Search

With the increasing sophistication of Advanced Persistent Threats (APTs), the demand for effective detection and mitigation strategies and methods has escalated. Program execution leaves traces in the system audit log, which can be analyzed to detect malicious activities. However, collecting and analyzing large volumes of audit logs over extended periods is challenging, further compounded by insufficient labeling that hinders their usability. Addressing these challenges, this paper introduces SAGA (Synthetic Audit log Generation for APT campaigns), a novel approach for generating find-grained labeled synthetic audit logs that mimic real-world system logs while embedding stealthy APT attacks. SAGA generates configurable audit logs for arbitrary duration, blending benign logs from normal operations with malicious logs based on the definitions the MITRE ATT\&CK framework. Malicious audit logs follow an APT lifecycle, incorporating various attack techniques at each stage. These synthetic logs can serve as benchmark datasets for training machine learning models and assessing diverse APT detection methods. To demonstrate the usefulness of synthetic audit logs, we ran established baselines of event-based technique hunting and APT campaign detection using various synthetic audit logs. In addition, we show that a deep learning model trained on synthetic audit logs can detect previously unseen techniques within audit logs.

As Advanced Persistent Threats (APTs) grow increasingly sophisticated, the demand for effective detection methods has intensified. This study addresses the challenge of identifying APT campaign attacks through system event logs. A cascading approach, name SFM, combines Technique hunting and APT campaign attribution. Our approach assumes that real-world system event logs contain a vast majority of normal events interspersed with few suspiciously malicious ones and that these logs are annotated with Techniques of MITRE ATT&CK framework for attack pattern recognition. Then, we attribute APT campaign attacks by aligning detected Techniques with known attack sequences to determine the most likely APT campaign. Evaluations on five real-world APT campaigns indicate that the proposed approach demonstrates reliable performance.

As technology grows faster, the news spreads through social media. In order to attract more readers and acquire additional profit, some news agencies reproduce massive news in a more appealing manner. Therefore, it is essential to accurately predict whether a news article is from official news agencies. This work develops a headline classification based on Convoluted Neural Network to determine credibility of a news article. The model primarily focuses on investigating key factors from headlines. These factors include word segmentation, part-of-speech tags, and sentiment features. With integrating these features into the proposed classification model, the demonstrated evaluation achieves 93.99% for accuracy., Comment: Accepted by The 26th Taiwan Academic Network Conference (TANET) 2020

Deep learning has been used in the research of malware analysis. Most classification methods use either static analysis features or dynamic analysis features for malware family classification, and rarely combine them as classification features and also no extra effort is spent integrating the two types of features. In this paper, we combine static and dynamic analysis features with deep neural networks for Windows malware classification. We develop several methods to generate static and dynamic analysis features to classify malware in different ways. Given these features, we conduct experiments with composite neural network, showing that the proposed approach performs best with an accuracy of 83.17% on a total of 80 malware families with 4519 malware samples. Additionally, we show that using integrated features for malware family classification outperforms using static features or dynamic features alone. We show how static and dynamic features complement each other for malware classification.

Malware analysis has been extensively investigated as the number and types of malware has increased dramatically. However, most previous studies use end-to-end systems to detect whether a sample is malicious, or to identify its malware family. In this paper, we propose a neural network framework composed of an embedder, an encoder, and a filter to learn malware representations from characteristic execution sequences for malware family classification. The embedder uses BERT and Sent2Vec, state-of-the-art embedding modules, to capture relations within a single API call and among consecutive API calls in an execution trace. The encoder comprises gated recurrent units (GRU) to preserve the ordinal position of API calls and a self-attention mechanism for comparing intra-relations among different positions of API calls. The filter identifies representative API calls to build the malware representation. We conduct broad experiments to determine the influence of individual framework components. The results show that the proposed framework outperforms the baselines, and also demonstrates that considering Sent2Vec to learn complete API call embeddings and GRU to explicitly preserve ordinal information yields more information and thus significant improvements. Also, the proposed approach effectively classifies new malicious execution traces on the basis of similarities with previously collected families., Comment: Incorrect experiment data

This work investigates the framework and performance issues of the composite neural network, which is composed of a collection of pre-trained and non-instantiated neural network models connected as a rooted directed acyclic graph for solving complicated applications. A pre-trained neural network model is generally well trained, targeted to approximate a specific function. Despite a general belief that a composite neural network may perform better than a single component, the overall performance characteristics are not clear. In this work, we construct the framework of a composite network, and prove that a composite neural network performs better than any of its pre-trained components with a high probability bound. In addition, if an extra pre-trained component is added to a composite network, with high probability, the overall performance will not be degraded. In the study, we explore a complicated application -- PM2.5 prediction -- to illustrate the correctness of the proposed composite network theory. In the empirical evaluations of PM2.5 prediction, the constructed composite neural network models support the proposed theory and perform better than other machine learning models, demonstrate the advantages of the proposed framework., Comment: This version is accepted by IEEE TKDE

This work theoretically investigates the performance of a composite neural network. A composite neural network is a rooted directed acyclic graph combining a set of pre-trained and non-instantiated neural network models, where a pre-trained neural network model is well-crafted for a specific task and targeted to approximate a specific function with instantiated weights. The advantages of adopting such a pre-trained model in a composite neural network are two folds. One is to benefit from other's intelligence and diligence, and the other is saving the efforts in data preparation and resources and time in training. However, the overall performance of composite neural network is still not clear. In this work, we prove that a composite neural network, with high probability, performs better than any of its pre-trained components under certain assumptions. In addition, if an extra pre-trained component is added to a composite network, with high probability the overall performance will be improved. In the empirical evaluations, distinctively different applications support the above findings.

This paper proposes a novel and statistical method of ability estimation based on acquisition distribution for a personalized computer aided question generation. This method captures the learning outcomes over time and provides a flexible measurement based on the acquisition distributions instead of precalibration. Compared to the previous studies, the proposed method is robust, especially when an ability of a student is unknown. The results from the empirical data show that the estimated abilities match the actual abilities of learners, and the pretest and post-test of the experimental group show significant improvement. These results suggest that this method can serves as the ability estimation for a personalized computer-aided testing environment.

In the last several years, the field of computer assisted language learning has increasingly focused on computer aided question generation. However, this approach often provides test takers with an exhaustive amount of questions that are not designed for any specific testing purpose. In this work, we present a personalized computer aided question generation that generates multiple choice questions at various difficulty levels and types, including vocabulary, grammar and reading comprehension. In order to improve the weaknesses of test takers, it selects questions depending on an estimated proficiency level and unclear concepts behind incorrect responses. This results show that the students with the personalized automatic quiz generation corrected their mistakes more frequently than ones only with computer aided question generation. Moreover, students demonstrated the most progress between the pretest and post test and correctly answered more difficult questions. Finally, we investigated the personalizing strategy and found that a student could make a significant progress if the proposed system offered the vocabulary questions at the same level of his or her proficiency level, and if the grammar and reading comprehension questions were at a level lower than his or her proficiency level.

In recent years, the number of people studying English as a second language (ESL) has surpassed the number of native speakers. Recent work have demonstrated the success of providing personalized content based on reading difficulty, such as information retrieval and summarization. However, almost all prior studies of reading difficulty are designed for native speakers, rather than non-native readers. In this study, we investigate various features for ESL readers, by conducting a linear regression to estimate the reading level of English language sources. This estimation is based not only on the complexity of lexical and syntactic features, but also several novel concepts, including the age of word and grammar acquisition from several sources, word sense from WordNet, and the implicit relation between sentences. By employing Bayesian Information Criterion (BIC) to select the optimal model, we find that the combination of the number of words, the age of word acquisition and the height of the parsing tree generate better results than alternative competing models. Thus, our results show that proposed second language reading difficulty estimation outperforms other first language reading difficulty estimations.

Multi-output is essential in machine learning that it might suffer from nonconforming residual distributions, i.e., the multi-output residual distributions are not conforming to the expected distribution. In this paper, we propose "Wrapped Loss Function" to wrap the original loss function to alleviate the problem. This wrapped loss function acts just like the original loss function that its gradient can be used for backpropagation optimization. Empirical evaluations show wrapped loss function has advanced properties of faster convergence, better accuracy, and improving imbalanced data., Comment: 10 pages

The proliferation of malwares have been attributed to the alternations of a handful of original malware source codes. The malwares alternated from the same origin share some intrinsic behaviors and form a malware family. Expediently, identifying its malware family when a malware is first seen on the Internet can provide useful clues to mitigate the threat. In this paper, a malware profiler (VMP) is proposed to profile the execution behaviors of a malware by leveraging virtual machine introspection (VMI) technique. The VMP inserts plug-ins inside the virtual machine monitor (VMM) to record the invoked API calls with their input parameters and return values as the profile of malware. In this paper, a popular similarity measurement Jaccard distance and a phylogenetic tree construction method are adopted to discover malware families. The studies of malware profiles show the malwares from a malware family are very similar to each others and distinct from other malware families as well as benign software. This paper also examines VMP against existing anti-malware detection engines and some well-known malware grouping methods to compare the goodness in their malware family constructions. A peer voting approach is proposed and the results show VMP is better than almost all of the compared anti-malware engines, and compatible with the fine tuned text-mining approach and high order N-gram approaches. We also establish a malware profiling website based on VMP for malware research., Comment: 13 pages, 9 figures, 5 tables