Recent natural language processing (NLP) techniques have accomplished high performance on benchmark data sets, primarily due to the significant improvement in the performance of deep learning. The advances in the research community have led to great enhancements in state-of-the-art production systems for NLP tasks, such as virtual assistants, speech recognition, and sentiment analysis. However, such NLP systems still often fail when tested with adversarial attacks. The initial lack of robustness exposed troubling gaps in current models' language understanding capabilities, creating problems when NLP systems are deployed in real life. In this paper, we present a structured overview of NLP robustness research by summarizing the literature in a systemic way across various dimensions. We then take a deepdive into the various dimensions of robustness, across techniques, metrics, embedding, and benchmarks. Finally, we argue that robustness should be multi-dimensional, provide insights into current research, identify gaps in the literature to suggest directions worth pursuing to address these gaps INDEX TERMS Natural Language Processing; Adversarial Attacks; Robustness.
Cyber security is becoming the cornerstone of national security policies in many countries around the world as it is an interest to many stakeholders, including utilities, regulators, energy markets, government entities, and even those that wish to exploit the cyber infrastructure. Cyber warfare is quickly becoming the method of warfare and the tool of military strategists. Additionally, it is has become a tool for governments to aid or exploit for their own personal benefits. For cyber terrorists there has been an overwhelmingly abundance of new tools and technologies available that have allowed criminal acts to occur virtually anywhere in the world. This chapter discusses emerging laws, policies, processes, and tools that are changing the landscape of cyber security. This chapter provides an overview of the research to follow which will provide an in depth review of mobile security, mobile networks, insider threats, and various special topics in cyber security.
Recent natural language processing (NLP) techniques have accomplished high performance on benchmark datasets, primarily due to the significant improvement in the performance of deep learning. The advances in the research community have led to great enhancements in state-of-the-art production systems for NLP tasks, such as virtual assistants, speech recognition, and sentiment analysis. However, such NLP systems still often fail when tested with adversarial attacks. The initial lack of robustness exposed troubling gaps in current models' language understanding capabilities, creating problems when NLP systems are deployed in real life. In this paper, we present a structured overview of NLP robustness research by summarizing the literature in a systemic way across various dimensions. We then take a deep-dive into the various dimensions of robustness, across techniques, metrics, embeddings, and benchmarks. Finally, we argue that robustness should be multi-dimensional, provide insights into current research, identify gaps in the literature to suggest directions worth pursuing to address these gaps.
Smartphones are becoming enriched with confidential information due to their powerful computational capabilities and attractive communications features. The Android smartphone is one of the most widely used platforms by businesses and users alike. This is partially because Android smartphones use the free, open-source Linux as the underlying operating system, which allows development of applications by any software developer. This research study aims to explore security risks associated with the use of Android smartphones and the sensitive information they contain; the researcher devised a survey questionnaire to investigate and further understand security threats targeting Android smartphones. The survey also intended to study the scope of malware attacks targeting Android phones and the effectiveness of existing defense measures. The study surveyed the average Android users as the target population to understand how they perceive security and what security controls they use to protect their smartphones.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.