Search

In the past decade, the number of malware attacks have grown considerably and, more importantly, evolved. Many researchers have successfully integrated state-of-the-art machine learning techniques to combat this ever present and rising threat to information security. However, the lack of enough data to appropriately train these machine learning models is one big challenge that is still present. Generative modelling has proven to be very efficient at generating image-like synthesized data that can match the actual data distribution. In this paper, we aim to generate malware samples as opcode sequences and attempt to differentiate them from the real ones with the goal to build fake malware data that can be used to effectively train the machine learning models. We use and compare different Generative Adversarial Networks (GAN) algorithms and Hidden Markov Models (HMM) to generate such fake samples obtaining promising results.

This chapter describes the ways in which children and adolescents with written language disorders struggle with pragmatics. After defining written language disorders, the scant research available on this topic is summarized. The chapter focuses on the pragmatic deficits of students with oral language impairment often associated with literacy problems, students with reading disabilities including dyslexia, and students with writing disabilities. Specific subskills important for pragmatic language competence are discussed, such as perspective taking and presupposition, discourse regulation, and figurative language. Connections between social cognition, theory of mind, and pragmatic language abilities are identified. Pragmatic subskills’ presumed or documented relationships to reading and writing performance are detailed. Finally, an analytic comparison of texts written by students with writing challenges and one written by more accomplished peers are presented.

The impact of social media on the modern world is difficult to overstate. Virtually all companies and public figures have social media accounts on popular platforms such as Twitter and Facebook. In China, the micro-blogging service provider, Sina Weibo, is the most popular such service. To influence public opinion, Weibo trolls—the so-called Water Army—can be hired to post deceptive comments. In this chapter, we focus on troll detection via sentiment analysis and other user activity data on the Sina Weibo platform. We implement techniques for Chinese sentence segmentation, word embedding, and sentiment score calculation. In recent years, troll detection and sentiment analysis have been studied, but we are not aware of previous research that considers troll detection based on sentiment analysis. We employ the resulting techniques to develop and test a sentiment analysis approach for troll detection, based on a variety of machine learning strategies. Experimental results are generated and analyzed. A Chrome extension is presented that implements our proposed technique, which enables real-time troll detection when a user browses Sina Weibo.

In resource constrained devices, malware detection is typically based on offline analysis using emulation. An alternative to such emulation is malware analysis based on code that is executed on an actual device. In this research, we collect features from a corpus of Android malware using both emulation and on-phone instrumentation. We train machine learning models using the emulator-based features and we train models on features collected via instrumentation, and we compare the results obtained in these two cases. We obtain strong detection and classification results, and our results improve slightly on previous work. Consistent with previous work, we find that emulation fails for a significant percentage of malware applications. However, we also find that emulation fails to extract useful features from an even larger percentage of benign applications. We show that for applications that are amenable to emulation, malware detection and classification rates based on emulation are consistently within 1% of those obtained using more intrusive and costly on-phone analysis. We also show that emulation failures are easily explainable and appear to have little to do with malware writers employing anti-emulation techniques, contrary to claims made in previous research. Among other contributions, this work points to a lack of sophistication in Android malware.

In this chapter, we consider intrusion detection systems (IDS) in the context of an automotive controller area network (CAN), which is also known as the CAN bus. We provide a discussion of various IDS topics, including masquerade detection, and we include a selective survey of previous research involving IDS in a CAN network. We also discuss background topics and relevant practical issues, such as data collection on the CAN bus. Finally, we present experimental results where we have applied a variety of machine learning techniques to CAN data. We use both real and simulated data, and we conduct experiments to determine the status of a vehicle from its network packets, as well as to detect masquerading behavior on a CAN network.

This chapter provides an introduction in the simulation and design of integrated photonic microsystems. Using optical beamformers as case study, with applications in LiDAR or wireless optical telecommunication, basic building blocks for photonic integrated circuits (PICs) are introduced. Besides the discussion of their key performance metrics, their modeling and purpose in optical phased array sub-systems, the chapter extends to the simulation of their grouped performance assembled in a simple scanner.

Many applications are being developed that adopt a new emerging technology inspired by biological structures in nature to solve real-life problems; this approach involves implementations based on artificial neural networks (ANNs), deep learning, and other forms of artificial intelligence (AI). Autonomous driving is one area where these AI implementations can be applied; however, with it brings several uncertainties, including the safety and security of the implementation. The intent of this paper is to provide a new perspective in using cryptography as a methodology to implement safety in the hardware that incorporates AI technology in automotive while addressing at the same time classical problems due to physical and software failures.

Encrypted code is often present in some types of advanced malware, while such code virtually never appears in legitimate applications. Hence, the presence of encrypted code within an executable file could serve as a strong heuristic for malware detection. In this chapter, we consider the feasibility of detecting encrypted segments within an executable file using hidden Markov models.

A masquerade is a type of attack where an intruder attempts to avoid detection by impersonating an authorized user of a system. In this research, we consider the problem of masquerade detection on mobile devices. Specifically, we experiment with a variety of machine learning techniques to determine how accurately we can distinguish mobile users, based on various features. Here, our primary goal is to determine which techniques are most likely to be effective in a more comprehensive masquerade detection system.

Recent work has shown that a function call graph technique can perform well on some challenging malware detection problems. In this chapter, we compare this function call graph approach to elementary machine learning techniques that are trained on simpler features. We find that the machine learning techniques are generally more robust than the function call graphs, in the sense that the malware must be modified to a far greater extent before the machine learning techniques are significantly degraded. This work provides evidence that machine learning is likely to perform better than ad hoc approaches, particularly when faced with intelligent attackers who can attempt to exploit the inherent weaknesses in a given detection strategy.