanced and noisy-label learning scenarios. A deep understanding of the weighting mechanism facilitates the application of existing weighting strategies and illuminates the design of new weighting strategies for real learning tasks. Scholars have focused on exploring existing weighting methods. However, their studies mainly establish how the weights of samples influence the model training. Little headway is made on the weighting mechanism, i.e., which and how the characteristics of a sample influence its weight. In this study, we adopt a data-driven approach to investigate the weighting mechanism by utilizing an interpretable weighting framework. First, a wide range of sample characteristics is extracted from the classifier network during training. Second, the extracted characteristics are fed into a new neural regression tree (NRT), which is a tree model implemented by a neural network, and its output is the weight of the input sample. Third, the NRT is trained using meta-learning within the whole training process. Once the NRT is learned, the weighting mechanism, including the importance of weighting characteristics, prior modes, and specific weighting rules, can be obtained. We conduct extensive experiments on benchmark noisy and imbalanced data corpora. A package of weighting mechanisms is derived from the learned NRT. Furthermore, our proposed interpretable weighting framework exhibits superior performance in comparison to existing weighting strategies.

Current local density-based anomaly detection methods are limited in that the local density estimation and the neighborhood density estimation are not accurate enough for complex and large databases, and the detection performance depends on the size parameter of the neighborhood. In this paper, we propose a new kernel function to estimate samples' local densities and propose a weighted neighborhood density estimation to increase the robustness to changes in the neighborhood size. We further propose a local kernel regression estimator and a hierarchical strategy for combining information from the multiple scale neighborhoods to refine anomaly factors of samples. We apply our general anomaly detection method to image saliency detection by regarding salient pixels in objects as anomalies to the background regions. Local density estimation in the visual feature space and kernel-based saliency score propagation in the image enable the assignment of similar saliency values to homogenous object regions. Experimental results on several benchmark datasets demonstrate that our anomaly detection methods overall outperform several state-of-art anomaly detection methods. The effectiveness of our image saliency detection method is validated by comparison with several state-of-art saliency detection methods.

Nonlinear classifiers (i.e., kernel support vector machines (SVMs)) are effective for nonlinear data classification. However, nonlinear classifiers are usually prohibitively expensive when dealing with large nonlinear data. Ensembles of linear classifiers have been proposed to address this inefficiency, which is called the ensemble linear classifiers for nonlinear data problem. In this article, a new iterative learning approach is introduced that involves two steps at each iteration: partitioning the data into clusters according to Gaussian mixture models with local consistency and then training basic classifiers (i.e., linear SVMs) for each cluster. The two divide-and-conquer steps are combined into a graphical model. Meanwhile, with training, each classifier is regarded as a task; clustered multitask learning is employed to capture the relatedness among different tasks and avoid overfitting in each task. In addition, two novel extensions are introduced based on the proposed approach. First, the approach is extended for quality-aware web data classification. In this problem, the types of web data vary in terms of information quality. The ignorance of the variations of information quality of web data leads to poor classification models. The proposed approach can effectively integrate quality-aware factors into web data classification. Second, the approach is extended for listwise learning to rank to construct an ensemble of linear ranking models, whereas most existing listwise ranking methods construct a solely linear ranking model. Experimental results on benchmark datasets show that our approach outperforms state-of-the-art algorithms. During prediction for nonlinear classification, it also obtains comparable classification performance to kernel SVMs, with much higher efficiency.

Supplementary information has been proven to be particularly useful in many machine learning tasks. In ensemble learning for a set of trained base classifiers, there also exists abundant implicit supplementary information about the performance orderings for the trained base classifiers in previous literature. However, few classifier ensemble studies consider exploring and utilizing supplementary information. The current study proposes a new learning method for stack classifier ensembles by considering the implicit supplementary ordering information regarding a set of trained classifiers. First, a new metric learning algorithm for measuring the similarities between two arbitrary learning tasks is introduced. Second, supplementary ordering information for the trained classifiers of a given learning task is inferred based on the learned similarities and related performance results reported in the previous literature. Third, a set of ordered soft constraints is generated based on the supplementary ordering information, and achieving the optimal combination weights of the trained classifiers is formalized into a goal programming problem. The optimal combination weights are then obtained. Finally, the experimental results verify the effectiveness of the proposed new classifier ensemble method.

Learning to rank has received great attention in recent years as it plays a crucial role in many applications such as information retrieval and data mining. The existing concept of learning to rank assumes that each training instance is associated with a reliable label. However, in practice, this assumption does not necessarily hold true as it may be infeasible or remarkably expensive to obtain reliable labels for many learning to rank applications. Therefore, a feasible approach is to collect labels from crowds and then learn a ranking function from crowdsourcing labels. This study explores the listwise learning to rank with crowdsourcing labels obtained from multiple annotators, who may be unreliable. A new probabilistic ranking model is first proposed by combining two existing models. Subsequently, a ranking function is trained by proposing a maximum likelihood learning approach, which estimates ground-truth labels and annotator expertise, and trains the ranking function iteratively. In practical crowdsourcing machine learning, valuable side information (e.g., professional grades) about involved annotators is normally attainable. Therefore, this study also investigates learning to rank from crowd labels when side information on the expertise of involved annotators is available. In particular, three basic types of side information are investigated, and corresponding learning algorithms are consequently introduced. Further, the top-k learning to rank from crowdsourcing labels are explored to deal with long training ranking lists. The proposed algorithms are tested on both synthetic and real-world data. Results reveal that the maximum likelihood estimation approach significantly outperforms the average approach and existing crowdsourcing regression methods. The performances of the proposed algorithms are comparable to those of the learning model in consideration reliable labels. The results of the investigation further indicate that side information is helpful in inferring both ranking functions and expertise degrees of annotators.

Listwise learning to rank (LTR) is aimed at constructing a ranking model from listwise training data to order objects. In most existing studies, each training instance consists of a set of objects described by preference features. In a preference feature space for the objects in training, the structure of the objects is associated with the absolute preference degrees for the objects. The degrees significantly influence the ordering of the objects. Nevertheless, the structure of the training objects in their preference feature space has rarely been studied. In addition, most listwise LTR algorithms yield a single linear ranking model for all objects, but this ranking model may be insufficient to capture the underlying nonlinear ranking mechanism among all objects. This study proposes a divide-and-train method to learn a nonlinear ranking model from listwise training data. First, a rank-preserving clustering approach is used to infer the structure of objects in their preference feature space and all the objects in training data are divided into several clusters. Each cluster is assumed to correspond to a preference degree and an ordinal regression function is then learned. Second, considering that relations exist among the clusters, a multi-task listwise ranking approach is then employed to train linear ranking functions for all the clusters (or preference degrees) simultaneously. Our proposed method utilizes both the (relative) preferences among objects and the intrinsic structure of objects. Experimental results on benchmark data sets suggest that the proposed method outperforms state-oft-the-art listwise LTR algorithms.

Kernel SVM is prohibitively expensive when dealing with large nonlinear data. While ensembles of linear classifiers have been proposed to address this inefficiency, these methods are time-consuming or lack robustness. We propose an efficient classifier for nonlinear data using a new iterative learning algorithm, which partitions the data into clusters, and then trains a linear SVM for each cluster. These two steps are combined into a graphical model, with the parameters estimated efficiently using the EM algorithm. During training, clustered multi-task learning is used to capture the relatedness among the multiple linear SVMs and avoid overfitting. Experimental results on benchmark datasets show that our method outperforms state-of-the-art methods. During prediction, it also obtains comparable classification performance to kernel SVM, with much higher efficiency.

Mining the data source from a crowd of people has elicited increasing attention in recent years. In existing studies, multiple users are utilized, in which each user is generally required to annotate only one attribute for each sample. However, there are cases in numerous annotation tasks wherein despite of the presence of multiple users, each user should classify or rate multiple attributes for each sample. This situation is referred to as multi-user multi-attribute annotations in this paper. This work deals with the learning problem under multi-user multi-attribute annotations. A generative model is introduced to describe the human labeling process for multi-user multi-attribute annotations. Subsequently, a maximum likelihood approach is leveraged to infer the parameters in the generative model, namely, ground-truth labels, user expertise, and annotation difficulties. The classifiers for each attribute are also learned simultaneously. Furthermore, the correlations among attributes are taken into account during inference and learning using conditional random field. The experimental results reveal that compared with existing methods that ignore the characteristics of multi-user multi-attribute annotations, our approach can obtain better estimation of the ground truth labels, user experts, annotation difficulties as well as attribute classifiers.

Visual complexities (VisComs) of Web pages significantly affect user experience, and automatic evaluation can facilitate a large number of Web-based applications. The construction of a model for measuring the VisComs of Web pages requires the extraction of typical features and learning based on labeled Web pages. However, as far as the authors are aware, little headway has been made on measuring VisCom in Web mining and machine learning. The present article provides a new approach combining Web mining techniques and machine learning algorithms for measuring the VisComs of Web pages. The structure of a Web page is first analyzed, and the layout is then extracted. Using a Web page as a semistructured image, three classes of features are extracted to construct a feature vector. The feature vector is fed into a learned measuring function to calculate the VisCom of the page. In the proposed approach of the present study, the type of the measuring function and its learning depend on the quantification strategy for VisCom. Aside from using a category and a score to represent VisCom as existing work, this study presents a new strategy utilizing a distribution to quantify the VisCom of a Web page. Empirical evaluation suggests the effectiveness of the proposed approach in terms of both features and learning algorithms.

Current Web mining explores useful and valuable information (content) online for users. However, there is scant research on the overall visual aspect of Web pages, even though visual elements such as aesthetics significantly influence user experience. A beautiful and well-laid out Web page greatly facilitates users' accessing and enhances browsing experiences.We use "visual quality (VisQ)" to denote the aesthetics of Web pages. In this paper, a computational aesthetics approach is proposed to learn the evaluation model for the visual quality of Web pages. First, a Web page layout extraction algorithm (V-LBE) is introduced to partition a Web page into major layout blocks. Then, regarding a Web page as a semi-structured image, features (e.g., layout,visual complexity, colorfulness) known to significantly affect the visual quality of a Web page are extracted to construct a feature vector. We present a multi-cost-sensitive learning for visual quality classification and a multi-value regression for visual quality score assignment. Our experiments compare the extracted features and conclude that the Web page's layout visual features (LV) and text visual features (TV) are the primary affecting factors toward Web page's visual quality. The performance of the learned visual quality classifier is close to some persons'. The learned regression function also achieves promising results.

Many existing ranking-related information processing applications can be summarized into one theoretical problem called group ranking (GR). A simple average-ranking approach is usually applied to GR. Although the approach seems reasonable, no theoretical analysis about its intrinsic mechanism has been presented, increasing the difficulty of evaluating the ranking results. This study provides a formal analysis for GR. We first construct an objective function for the GR problem, and discover that each GR problem can be transformed into a rank aggregation problem whose objective function is proved to be equal to the objective function of GR. As a consequence, the average-ranking approach can be explained by two well-known rank aggregation techniques. We incorporate two other effective rank aggregation methods into the GR problem and obtain two new GR algorithms. We apply the GR algorithms into image retrieval to diversify the image search results returned by search engines. Experimental results show the effectiveness of the proposed GR algorithms.

This paper studies a new data mining problem called multi-instance outlier identification. This problem arises in tasks where each sample consists of many alternative feature vectors (instances) that describe it. This paper defines the multi-instance outliers and analyzes the basic types of multi-instance outliers. Two general identification approaches are proposed based on the state-of-the-art (single-instance) outlier detector LOF (local outlier factor). One approach utilizes the underlying mechanism of the kernel method and plunges the set distance into LOF to detect the multi-instance outliers. The other approach takes each instance's neighborhood into account. Based on the two approaches, four concrete multi-instance outlier detectors are then introduced. We conduct experiments over four synthetic data collections and three real-world data collections (two Musk data sets [22, 23] and a hard-drive inspection data set [24]). The experimental results show that the proposed multi-instance outlier detectors are effective while the algorithms that ignore the multi-instance settings perform poorly. Especially, the results on the two Musk sets are consistent with the multi-instance learning results; the results on the hard-drive inspection data set demonstrate that multi-instance outlier identification is promising for real applications.

The online communities are becoming so popular along with the development of the web but indexing and searching for the discussion data are big challenges to current applications. Topic detection was proposed to solve the problem but the accuracy is still not satisfactory, mainly because key elements are usually implicit or ambiguous which literal content comparison cannot handle. In this paper, we propose to improve the basic topic detection model by combining domain knowledge. The domain knowledge can be automatically extracted from a collection of external knowledge sources and applied to the content analysis of the threads. Two approaches, i.e. the LDA and the Concept Mapping, are proposed to implement the knowledge extraction and integration. Experimental results show that both approaches make the detection accuracy outperform the previous model. The LDA approach achieves better overall performance while the Concept Mapping is more suitable for dynamic knowledge sources.

A beautiful and well-laid out Web page greatly facilitates users' accessing and enhances browsing experiences. We use "visual quality (VQ)" to denote the aesthetics of Web pages. In this paper, a computational aesthetics approach is proposed to learn the evaluation model for the visual quality of Web pages. First, a Web page layout extraction algorithm (V-LBE) is introduced to partition a Web page into major layout blocks. Then, regarding a Web page as a semi-structured image, features known to significantly affect the visual quality of a Web page are extracted to construct a feature vector. The experimental results show the initial success of our approach. Potential applications include Web search and Web design.

Along with the explosive growth of the World Wide Web, an immense industry for the production and consumption of pornography has grown. Though the censorship and legal restraints on pornography are discriminating in different historical, cultural and national contexts, selling pornography to minors is not allowed in most cases. Detecting human skin tone is of utmost importance in pornography image filtering algorithms. In this paper, we propose two patch-based skin color detection algorithms: regular patch and irregular patch skin color detection algorithms. On the basis of skin detection, we extract 31-dimensional features from the input image, and these features are fed into a random forest classifier. Our algorithm has been incorporated into an adult-content filtering infrastructure, and is now in active use for preventing minors from accessing pornographic images via mobile phones.

Clustering ensembles combine different clustering solutions into a single robust and stable one. Most of existing methods become highly time-consuming when the data size turns to large. In this paper, we study the properties of the defined 'clustering fragment' and put forward a useful proposition. Solid proofs are presented with two widely used goodness measures for clustering ensembles. Finally, a new ensemble framework termed as fragment-based clustering ensembles is proposed. Theoretically, most of existing methods can be improved by adopting this framework. To evaluate the proposed framework, three new methods are introduced by bring three popular clustering ensemble methods into our framework. The experimental results on several public data sets show that the three introduced methods are greatly improved in computational complexity and also achieved better or similar accurate results than the original methods.

Filtering feature selection method (filtering method, for short) is a well-known feature selection strategy in pattern recognition and data mining. Filtering method outperforms other feature selection methods in many cases when the dimension of features is large. There are so many filtering methods proposed in previous work leading to the “selection trouble” that how to select an appropriate filtering method for a given text data set. Since to find the best filtering method is usually intractable in real application, this paper takes an alternative path. We propose a feature selection framework that fuses the results obtained by different filtering methods. In fact, deriving a better rank list from different rank lists, known as rank aggregation, is a hot topic studied in many disciplines. Based on the proposed framework and Markov chains rank aggregation techniques, in this paper, we present two new feature selection methods: FR-MC1 and FR-MC4. We also introduce a perturbation algorithm to alleviate the drawbacks of Markov chains rank aggregation techniques. Empirical evaluation on two public text data sets shows that the two new feature selection methods achieve better or comparable results than classical filtering methods, which also demonstrate the effectiveness of our framework.

Image spam is a new obfuscating method which spammers invented to more effectively bypass conventional text based spam filters. In this paper, we extract local invariant features of images and run a one-class SVM classifier which uses the pyramid match kernel as the kernel function to detect image spam. Experimental results demonstrate that our algorithm is effective for fighting image spam.

Judging whether a Web image contains people is useful in both pornographic image recognition and image filtering when searching for images of people. We proposed an approximate but rapid method to solve this problem. For a Web image, three types of probabilities are calculated from the image itself, the imagepsilas associated texts and the title of the Web page is located, respectively. Then a final probability representing the peoplepsilas existence is achieved by fusion of the three probabilistic values. Based on the probability of peoplepsilas existence, we proposed a two-layer framework for pornographic image recognition and a solution of image retrieval respectively. In the experiments conducted, our proposed framework and solution demonstrate good performances in the image recognition and filtering respectively.

The threaded discussion communities are one of the most common forms of online communities, which are becoming more and more popular among web users. Everyday a huge amount of new discussions are added to these communities, which are difficult to summarize and search. In this paper, we propose a topic detection and tracking (TDT) method for the discussion threads. Most existing TDT methods deal with the news stories, but the language used in discussion data are much more casual, oral and informal compared with news data. To solve this problem, we design several extensions to the basic TDT framework, focusing on the very nature of discussion data, including a thread/post activity validation step, a term pos-weighting strategy, and a two-level decision framework considering not only the content similarity but also the user activity information. Experiment results show that our pro-posed method greatly improves current TDT methods in real discussion community environment. The discussion data can be better organized for searching and visualization with the help of TDT.

Currently most link-related applications treat all links in the same web page to be identical. One link-related application usually requires one certain property of hyperlinks but actually not all links have this property or they have this property on different levels. Based on a study of how human users judge the links, the idea of the link function classification (LFC) is introduced in this paper. The link functions reflect the purpose that links are created by web page designers and the way they are used by viewers. Links in a certain function class imply one certain relationship between the adjacent pages, and thus they can be assumed to have similar properties. An algorithm is proposed to analyze the link functions based on both vision and structure features which simulates the reaction on the links of human users. Current applications can be enhanced by LFC with a more accurate modeling of the web graph. New mining methods can be also developed by making more and stronger assumptions on links within each function class due to the purer property set they share.

The World Wide Web has been growing rapidly in recent years, along with increasing needs for content-based Webpage filtering. But most existing filtering systems cannot easily satisfy the personalized filtering demands from different users at the same time. In this paper, a customizable instance-driven Webpage filtering strategy is proposed. For different users, different Webpage filters are produced by our system through mining the certain Webpage classes they focus on. A semi-supervised learning (SSL) approach is applied for obtaining a precise description of the Webpage class which a user wants to filter based on the small sized user instance set he or she provided. Subsequently, a feature selection step is performed and a Bayes classifier is created over the enlarged training set. Experimental results show the great stability and high performance of our proposed method, and it outperforms existing methods.

With the rapid development of the Internet, people benefit much from the sharing of information. Meanwhile, the WWW era is a double-edged sword which spreads harmful and erotic content widely. In this paper, a new statistical approach has been exploited by combining the results of two or more different classification methods using our filtering system. We first briefly introduce the classification of discrete texts, continuous texts and images separately, and then describe the specific way we have been exploring to merge the text and image classification result. Also there is a section illustrating our system framework. Finally we assess our method by demonstrating the experimental results and comparing it to some common-used filtering methods