Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications. Hundreds of papers have either proposed new feature attribution methods, discussed or harnessed these tools in their work. However, despite humans being the target end-users, most attribution methods were only evaluated on proxy automatic-evaluation metrics [52, 66, 68]. In this paper, we conduct the first, large-scale user study on 320 lay and 11 expert users to shed light on the effectiveness of state-of-the-art attribution methods in assisting humans in ImageNet classification, Stanford Dogs fine-grained classification, and these two tasks but when the input image contains adversarial perturbations. We found that, in overall, feature attribution is surprisingly not more effective than showing humans nearest training-set examples. On a hard task of fine-grained dog categorization, presenting attribution maps to humans does not help, but instead hurts the performance of human-AI teams compared to AI alone. Importantly, we found automatic attribution-map evaluation measures to correlate poorly with the actual human-AI team performance. Our findings encourage the community to rigorously test their methods on the downstream human-in-the-loop applications and to rethink the existing evaluation metrics.

The widespread utilization of AI systems has drawn attention to the potential impacts of such systems on society. Of particular concern are the consequences that prediction errors may have on real-world scenarios, and the trust humanity places in AI systems. It is necessary to understand how we can evaluate trustworthiness in AI and how individuals and entities alike can develop trustworthy AI systems. In this paper, we analyze each element of trustworthiness and provide a set of 20 guidelines that can be leveraged to ensure optimal AI functionality while taking into account the greater ethical, technical, and practical impacts to humanity. Moreover, the guidelines help ensure that trustworthiness is provable and can be demonstrated, they are implementation agnostic, and they can be applied to any AI system in any sector.

Internet-of-Things (IoT) and cyber-physical systems (CPSs) may consist of thousands of devices connected in a complex network topology. The diversity and complexity of these components present an enormous attack surface, allowing an adversary to exploit security vulnerabilities of different devices to execute a potent attack. Though significant efforts have been made to improve the security of individual devices in these systems, little attention has been paid to security at the aggregate level. In this article, we describe a comprehensive risk management system, called GRAVITAS, for IoT/CPS that can identify undiscovered attack vectors and optimize the placement of defenses within the system for optimal performance and cost. While existing risk management systems consider only known attacks, our model employs a machine learning approach to extrapolate undiscovered exploits, enabling us to identify attacks overlooked by manual penetration testing (pen-testing). The model is flexible enough to analyze practically any IoT/CPS and provide the system administrator with a concrete list of suggested defenses that can reduce system vulnerability at optimal cost. GRAVITAS can be employed by governments, companies, and system administrators to design secure IoT/CPS at scale, providing a quantitative measure of security and efficiency in a world where IoT/CPS devices will soon be ubiquitous.

Machine learning based data-driven technologies have shown impressive performances in a variety of application domains. Most enterprises use data from multiple sources to provide quality applications. The reliability of the external data sources raises concerns for the security of the machine learning techniques adopted. An attacker can tamper the training or test datasets to subvert the predictions of models generated by these techniques. Data poisoning is one such attack wherein the attacker tries to degrade the performance of a classifier by manipulating the training data. In this work, we focus on label contamination attack in which an attacker poisons the labels of data to compromise the functionality of the system. We develop Gradient-based Data Subversion strategies to achieve model degradation under the assumption that the attacker has limited-knowledge of the victim model. We exploit the gradients of a differentiable convex loss function (residual errors) with respect to the predicted label as a warm-start and formulate different strategies to find a set of data instances to contaminate. Further, we analyze the transferability of attacks and the susceptibility of binary classifiers. Our experiments show that the proposed approach outperforms the baselines and is computationally efficient.

Recently, the Centers for Disease Control and Prevention (CDC) has worked with other federal agencies to identify counties with increasing coronavirus disease 2019 (COVID-19) incidence (hotspots) and offers support to local health departments to limit the spread of the disease. Understanding the spatio-temporal dynamics of hotspot events is of great importance to support policy decisions and prevent large-scale outbreaks. This paper presents a spatio-temporal Bayesian framework for early detection of COVID-19 hotspots (at the county level) in the United States. We assume both the observed number of cases and hotspots depend on a class of latent random variables, which encode the underlying spatio-temporal dynamics of the transmission of COVID-19. Such latent variables follow a zero-mean Gaussian process, whose covariance is specified by a non-stationary kernel function. The most salient feature of our kernel function is that deep neural networks are introduced to enhance the model's representative power while still enjoying the interpretability of the kernel. We derive a sparse model and fit the model using a variational learning strategy to circumvent the computational intractability for large data sets. Our model demonstrates better interpretability and superior hotspot-detection performance compared to other baseline methods.

Over the last few months, I've noticed a significant reduction in the heady optimism of articles and opinion pieces in the press on the subject of artificial intelligence. In fact, many are now questioning the timescales given by manufacturers for the introduction of high-profile applications such as autonomous vehicles based on AI. If you are of a certain age, you might feel we've been here before… Unlike most other new technologies, artificial intelligence and robotics have gone through more than one'hype cycle' – overexcitement at the possibilities, with rapid development followed by a reality-check and a period of disappointment (the so-called AI Winter) before the next'breakthrough'. A new technology introduction, the invention of the airplane for example, normally works from the outset. The Wright brothers' first effort actually flew; not very far it's true, but it did achieve what its designers wanted and impressed the general public. Sure, visionaries saw the potential and I've no doubt there was much talk about a future of mass travel over large distances – early 20th century newspaper hype – long before it became a reality. Aircraft development has been an almost continuous process since then, with dreams becoming reality at a breathless pace culminating in the supersonic Concorde and vertical take-off/landing (VTOL) military jets. Communication is another example: we've gone from a basic voice telephone network in the 1950s to the Smartphone and the Internet in less than 50 years.

Apache Open Source Projects – Open source software has long been mistakenly considered inferior to proprietary software. But in the meantime many successful Apache Open Source projects could teach you better. They are often not only the big, whole solution, but can be used modularly for small problems and allow access to the know-how of many developers. Especially in the data science sector, many exciting projects based on the Python programming language have been established in recent years, which are built, maintained and continuously expanded by large, very active communities. In the meantime, these solutions have also been accepted in the business world.

Did you know India had an exclusive centre for robotics since 1986? The Centre for Artificial Intelligence and Robotics (CAIR) lab started with just three staff in a tiny office in Bengaluru. Today, the centre has more than 300 employees. CAIR is involved in research and development in AI, robotics, command and control, networking, information and communication security, along with the development of mission-critical products for battlefield communication and management systems. CAIR was appraised for Capability Maturity Model Integration (CMMI) Maturity Level 2 in 2014 and has ISO 9001:2015 certification.

Follow us on Facebook, Youtube, Twitter, and Instagram for the latest stories and updates daily. Well, it seems that a lot of people rates Artificial Intelligence (AI) higher than politicians' intelligence. A recent study conducted by researchers at Spanish-based IE University has found that most people across the globe would like to see lawmakers in their respective countries to be replaced with AI. As reported by CNBC, the study was conducted by IE University's Center for the Governance of Change whereby they held a survey on 2,769 people from 11 countries worldwide to gauge the views on the use of AI in governance. The survey asked the respondents how they would feel about reducing the number of Members of Parliaments (MPs) or lawmakers in their respective countries and instead giving those seats to an AI that would have access to all of their data.

How AI enhances security for IoT environments. Elon Musk's prediction that AI will outsmart humans in less than 5 years is a bold statement, predicting that machines will possess super-human qualities which help boost organizations' profits and goals. For many, these ideas belong in sci-fi fantasies rather than as a future fixture of working practices. In the broadest sense, there are no signs that AI comes close to human consciousness or sentience. When we talk about the power of AI, it's more helpful to consider the specific use cases and sectors where it will, and is having, a transformative effect – and there is one area in particular where AI has been seen to mimic the capabilities of complex human thought processes: cyber security.