The concept of traceability between artifacts is considered an enabler for software project success. This concept has received plenty of attention from the research community and is by many perceived to always be available in an industrial setting. In this industry-academia collaborative project, a team of researchers, supported by testing practitioners from a large telecommunication company, sought to investigate the partner company's issues related to software quality. However, it was soon identified that the fundamental traceability links between requirements and test cases were missing. This lack of traceability impeded the implementation of a solution to help the company deal with its quality issues. In this experience report, we discuss lessons learned about the practical value of creating and maintaining traceability links in complex industrial settings and provide a cautionary tale for researchers.
相關內容
Flawed TLS certificates are not uncommon on the Internet. While they signal a potential issue, in most cases they have benign causes (e.g., misconfiguration or even deliberate deployment). This adds fuzziness to the decision on whether to trust a connection or not. Little is known about perceptions of flawed certificates by IT professionals, even though their decisions impact high numbers of end users. Moreover, it is unclear how much the content of error messages and documentation influences these perceptions. To shed light on these issues, we observed 75 attendees of an industrial IT conference investigating different certificate validation errors. We also analyzed the influence of reworded error messages and redesigned documentation. We find that people working in IT have very nuanced opinions, with trust decisions being far from binary. The self-signed and the name-constrained certificates seem to be over-trusted (the latter also being poorly understood). We show that even small changes in existing error messages can positively influence resource use, comprehension, and trust assessment. At the end of the article, we summarize lessons learned from conducting usable security studies with IT professionals.
We propose application-layer coding schemes to recover lost data in delay-sensitive uplink (sensor-to-gateway) communications in the Internet of Things. Built on an approach that combines retransmissions and forward erasure correction, the proposed schemes' salient features include low computational complexity and the ability to exploit sporadic receiver feedback for efficient data recovery. Reduced complexity is achieved by keeping the number of coded transmissions as low as possible and by devising a mechanism to compute the optimal degree of a coded packet in O(1). Our major contributions are: (a) An enhancement to an existing scheme called windowed coding, whose complexity is greatly reduced and data recovery performance is improved by our proposed approach. (b) A technique that combines elements of windowed coding with a new feedback structure to further reduce the coding complexity and improve data recovery. (c) A coded forwarding scheme in which a relay node provides further resilience against packet loss by overhearing source-to-destination communications and making forwarding decisions based on overheard information.
We consider studies where multiple measures on an outcome variable are collected over time, but some subjects drop out before the end of follow up. Analyses of such data often proceed under either a 'last observation carried forward' or 'missing at random' assumption. We consider two alternative strategies for identification; the first is closely related to the difference-in-differences methodology in the causal inference literature. The second enables correction for violations of the parallel trend assumption, so long as one has access to a valid 'bespoke instrumental variable'. These are compared with existing approaches, first conceptually and then in an analysis of data from the Framingham Heart Study.
We bridge two research directions on graph neural networks (GNNs), by formalizing the relation between heterophily of node labels (i.e., connected nodes tend to have dissimilar labels) and the robustness of GNNs to adversarial attacks. Our theoretical and empirical analyses show that for homophilous graph data, impactful structural attacks always lead to reduced homophily, while for heterophilous graph data the change in the homophily level depends on the node degrees. These insights have practical implications for defending against attacks on real-world graphs: we deduce that separate aggregators for ego- and neighbor-embeddings, a design principle which has been identified to significantly improve prediction for heterophilous graph data, can also offer increased robustness to GNNs. Our comprehensive experiments show that GNNs merely adopting this design achieve improved empirical and certifiable robustness compared to the best-performing unvaccinated model. Additionally, combining this design with explicit defense mechanisms against adversarial attacks leads to an improved robustness with up to 18.33% performance increase under attacks compared to the best-performing vaccinated model.
Are intelligent machines really intelligent? Is the underlying philosophical concept of intelligence satisfactory for describing how the present systems work? Is understanding a necessary and sufficient condition for intelligence? If a machine could understand, should we attribute subjectivity to it? This paper addresses the problem of deciding whether the so-called "intelligent machines" are capable of understanding, instead of merely processing signs. It deals with the relationship between syntaxis and semantics. The main thesis concerns the inevitability of semantics for any discussion about the possibility of building conscious machines, condensed into the following two tenets: "If a machine is capable of understanding (in the strong sense), then it must be capable of combining rules and intuitions"; "If semantics cannot be reduced to syntaxis, then a machine cannot understand." Our conclusion states that it is not necessary to attribute understanding to a machine in order to explain its exhibited "intelligent" behavior; a merely syntactic and mechanistic approach to intelligence as a task-solving tool suffices to justify the range of operations that it can display in the current state of technological development.
Evaluation of researchers' output is vital for hiring committees and funding bodies, and it is usually measured via their scientific productivity, citations, or a combined metric such as h-index. Assessing young researchers is more critical because it takes a while to get citations and increment of h-index. Hence, predicting the h-index can help to discover the researchers' scientific impact. In addition, identifying the influential factors to predict the scientific impact is helpful for researchers seeking solutions to improve it. This study investigates the effect of author, paper and venue-specific features on the future h-index. For this purpose, we used machine learning methods to predict the h-index and feature analysis techniques to advance the understanding of feature impact. Utilizing the bibliometric data in Scopus, we defined and extracted two main groups of features. The first relates to prior scientific impact, and we name it 'prior impact-based features' and includes the number of publications, received citations, and h-index. The second group is 'non-impact-based features' and contains the features related to author, co-authorship, paper, and venue characteristics. We explored their importance in predicting h-index for researchers in three different career phases. Also, we examine the temporal dimension of predicting performance for different feature categories to find out which features are more reliable for long- and short-term prediction. We referred to the gender of the authors to examine the role of this author's characteristics in the prediction task. Our findings showed that gender has a very slight effect in predicting the h-index. We found that non-impact-based features are more robust predictors for younger scholars than seniors in the short term. Also, prior impact-based features lose their power to predict more than other features in the long-term.
While the amount of data created and stored continues to increase at striking rates, data protection and concealment increases its importance as a field of scientific study that requires more effort. It is essential to protect critical data at every stage while it is being stored and transferred. One cryptographic tool that is of interest and can be widely used in this medium is zero-knowledge proof systems. This cryptographic structure allows one party to securely guarantee the authenticity and accuracy of the data at hand, without leaking any confidential information during communication. The strength of zero-knowledge protocols is mostly based on a few hard-to-solve problems. There is a need to design more secure and efficient zero-knowledge systems. This need brings the necessity of determining suitable difficult problems to design secure zero-knowledge schemes. In this study, after a brief overview of zero-knowledge proof systems, the relationship of these structures to group-theoretic algorithmic problems and an annotated list of intractable algorithmic problems in group theory are given.
Recommender systems are the algorithms which select, filter, and personalize content across many of the worlds largest platforms and apps. As such, their positive and negative effects on individuals and on societies have been extensively theorized and studied. Our overarching question is how to ensure that recommender systems enact the values of the individuals and societies that they serve. Addressing this question in a principled fashion requires technical knowledge of recommender design and operation, and also critically depends on insights from diverse fields including social science, ethics, economics, psychology, policy and law. This paper is a multidisciplinary effort to synthesize theory and practice from different perspectives, with the goal of providing a shared language, articulating current design approaches, and identifying open problems. It is not a comprehensive survey of this large space, but a set of highlights identified by our diverse author cohort. We collect a set of values that seem most relevant to recommender systems operating across different domains, then examine them from the perspectives of current industry practice, measurement, product design, and policy approaches. Important open problems include multi-stakeholder processes for defining values and resolving trade-offs, better values-driven measurements, recommender controls that people use, non-behavioral algorithmic feedback, optimization for long-term outcomes, causal inference of recommender effects, academic-industry research collaborations, and interdisciplinary policy-making.
The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training. The reasons for this are manifold and range from time and cost constraints to ethical considerations. As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches, and eventually to increase the generalization capability of these models. Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-based models with existing knowledge. The identified approaches are structured according to the categories integration, extraction and conformity. Special attention is given to applications in the field of autonomous driving.
In the past few decades, artificial intelligence (AI) technology has experienced swift developments, changing everyone's daily life and profoundly altering the course of human society. The intention of developing AI is to benefit humans, by reducing human labor, bringing everyday convenience to human lives, and promoting social good. However, recent research and AI applications show that AI can cause unintentional harm to humans, such as making unreliable decisions in safety-critical scenarios or undermining fairness by inadvertently discriminating against one group. Thus, trustworthy AI has attracted immense attention recently, which requires careful consideration to avoid the adverse effects that AI may bring to humans, so that humans can fully trust and live in harmony with AI technologies. Recent years have witnessed a tremendous amount of research on trustworthy AI. In this survey, we present a comprehensive survey of trustworthy AI from a computational perspective, to help readers understand the latest technologies for achieving trustworthy AI. Trustworthy AI is a large and complex area, involving various dimensions. In this work, we focus on six of the most crucial dimensions in achieving trustworthy AI: (i) Safety & Robustness, (ii) Non-discrimination & Fairness, (iii) Explainability, (iv) Privacy, (v) Accountability & Auditability, and (vi) Environmental Well-Being. For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems. We also discuss the accordant and conflicting interactions among different dimensions and discuss potential aspects for trustworthy AI to investigate in the future.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191