The problem of sensitive information leaks became apparent in the recent infamous security breaches such as WikiLeaks, DNC emails, and Panama Papers. Detecting sensitive texts on the fly enhances the capabilities of security solutions' to monitor and protect critical information flow within the network. Automated text security classification is relatively a new research area, where sensitive texts are marked with labels as Secret, Confidential, and Unclassified with no human interaction. This paper examines the performance of deep learning networks in detecting the sensitivity levels of a given text. In deep text classification networks, regardless of text samples length, each paragraph/sentence is represented by a single sequence. We propose techniques to expand training set size, minimize the number of padding character in sequences, and lower inputs' dimensionality through learning from long paragraphs' segments as independent instances. Also, we introduce a wide variation of Convolution Neural Networks (CNN) network evaluated on four large sets of U. S. embassy's diplomatic cables. We are not aware of any paper that applied deep networks to sensitive text classification. Thus, we further evaluate our multi-sequencing technique and CNN network on well-researched non-sensitive text corpora. Our approach outperformed the state-of-the-art models on non-sensitive text datasets and competed with other traditional classifiers on the sensitive text datasets.
The U.S Government has been the target for cyber-attacks from all over the world. Just recently, former President Obama accused the Russian government of the leaking emails to Wikileaks and declared that the U.S. might be forced to respond. While Russia denied involvement, it is clear that the U.S. has to take some defensive measures to protect its data infrastructure. Insider threats have been the cause of other sensitive information leaks too, including the infamous Edward Snowden incident. Most of the recent leaks were in the form of text. Due to the nature of text data, security classifications are assigned manually. In an adversarial environment, insiders can leak texts through E-mail, printers, or any untrusted channels. The optimal defense is to automatically detect the unstructured text security class and enforce the appropriate protection mechanism without degrading services or daily tasks. Unfortunately, existing Data Leak Prevention (DLP) systems are not well suited for detecting unstructured texts. In this paper, we compare two recent approaches in the literature for text security classification, evaluating them on actual sensitive text data from the WikiLeaks dataset.
Words selection, writing style, stories cherry-picking, and many other factors play a role in framing news articles to fit the targeted audience or to align with the authors' beliefs. Hence, reporting facts alone is not evidence of bias-free journalism. Since the 2016 United States presidential elections, researchers focused on the media influence on the results of the elections. The news media attention has deviated from political parties to candidates. The news media shapes public perception of political candidates through news personalization. Despite its criticality, we are not aware of any studies which have examined news personalization from the machine learning or deep neural network perspective. In addition, some candidates accuse the media of favoritism which jeopardizes their chances of winning elections. Multiple methods were introduced to place news sources on one side of the political spectrum or the other, yet the mainstream media claims to be unbiased. Therefore, to avoid inaccurate assumptions, only news sources that have stated clearly their political affiliation are included in this research.
Many security related big data problems, including document, traffic, and system log analysis require analysis of unstructured text. Consider the task of analyzing company documents for secure storage. Some might be too sensitive to put on a public cloud and require private storage with associated backup overhead, some may safe on the cloud in encrypted form, and some may be sufficiently non-sensitive to be stored on the cloud in plain-text without encryption and decryption overhead. Being able to make such categorizations autonomously can significantly strengthen data security, organization, and storage efficiency. In this paper, we analyze several base machine learning based security risk assessment algorithms and develop techniques to improve upon standard algorithms. In particular, we examine labeling document sensitivity, labeling each paragraph in the document with one of three levels of security risk. For evaluation, we use real sensitive texts, from documents leaked by the WikiLeaks organization. We improve upon the base models using probabilistic topic modeling via Latent Dirichlet Analysis to identify samples from impure subtopics in the training set, prior to training a logistic regression classifier.
Individuals inadvertently allow emotions to drive their rational thoughts to predetermined conclusions regarding political partiality issues. Being well-informed about the subject in question mitigates emotions’ influence on humans’ cognitive reasoning, but it does not eliminate bias. By nature, humans tend to pick a side based on their beliefs, personal interests, and principles. Hence, journalists’ political leaning is defining factor in the rise of the polarity of political news coverage. Political bias studies usually align subjects or controversial topics of the news coverage to a particular ideology. However, politicians as private citizens or public officials are also consistently in the media spotlight throughout their careers. Detecting political polarity in the news coverage of politicians rather than topics adds a new perspective. Determining the best approach for detecting political polarity in the news relies on the news delivery method. Data types such as videos, audio, or text could summarize the news delivery methods. Text is one of the most prominent news delivery methods. Text pattern recognition and text classification are well-established research areas with applications in many multidisciplinary domains. We propose to use deep neural networks to detect ideology in news media articles that cover news related to political officials, namely, President Obama and Trump. Deep network models were able to identify the political ideology of articles with over 0.9 F1-Score. An evaluation and analysis of deep neural network performance in detecting political ideology of news articles, articles’ authors, and news sources are presented in the paper. Furthermore, this paper experiments on and provides a detailed analysis of newly reconstructed datasets.
The U.S Government has been the target for cyber-attacks from all over the world. Just recently, former President Obama accused the Russian government of the leaking emails to Wikileaks and declared that the U.S. might be forced to respond. While Russia denied involvement, it is clear that the U.S. has to take some defensive measures to protect its data infrastructure. Insider threats have been the cause of other sensitive information leaks too, including the infamous Edward Snowden incident. Most of the recent leaks were in the form of text. Due to the nature of text data, security classifications are assigned manually. In an adversarial environment, insiders can leak texts through E-mail, printers, or any untrusted channels. The optimal defense is to automatically detect the unstructured text security class and enforce the appropriate protection mechanism without degrading services or daily tasks. Unfortunately, existing Data Leak Prevention (DLP) systems are not well suited for detecting unstructured texts. In this paper, we compare two recent approaches in the literature for text security classification, evaluating them on actual sensitive text data from the WikiLeaks dataset.
The U.S Government has been the target for cyberattacks from all over the world. Just recently, former President Obama accused the Russian government of the leaking emails to Wikileaks and declared that the U.S. might be forced to respond. While Russia denied involvement, it is clear that the U.S. has to take some defensive measures to protect its data infrastructure. Insider threats have been the cause of other sensitive information leaks too, including the infamous Edward Snowden incident. Most of the recent leaks were in the form of text. Due to the nature of text data, security classifications are assigned manually. In an adversarial environment, insiders can leak texts through E-mail, printers, or any untrusted channels. The optimal defense is to automatically detect the unstructured text security class and enforce the appropriate protection mechanism without degrading services or daily tasks. Unfortunately, existing Data Leak Prevention (DLP) systems are not well suited for detecting unstructured texts. In this paper, we compare two recent approaches in the literature for text security classification, evaluating them on actual sensitive text data from the WikiLeaks dataset.
Non-partisanship is one of the qualities that con-tribute to journalistic objectivity. Factual reporting alone cannot combat political polarization in the news media. News framing, agenda settings, and priming are influence mechanisms that lead to political polarization, but they are hard to identify. This paper attempts to automate the detection of two political science concepts in news coverage: politician personalization and political ideology. Politicians’ news coverage personalization is a concept that encompasses one more of the influence mechanisms. Political ideologies are often associated with controversial topics such as abortion and health insurance. However, the paper prove that politicians’ personalization is related to the political ideology of the news articles. Constructing deep neural network models based on politicians’ personalization improved the performance of political ideology detection models. Also, deep networks models could predict news articles’ politician personalization with a high F1 score. Despite being trained on less data, personalized-based deep networks proved to be more capable of capturing the ideology of news articles than other non-personalized models. The dataset consists of two politician personalization labels, namely Obama and Trump, and two political ideology labels, Democrat and Republican. The results showed that politicians’ personalization and political polarization exist in news articles, authors, and media sources.
In recent years, traditional cybersecurity safeguards have proven ineffective against insider threats. Famous cases of sensitive information leaks caused by insiders, including the WikiLeaks release of diplomatic cables and the Edward Snowden incident, have greatly harmed the U.S. government's relationship with other governments and with its own citizens. Data Leak Prevention (DLP) is a solution for detecting and preventing information leaks from within an organization's network. However, state-of-art DLP detection models are only able to detect very limited types of sensitive information, and research in the field has been hindered due to the lack of available sensitive texts. Many researchers have focused on document-based detection with artificially labeled "confidential documents" for which security labels are assigned to the entire document, when in reality only a portion of the document is sensitive. This type of whole-document based security labeling increases the chances of preventing authorized users from accessing non-sensitive information within sensitive documents. In this paper, we introduce Automated Classification Enabled by Security Similarity (ACESS), a new and innovative detection model that penetrates the complexity of big text security classification/detection. To analyze the ACESS system, we constructed a novel dataset, containing formerly classified paragraphs from diplomatic cables made public by the WikiLeaks organization. To our knowledge this paper is the first to analyze a dataset that contains actual formerly sensitive information annotated at paragraph granularity.
'/%3e%3cuse xlink:href='%23a' transform='rotate(144 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(216 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(288 450 300)'/%3e%3c/svg%3e)