Artificial Intelligence Security: Threats and Countermeasures

In recent years, with rapid technological advancement in both computing hardware and algorithm, Artificial Intelligence (AI) has demonstrated significant advantage over human being in a wide range of fields, such as image recognition, education, autonomous vehicles, finance, and medical diagnosis. However, AI-based systems are generally vulnerable to various security threats throughout the whole process, ranging from the initial data collection and preparation to the training, inference, and final deployment. In an AI-based system, the data collection and pre-processing phase are vulnerable to sensor spoofing attacks and scaling attacks, respectively, while the training and inference phases of the model are subject to poisoning attacks and adversarial attacks, respectively. To address these severe security threats against the AI-based systems, in this article, we review the challenges and recent research advances for security issues in AI, so as to depict an overall blueprint for AI security. More specifically, we first take the lifecycle of an AI-based system as a guide to introduce the security threats that emerge at each stage, which is followed by a detailed summary for corresponding countermeasures. Finally, some of the future challenges and opportunities for the security issues in AI will also be discussed.

Automated Annotations for AI Data and Model Transparency

The data and Artificial Intelligence revolution has had a massive impact on enterprises, governments, and society alike. It is fueled by two key factors. First, data have become increasingly abundant and are often available openly. Enterprises have more data than they can process. Governments are spearheading open data initiatives by setting up data portals such as data.gov and releasing large amounts of data to the public. Second, AI engineering development is becoming increasingly democratized. Open source frameworks have enabled even an individual developer to engineer sophisticated AI systems. But with such ease of use comes the potential for irresponsible use of data. Ensuring that AI systems adhere to a set of ethical principles is one of the major problems of our age. We believe that data and model transparency has a key role to play in mitigating the deleterious effects of AI systems. In this article, we describe a framework to synthesize ideas from various domains such as data transparency, data quality, data governance among others to tackle this problem. Specifically, we advocate an approach based on automated annotations (of both data and the AI model), which has a number of appealing properties. The annotations could be used by enterprises to get visibility of potential issues, prepare data transparency reports, create and ensure policy compliance, and evaluate the readiness of data for diverse downstream AI applications. We propose a model architecture and enumerate its key components that could achieve these requirements. Finally, we describe a number of interesting challenges and opportunities.

Challenges and Opportunities for Practical and Effective Dynamic Information Flow Tracking

Information flow tracking was proposed more than 40 years ago to address the limitations of access control mechanisms to guarantee the confidentiality and integrity of information flowing within a system, but has not yet been widely applied in practice for security solutions. Here, we survey and systematize literature on dynamic information flow tracking (DIFT) to discover challenges and opportunities to make it practical and effective for security solutions. We focus on common knowledge in the literature and lingering research gaps from two dimensions— (i) the layer of abstraction where DIFT is implemented (software, software/hardware, or hardware) and (ii) the security goal (confidentiality and/or integrity). We observe that two major limitations hinder the practical application of DIFT for on-the-fly security applications: (i) high implementation overhead and (ii) incomplete information flow tracking (low accuracy). We posit, after review of the literature, that addressing these major impedances via hardware parallelism can potentially unleash DIFT’s great potential for systems security, as it can allow security policies to be implemented in a built-in and standardized fashion. Furthermore, we provide recommendations for the next generation of practical and efficient DIFT systems with an eye towards hardware-supported implementations.

A Data-Driven Analysis on Sustainable Energy Security

This study provides a data-driven analysis that illustrates a clear renewable energy depiction in sustainable energy security and unveils the regional issues due to the literature solely occupies energy security concept in the descriptions view, and renewable energy differences related to regions are rarely discussed. A hybrid method is proposed to valid those indicators and shows the trend of future studies. This study enriches the challenges and opportunities by contributing to understand the fundamental knowledge of renewable energy in sustainable energy security frontier, conveyance directions for future study and investigation, and assessment on global renewable energy position and regional disparities. There are valid 19 indicators, in which energy demand, energy policy, renewable resources, smart grid, and uncertainty representing the future trends. World regional comparison includes 115 countries/territories and categorized into five geographical regions. The result shows that those indicators have addressed different issues in the world regional comparison.

Gotta CAPTCHA ’Em All: A Survey of 20 Years of the Human-or-computer Dilemma

A recent study has found that malicious bots generated nearly a quarter of overall website traffic in 2019 [102]. These malicious bots perform activities such as price and content scraping, account creation and takeover, credit card fraud, denial of service, and so on. Thus, they represent a serious threat to all businesses in general, but are especially troublesome for e-commerce, travel, and financial services. One of the most common defense mechanisms against bots abusing online services is the introduction of Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA), so it is extremely important to understand which CAPTCHA schemes have been designed and their actual effectiveness against the ever-evolving bots. To this end, this work provides an overview of the current state-of-the-art in the field of CAPTCHA schemes and defines a new classification that includes all the emerging schemes. In addition, for each identified CAPTCHA category, the most successful attack methods are summarized by also describing how CAPTCHA schemes evolved to resist bot attacks, and discussing the limitations of different CAPTCHA schemes from the security, usability, and compatibility point of view. Finally, an assessment of the open issues, challenges, and opportunities for further study is provided, paving the road toward the design of the next-generation secure and user-friendly CAPTCHA schemes.

A Tale of Two Cities: Software Developers Working from Home during the COVID-19 Pandemic

The COVID-19 pandemic has shaken the world to its core and has provoked an overnight exodus of developers who normally worked in an office setting to working from home. The magnitude of this shift and the factors that have accompanied this new unplanned work setting go beyond what the software engineering community has previously understood to be remote work. To find out how developers and their productivity were affected, we distributed two surveys (with a combined total of 3,634 responses that answered all required questions) weeks apart to understand the presence and prevalence of the benefits, challenges, and opportunities to improve this special circumstance of remote work. From our thematic qualitative analysis and statistical quantitative analysis, we find that there is a dichotomy of developer experiences influenced by many different factors (that for some are a benefit, while for others a challenge). For example, a benefit for some was being close to family members but for others having family members share their working space and interrupting their focus, was a challenge. Our surveys led to powerful narratives from respondents and revealed the scale at which these experiences exist to provide insights as to how the future of (pandemic) remote work can evolve.

AutoML to Date and Beyond: Challenges and Opportunities

As big data becomes ubiquitous across domains, and more and more stakeholders aspire to make the most of their data, demand for machine learning tools has spurred researchers to explore the possibilities of automated machine learning (AutoML). AutoML tools aim to make machine learning accessible for non-machine learning experts (domain experts), to improve the efficiency of machine learning, and to accelerate machine learning research. But although automation and efficiency are among AutoML’s main selling points, the process still requires human involvement at a number of vital steps, including understanding the attributes of domain-specific data, defining prediction problems, creating a suitable training dataset, and selecting a promising machine learning technique. These steps often require a prolonged back-and-forth that makes this process inefficient for domain experts and data scientists alike and keeps so-called AutoML systems from being truly automatic. In this review article, we introduce a new classification system for AutoML systems, using a seven-tiered schematic to distinguish these systems based on their level of autonomy. We begin by describing what an end-to-end machine learning pipeline actually looks like, and which subtasks of the machine learning pipeline have been automated so far. We highlight those subtasks that are still done manually—generally by a data scientist—and explain how this limits domain experts’ access to machine learning. Next, we introduce our novel level-based taxonomy for AutoML systems and define each level according to the scope of automation support provided. Finally, we lay out a roadmap for the future, pinpointing the research required to further automate the end-to-end machine learning pipeline and discussing important challenges that stand in the way of this ambitious goal.