Search

Function-as-a-Service (FaaS) has raised a growing interest in how to "tame" serverless to enable domain-specific use cases such as data-intensive applications and machine learning (ML), to name a few. Recently, several systems have been implemented for training ML models. Certainly, these research articles are significant steps in the correct direction. However, they do not completely answer the nagging question of when serverless ML training can be more cost-effective compared to traditional "serverful" computing. To help in this task, we propose MLLess, a FaaS-based ML training prototype built atop IBM Cloud Functions. To boost cost-efficiency, MLLess implements two key optimizations: a significance filter and a scale-in auto-tuner, and leverages them to specialize model training to the FaaS model. Our results certify that MLLess can be 15X faster than serverful ML systems [24] at a lower cost for ML models (such as sparse logistic regression and matrix factorization) that exhibit fast convergence.

Despite the central importance of research papers to scientific progress, they can be difficult to read. Comprehension is often stymied when the information needed to understand a passage resides somewhere else: in another section, or in another paper. In this work, we envision how interfaces can bring definitions of technical terms and symbols to readers when and where they need them most. We introduce ScholarPhi, an augmented reading interface with four novel features: (1) tooltips that surface position-sensitive definitions from elsewhere in a paper, (2) a filter over the paper that "declutters" it to reveal how the term or symbol is used across the paper, (3) automatic equation diagrams that expose multiple definitions in parallel, and (4) an automatically generated glossary of important terms and symbols. A usability study showed that the tool helps researchers of all experience levels read papers. Furthermore, researchers were eager to have ScholarPhi's definitions available to support their everyday reading., 18 pages, 17 figures, 2 tables. To appear at the 2021 ACM CHI Conference on Human Factors in Computing Systems. For associated video, see https://youtu.be/yYcQf-Yq8B0. v2 changes: expanded discussion of design process and implementation; improved figure design. v3 changes: fixed typo in cell of Table 2; updated HEDDEx and Schwarz-Hearst accuracy in Section 5.3

Automatically detecting the positions of key-points (e.g., facial key-points or finger key-points) in an image is an essential problem in many applications, such as driver's gaze detection and drowsiness detection in automated driving systems. With the recent advances of Deep Neural Networks (DNNs), Key-Points detection DNNs (KP-DNNs) have been increasingly employed for that purpose. Nevertheless, KP-DNN testing and validation have remained a challenging problem because KP-DNNs predict many independent key-points at the same time -- where each individual key-point may be critical in the targeted application -- and images can vary a great deal according to many factors. In this paper, we present an approach to automatically generate test data for KP-DNNs using many-objective search. In our experiments, focused on facial key-points detection DNNs developed for an industrial automotive application, we show that our approach can generate test suites to severely mispredict, on average, more than 93% of all key-points. In comparison, random search-based test data generation can only severely mispredict 41% of them. Many of these mispredictions, however, are not avoidable and should not therefore be considered failures. We also empirically compare state-of-the-art, many-objective search algorithms and their variants, tailored for test suite generation. Furthermore, we investigate and demonstrate how to learn specific conditions, based on image characteristics (e.g., head posture and skin color), that lead to severe mispredictions. Such conditions serve as a basis for risk analysis or DNN retraining., to appear in ISSTA 2021

FT-Matrix is a typical vector-SIMD architecture that refines the cooperation between scalar and vector units. This approach is widely used in digital signal processing, high-performance computing, and artificial intelligence, among other fields. FT-Matrix currently adopts C vector extension as the main programming model, improving the utilization efficiency of SIMD by providing explicit vector extension API. Moreover, it is difficult to efficiently transplant parallel programs (OpenCL, CUDA) adopted by users. This paper proposes an automatic mapping and code optimization method for OpenCL kernels on FT-Matrix architecture. The proposed approach solves these challenges by means of work item coalescing, slicing and rotation, and instruction-level code optimization. Preliminary results show that our method can achieve high performance and good hardware utilization for OpenCL kernels, as well as decreasing the programming difficulty on FT-Matrix.

Edge computing promises to bring computation close to the end-users to support emergent applications such as virtual reality. However, the computational capacity at the edge of the network is currently limited. To become a pervasive paradigm, edge computing needs highly dispersed decentralized deployments, that, contrary to cloud, cannot benefit from economies of scale. In this situation, crowdsourcing appears attractive - there are plenty of computing devices at the disposal of the general public, and these devices are located exactly where computing power is needed the most - at the edge of the network. Crowdsourcing has been a success maker for scientific computing projects, e.g., SETI@home, or distributed ledger systems empowering decentralized finance. However, as of now, there is no crowdsourced system that addresses the needs of edge computing. In this position paper, we aim to identify the causes of this shortcoming, analyze the potential ways to overcome it, and outline future directions.

The aim of the SPICE project is to build social cohesion, both between and within citizen communities, by developing tools and methods to support citizen curation. We define citizen curation as a process in which cultural objects are used as a resource by citizens to develop their own personal interpretations. Within communities, citizens can use their interpretations to build a representation of themselves and their shared perspective on culture. Interpretations can also be used to support social cohesion across groups. In this short position paper we outline the methodologies and technologies needed to be built in order to build a recommender system of cultural objects that will implement these goals of social cohesion and inclusion.

Tactile Internet (TI) refers to the transmission of touch and the real-time control of applications like the remote control for teleoperation of machines, drones or vehicles. Traditional TCP and UDP protocols are not suitable for these applications, because they are mainly designed for content delivery or non real-time interactive applications. Some ideas from transport protocols for real-time multimedia like RTP are closer to Tactile Internet; however, they do not satisfy requirements of low latency and high reliability. In this paper, we present the Multi-connection Tactile Internet Protocol (MTIP), a novel transport protocol on top of the Internet Protocol to support the reliability and latency for Internet applications over multi-homed devices connected to several wireless networks. In order to provide that service, MTIP is based on the combination of sequence numbers and timestamps in packets, enhanced with global clocks and context awareness. The paper focuses on building a state machine based model of MTIP to prove the correct behaviour of the protocol using the SPIN tool to verify a number of relevant correctness properties.

A cyber cyber digital twin is a deployed software model that executes in tandem with the system it simulates, contributing to, and drawing from, the system's behaviour. This paper outlines Facebook's cyber cyber digital twin, dubbed WW, a twin of Facebook's WWW platform, built using web-enabled simulation. The paper focuses on the current research challenges and opportunities in the area of measurement. Measurement challenges lie at the heart of modern simulation. They directly impact how we use simulation outcomes for automated online and semi-automated offline decision making. Measurements also encompas how we verify and validate those outcomes. Modern simulation systems are increasingly becoming more like cyber cyber digital twins, effectively moving from manual to automated decision making, hence, these measurement challenges acquire ever greater significance.

Current popular phishing prevention techniques mainly utilize reactive blocklists, which leave a ``window of opportunity'' for attackers during which victims are unprotected. One possible approach to shorten this window aims to detect phishing attacks earlier, during website preparation, by monitoring Certificate Transparency (CT) logs. Previous attempts to work with CT log data for phishing classification exist, however they lack evaluations on actual CT log data. In this paper, we present a pipeline that facilitates such evaluations by addressing a number of problems when working with CT log data. The pipeline includes dataset creation, training, and past or live classification of CT logs. Its modular structure makes it possible to easily exchange classifiers or verification sources to support ground truth labeling efforts and classifier comparisons. We test the pipeline on a number of new and existing classifiers, and find a general potential to improve classifiers for this scenario in the future. We publish the source code of the pipeline and the used datasets along with this paper (https://gitlab.com/rwth-itsec/ctl-pipeline), thus making future research in this direction more accessible., Comment: Accepted at The 16th International Conference on Availability, Reliability and Security (ARES 2021)

Online learning to rank (OLTR) uses interaction data, such as clicks, to dynamically update rankers. OLTR has been thought to capture user intent change overtime - a task that is impossible for rankers trained on statistic datasets such as in offline and counterfactual learning to rank. However, this feature has never been demonstrated and empirically studied, as previous work only considered simulated online data with single user intent or real online data with no explicit notion of intents and how they change over interactions. In this paper, we address this gap by study the capability of OLTR algorithms to adapt to user intent change. Our empirical experiments show that the adaptation to intent change does vary across OLTR methods, and is also dependent on the amount of noise in the implicit feedback signal. This is an important result, as it highlights that intent change adaptation should be studied alongside online and offline performance. Investigating how OLTR algorithms adapt to intent change is challenging as current LTR datasets do not explicitly contain the required intent data. Along with the main findings reported in this paper related to intent change, we also contribute a methodology to investigate this aspect of OLTR methods. Specifically, we create a collection for OLTR with explicit intent change by adapting an existing TREC collection to this task. We further introduce methods to model and simulate click behaviour related to intent change. We further propose novel evaluation metrics tailored to study different aspects of how OLTR methods adapt to intent change.

Marginalized communities’ access to and use of ICT have long been a concern in HCI4D and social computing. Many works in this domain have pointed out that the challenges to access to ICT often go beyond limited computing resources and skills and frequently include many other socio-cultural factors. In this paper, we report three of the factors that arose while studying rural Bangladeshi women’s access to ICT: stigma, rumor, and superstition. Through an eight-month-long mix-method study with 23 rural women in Jessore, we explored the forms of fear and resistance to use computing devices prevalent among this population, particularly among the women we studied. We report how their stigma, rumors and superstitions often entangled with each other and created a gender-specific resistance to women’s ICT use. This paper further discusses how this resistance was connected to a weak economy and insufficient legal and educational infrastructure in the rural community. We extend the discussion to implications for design, policy, patriarchy, and other social practices to address these human factors in HCI4D and social sustainability scholarship.

Voice assistants (VA) collect data about users’ daily life including interactions with other connected devices, musical preferences, and unintended interactions. While users appreciate the convenience of VAs, their understanding and expectations of data collection by vendors are often vague and incomplete. By making the collected data explorable for consumers, our research-through-design approach seeks to unveil design resources for fostering data literacy and help users in making better informed decisions regarding their use of VAs. In this paper, we present the design of an interactive prototype that visualizes the conversations with VAs on a timeline and provides end users with basic means to engage with data, for instance allowing for filtering and categorization. Based on an evaluation with eleven households, our paper provides insights on how users reflect upon their data trails and presents design guidelines for supporting data literacy of consumers in the context of VAs.

The interpretability or explainability of AI systems (XAI) has been a topic gaining renewed attention in recent years across AI and HCI communities. Recent work has drawn attention to the emergent explainability requirements of in situ, applied projects, yet further exploratory work is needed to more fully understand this space. This paper investigates applied AI projects and reports on a qualitative interview study of individuals working on AI projects at a large technology and consulting company. Presenting an empirical understanding of the range of stakeholders in industrial AI projects, this paper also draws out the emergent explainability practices that arise as these projects unfold, highlighting the range of explanation audiences (who), as well as how their explainability needs evolve across the AI project lifecycle (when). We discuss the importance of adopting a sociotechnical lens in designing AI systems, noting how the “AI lifecycle” can serve as a design metaphor to further the XAI design field.

Secure ranging is poised to play a critical role in several emerging applications such as self-driving cars, unmanned aerial systems, wireless IoT devices, and augmented reality. In this paper, we propose a design of a secure broadcast ranging systems with unique features and techniques. Its spectral-flexibility, and low-power short ranging bursts enable co-existence with existing systems such as in the 2.4GHz ISM band. We exploit a set of RF techniques such as upsampling and successive interference cancellation to achieve high accuracy and scalability to tens of reflectors even when operating over narrow bands of spectrum. We demonstrate that it can be implemented on popular SDR platforms FPGA and/or hosts (with minimal FPGA modifications). The protocol design, and cryptographically generated/detected signals, and randomized timing of transmissions, provide stealth and security against denial of service, sniffing, and distance manipulation attacks. Through extensive experimental evaluations (and simulations for scalability to over 100 reflectors) we demonstrate an accuracy below 20cm on a wide range of SNR (as low as 0dB), spectrum 25MHz-100MHz, with bursts as short as 5us., Comment: correct function name in figure 1; add protocol diagram in appendix; move appendix to the end of paper

Problem decomposition is an important part of many state-of-the-art Evolutionary Algorithms (EAs). The quality of the decomposition may be decisive for the EA effectiveness and efficiency. Therefore, in this paper, we focus on the recent proposition of Linkage Learning based on Local Optimization (3LO). 3LO is an empirical linkage learning (ELL) technique and is proven never to report the false linkage. False linkage is one of the possible linkage defects and occurs when linkage marks two independent genes as a dependent. Although thanks to the problem decomposition quality, the use of 3LO may lead to excellent results, its main disadvantage is its high computational cost. This disadvantage makes 3LO not applicable to state-of-the-art EAs that originally employed Statistical-based Linkage Learning (SLL) and frequently update the linkage information. Therefore, we propose the Direct Linkage Empirical Discovery technique (DLED) that preserves 3LO advantages, reduces its costs, and we prove that it is precise in recognizing the direct linkage. The concept of direct linkage, which we identify in this paper, is related to the quality of the decomposition of overlapping problems. The results show that incorporating DLED in three significantly different state-of-the-art EAs may lead to promising results.

A core challenge of evolutionary search is the need to balance between exploration of the search space and exploitation of highly fit regions. Quality-diversity search has explicitly walked this tightrope between a population's diversity and its quality. This paper extends a popular quality-diversity search algorithm, MAP-Elites, by treating the selection of parents as a multi-armed bandit problem. Using variations of the upper-confidence bound to select parents from under-explored but potentially rewarding areas of the search space can accelerate the discovery of new regions as well as improve its archive's total quality. The paper tests an indirect measure of quality for parent selection: the survival rate of a parent's offspring. Results show that maintaining a balance between exploration and exploitation leads to the most diverse and high-quality set of solutions in three different testbeds., Comment: Proceedings of the Genetic and Evolutionary Computation Conference, 9 pages, 6 figures, 3 tables

The COVID-19 emergency has posed many challenges to the worldwide school system leading to school closures and massive adoption of distance education. These events affected not only the way education is delivered but also the overall school community’s wellbeing and cohesion. In this paper, we present a playful education platform originally designed to promote sustainable mobility in schools that has been adapted to support distance learning and community engagement during the health emergency. In the original version of the platform, the home-school distances traveled by students with sustainable means contributed to the advancement of the whole class in a collective virtual trip associated with playful learning material. Conversely, in a revised version of the platform adapted to the new context, students could advance in the virtual trip by reporting the good deeds performed at home. Findings from 161 questionnaires completed by teachers, families, and students, as well as results from online workshops with students, and the analysis of log files at the end of the school year revealed the opportunities and limitations of converting a playful activity conceived for being experienced in class into an online activity to be completed at home. The results show that the adapted version contributed to the school community cohesion and provided a positive experience to all its members, even though it was not able to completely overcome the generalized feeling of isolation. This paper contributes to understanding the social value of collaborative and playful digital activities that involve the entire school community, showing how technology can impact education and support communities in times of crisis.

A multitude of cloud-native applications take up a significant share of today's world wide web, the majority of which implicitly require soft-real-time guarantees when hosted on servers at various data centers across the globe. With the rapid development of cloud computing and virtualization techniques, many applications have been moved onto cloud and edge platforms that require efficient virtualization techniques. This means a set of applications must be executed on a Virtual Machine (VM) and multiple VMs must be temporally and spatially scheduled on a set of CPUs. Designed to leverage the cloud infrastructure model, many of these cloud-native applications such as media servers strongly demand low data latency and high compute-resource availability, both of which must be predictable. However, state-of-art VM schedulers fail to satisfy these requirements simultaneously. The scheduling of cloud-native applications on VMs and the scheduling of VMs on physical resources (CPUs), collectively need to be real-time in nature as specified by the Hierarchical Real-Time Scheduling (HiRTS) framework. Conforming to the specifications of this framework, the Regularity-based Resource Partitioning (RRP) model has been proposed that introduces the concept of regularity to provide a near-ideal resource supply to all VMs. In this paper, we make the theoretically superior Regularity-based Resource Partitioning (RRP) model ready for prime time by implementing its associated resource partitioning algorithms for the first time ever on the popular x-86 open-source hypervisor Xen, i.e., RRP-Xen. This paper also compares and contrasts the real-time performance of RRP-Xen against contemporary Xen schedulers such as Credit and RTDS. Our contributions include: (1) a novel implementation of the RRP model on Xen's x-86 based hypervisor, thereby providing a test-bed for future researchers; (2) the first-ever multi-core ARINC 653 VM scheduler prototype on Xen; and (3) numerous experiments and theoretical analysis to determine the real-time performance of RRP-Xen under a stringent workload environment.

This paper presents a design strategy of chiplet-based processing-in-memory systems for deep neural network applications. Monolithic silicon chips are area and power limited, failing to catch the recent rapid growth of deep learning algorithms. The paper first demonstrates a straightforward layer-wise method that partitions the workload of a monolithic accelerator to a multi-chiplet pipeline. A quantitative analysis shows that the straightforward separation degrades the overall utilization of computing resources due to the reduced on-chiplet memory size, thus introducing a higher memory wall. A tile interleaving strategy is proposed to overcome such degradation. This strategy can segment one layer to different chiplets which maximizes the computing utilization. To facilitate the strategy, the modification of the chiplet system hardware is also discussed. To validate the proposed strategy, a nine-chiplet processing-in-memory system is evaluated with a custom-designed object detection network. Each chiplet can achieve a peak performance of 204.8GOPS at a 100-MHz rate. The peak performance of the overall system is 1.711TOPS, where no off-chip memory access is needed. By the tile interleaving strategy, the utilization is improved from 53.9 to 92.8

This taxonomy paper presents a novel way of knowledge engineering in the software engineering research community. Till now, research papers are organized digitally as documents, mostly in PDF files. Not much effort is spent on effective knowledge classification, retrieval, storage, and representation. In contrast to the current paper-based approach for knowledge documentation, we present a statement-based approach, where each statement is linked to arguments and data of its evidence as well as to related statements. We argue that in this way, knowledge will be easier to retrieve, compare, and evaluate in contrast to current paper-based knowledge engineering in scientific search engines and digital libraries. Therefore, we present as a first step a novel multi-dimensional classification for statements in software engineering research. Statements are classified according to their research object, their kind (e.g., relevance), and their underlying evidence. This classification is validated and extended with a first systematic literature review. Additionally, we provide an example for illustration purpose.

Video streaming platforms such as Youtube, Twitch, and DLive allow users to live-stream video content for viewers who can optionally express their appreciation through monetary donations. DLive is one of the smaller and lesser-known streaming platforms, and historically has had fewer content moderation practices. It has thus become a popular place for violent extremists and other clandestine groups to earn money and propagandize. What is the financial structure of the DLive streaming ecosystem and how much money is changing hands? In the past it has been difficult to understand how far-right extremists fundraise via podcasts and video streams because of the secretive nature of the activity and because of the difficulty of getting data from social media platforms. This paper describes a novel experiment to collect and analyze data from DLive's publicly available ledgers of transactions in order to understand the financial structure of the clandestine, extreme far-right video streaming community. The main findings of this paper are, first, that the majority of donors are using micropayments in varying frequencies, but a small handful of donors spend large amounts of money to finance their favorite streamers. Next, the timing of donations to high-profile far-right streamers follows a fairly predictable pattern that is closely tied to a broadcast schedule. Finally, the far-right video streaming financial landscape is divided into separate cliques which exhibit very little crossover in terms of sizable donations. This work will be important to technology companies, policymakers, and researchers who are trying to understand how niche social media services, including video platforms, are being exploited by extremists to propagandize and fundraise., accepted at WebSci'21, 10 pages

Elasticity is an essential feature of cloud computing, which allows users to dynamically add or remove resources in response to workload changes. However, building applications that truly exploit elasticity is non-trivial. Traditional applications need to be modified to efficiently utilize variable resources. This paper explores thread oversubscription, i.e., provisioning more threads than the available cores, to exploit CPU elasticity in the cloud. While maintaining sufficient concurrency allows applications to utilize additional CPUs when more are made available, it is widely believed that thread oversubscription introduces prohibitive overheads due to excessive context switches, loss of locality, and contention on shared resources. In this paper, we conduct a comprehensive study of the overhead of thread oversubscription. We find that 1) the direct cost of context switching (i.e., 1-2 μs on modern processors) does not cause noticeable performance slow down to most applications; 2) oversubscription can be both constructive and destructive to the performance of CPU caches and TLB. We identify two previously under-studied issues that are responsible for drastic slowdowns in many applications under oversubscription. First, the existing thread sleep and wakeup process in the OS kernel is inefficient in handling oversubscribed threads. Second, pervasive busy-waiting operations in program code can waste CPU and starve critical threads. To this end, we devise two OS mechanisms, virtual blocking and busy-waiting detection, to enable efficient thread oversubscription without requiring program code changes. Experimental results show that our approaches can achieve an efficiency close to that in under-subscribed scenarios while preserving the capability to expand to many more CPUs. The performance gain is up to 77% for blocking- and 19x for busy-waiting-based applications compared to the vanilla Linux.

The rapid growth of software engineering research publications forces an amount of scholarly knowledge that needs to be managed, organized and communicated in digital libraries and scientific search engines. Thus, there is a need for classified papers to accomplish these tasks, but the classification process is cumbersome. Moreover, in case of new schemas, one would need to reclassify previously published research. We propose to automate the classification and present different possible techniques for doing so: Using natural language models, a rule-based approach, or an approach based on topic-labeling. In this proposal paper, we initially implemented a prototype for text classification of software engineering research papers.

Bridging the gap between academic research and industrial application is an important issue to promote Jackson's Problem Frames approach (PF) to the software engineering community. Various attempts have been made to tackle this problem, such as defining formal semantics of PF for software development, and providing a semi-formal approach to model transformations of problem diagrams, with automated tool support. In this paper, we propose to exclusively focus on exploring and evaluating the effectiveness of Jackson's problem diagrams for modeling the context of cyber-physical systems, by developing a suite of support tools enhanced with adaptive user interfaces, and empirically and comprehensively assess its usability. This paper introduces the state of the art, corresponding research questions, research methodologies and current progress of our research.

In this paper, we share our vision to study a complex Information Technology (IT) system handling a massive amount of data in the context of 'smart buildings.' One technique for analyzing complex IT systems relies on emulation, where the final software system is fully deployed on real architectures, and is evaluated in considering "small" instances of situations the system is supposed to solve. We propose a software architecture for studying the ecosystem of 'smart buildings'. This software architecture is built: 1) on top of ontologies for the description of smart buildings; 2) on a special tool for mastering the life cycle of data produced by sensors and actuators inside the buildings. We assume that it is equally important to model both the building's components and the flow of data produced inside the building. We use existing software components for both goals and to make real our concerns. According to a translational methodology, we also discuss use cases for illustrating the potential of our approach and the particular challenges associated with making the two main components of our emulation tool inter-operate. Therefore, our main contribution is to propose a comprehensive, ambitious and realistic research plan to guide communities. The paper illustrates how computer scientists and smart buildings domain scientists may communicate to address and solve specific research problems related to Big Data in emergent distributed environments. We are also guessing that experimental results that can demonstrate the practicality of the proposed combination of tools could be devised in the future, based on our broad vision. The paper is, first and foremost, a visionary paper.

When participatory technological design initiatives are focused on a very specific local context it becomes difficult to scale up their deployment to wider or different contexts. We have therefore extended the notion of empowered design and consequent technology appropriations and show that scaffolding, assistance that fades away, is a viable method to facilitate inter-community engagements with technology. This leads to technology appropriation by communities who did not participate in the original design, and they do this independently of the original academic design team. In this paper we report on our project process over an extended period of time. A collaborator and co-author on this paper is an elder from the original community who is acting to extend and adapt the technology with other, distant, communities from the same ethnic group, the ovaHimba. We particularly focus on the evolving role our collaborator took on over a number of field trips, and how our support, the scaffolding, became less and less important. His perspective is shared through translated statements and integrated into the text after our joint paper discussions.

This paper studies the design of a key-value (KV) store that can take full advantage of modern storage hardware with built-in transparent compression capability. Many modern storage appliances/drives implement hardware-based data compression, transparent to OS and applications. Moreover, the growing deployment of hardware-based compression in Cloud infrastructure leads to the imminent arrival of Cloud-based storage hardware with built-in transparent compression. By decoupling the logical storage space utilization efficiency from the true physical storage usage, transparent compression allows data management software to purposely waste logical storage space in return for simpler data structures and algorithms, leading to lower implementation complexity and higher performance. This work proposes a table-less hash-based KV store, where the basic idea is to hash the key space directly onto the logical storage space without using a hash table at all. With a substantially simplified data structure, this approach is subject to significant logical storage space under-utilization, which can be seamlessly mitigated by storage hardware with transparent compression. This paper presents the basic KV store architecture, and develops mathematical formulations to assist its configuration and analysis. We implemented such a KV store KallaxDB and carried out experiments on a commercial SSD with built-in transparent compression. The results show that, while consuming very little memory resource, it compares favorably with the other modern KV stores in terms of throughput, latency, and CPU usage.

The notion of establishing energy communities where householders collectively participate in using renewable energy is highly topical. In this paper, we interrogate a design vision of sustainable communal energy developed through a techno-solutionist narrative. The vision is exemplified in a recommendation-based mobile app, the Community Energy Planner app, that provides individual and collective energy feedback on renewable energy actions. To obtain insights into how householders understand and experience embedding such recommended communal energy feedback into domestic energy-consuming practices, we deployed the app with six households for one month. Through a qualitative study, we report on householders’ experiences living with the app on an individual and at a community level. Our findings are presented in four themes, revealing that recommended feedback on individual and collective energy actions is challenging to align with the messiness of domestic life. Finally, we discuss alternative design visions for sustainable communal energy. The main contribution of this paper is twofold: 1) a field deployment study of a techno-solutionist narrative of communal energy facilitated through an app and, 2) a discussion on alternatives to this design vision.

The NGAC (Next Generation Access Control) standard for attribute-based access control (ABAC) allows for run-time changes of the permission and prohibition configurations through administrative obligations triggered by access events. It makes access control more fine-grained and dynamic. However, it raises challenges for assuring the correctness of NGAC policies. As policy testing is an important technique for quality assurance, this paper presents an approach to mutation analysis of NGAC policies. It can evaluate the effectiveness of a testing method and reveal potential faults in an inadequately tested policy. The mutation analysis covers various types of potential faults in the assignments, associations, prohibitions, and obligations of NGAC policies. This paper also proposes an incremental testing approach that first validates the initial configuration of a policy and then the policy as a whole. It helps determine whether faults appear in the configuration or the obligations. To evaluate the work, we have developed four working policies and their test suites based on the current NGAC reference implementation. The empirical studies show that the mutation analysis can shed light on the strengths and weaknesses of the test suites. They also demonstrate the need for developing more cost-effective testing methods.

The ubiquitous presence of smart devices along with advancements in connectivity coupled with the elastic capabilities of cloud and edge systems have nurtured and revolutionized smart ecosystems. Intelligent, integrated cyber-physical systems offer increased productivity, safety, efficiency, speed and support for data driven applications beyond imagination just a decade ago. Since several connected devices work together as a coordinated unit to ensure efficiency and automation, the individual operations they perform are often reliant on each other. Therefore, it is important to control what functions or activities different devices can perform at a particular moment of time, and how they are related to each other. It is also important to consider additional factors such as conditions, obligation or mutability of activities, which are critical in deciding whether or not a device can perform a requested activity. In this paper, we take an initial step to propose and discuss the concept of Activity-Centric Access Control (ACAC) for smart and connected ecosystem. We discuss the notion of activity with respect to the collaborative and distributed yet integrated systems and identify the different entities involved along with the important factors to make an activity control decision. We outline a preliminary approach for defining activity control expressions which can be applied to different smart objects in the system. The main goal of this paper is to present the vision and need for the activity-centric approach for access control in connected smart systems, and foster discussion on the identified future research agenda.

The zero trust principle only allows authorized and authenticated actions in a computer network. A network policy satisfies the least privilege principle by minimizing the network permissions to only those needed by users and applications. However, administrators face many challenges in creating a least privilege policy since it requires a detailed understanding of the network topology and knowing the communication requirements of every network application and user. This paper addresses those challenges by introducing a graph-based policy specification framework to capture a network's communication requirements and a network compiler that turns those requirements into an enforceable policy. To offset the effort of building such a stringent policy, we incorporate patterns to spread the work of policy creation over time and people. In the paper, we first elaborate on how our framework's semantics enhances network security and resilience. We then introduce a Security Policy Regression Testing tool (SPRT), which leverages our framework's semantics, to test and reason about consistency, correctness, and relevance of network security policies. Finally, we outline relevant research directions.

This paper collects a large number of cases and makes a comparative analysis of the typical application of Chinese and American open government data for public governance. Through comparison, this paper finds the gap between China's open government data and the United States, and then analyzes the reasons. On this basis, through the investigation of advanced experience, this paper puts forward the suggestions of open government data to innovate public governance, including data catalogue compilation, data standard formulating, data quality assessment and open government data sharing cooperation, in order to improve Chinese open government data to innovate the public governance level.

Proliferating supply chain attacks indicate that today's practices are insufficient for ensuring security and increasingly represent the weakest link in cybersecurity of software-based operational technologies. By tracking every action of integrating procured software components into an existing system, from analyzing vendors’ security to auditing purchaser's supply chain, a more secure software supply chain can be provided. Hyperledger Fabric, as a permissioned blockchain network, provides immutable i.e. tamper-proof solution for tracking the information stored on the ledger, while allowing only preauthorized actors to participate in the network. An approach that is taken in this paper is to track the software components that are introduced in the system, whether they are commercial-off-the-shelf components or tailor-made components and track their security analysis by utilizing blockchain technology. By defining Organization in blockchain network which can participate in the supply chain management process, this paper demonstrates the benefits of utilizing Hyperledger Fabric for managing acquired software components that are introduced in critical infrastructure. Given the analyzed use cases and proposed architecture, it can be concluded that Hyperledger Fabric blockchain provides necessary trust in a multi-party environment which is the basis for more efficient auditing of the whole process. The trustworthy logs and easier auditing are the key enablers for a supply chain management process that can address the described needs.

The contemporary processors are unable to meet the increasing data-intensive and computation-demanding requirements in autonomous vehicle software applications. Recently, the new Heterogeneous System Architecture (HSA) has emerged as a promising solution to meet these requirements. The HSA reduces the latency of data exchange between the compute units and cache-coherent shared memory, which is not supported by the non-HSA compliant heterogeneous platforms with acceleration support. The main goal of the paper is to investigate the performance gain by the HSA and conduct a comparative evaluation of the HSA and non-HSA compliant heterogeneous platforms. The paper aims at evaluating these platforms by using two computation-intensive software functions in autonomous vehicles, namely the object detection and vehicle movement. In order to achieve this goal, the CUDA-accelerated source code of the functions is ported from a non-HSA compliant heterogeneous platform to the HSA platform. In this regard, the paper presents the architecture of a proof-of-concept prototype and provides evaluation using the prototype.

This paper provides an in-depth analysis of the mechanism of cross-border e-commerce multilateral trade integration based on the big data synergy theory, and uses the big data synergy theory method to form an overall causal feedback map of the credit synergy system by analysing the causal feedback relationship between the static cross-border e-commerce credit synergy system indicators. Through the form of an expert questionnaire, the relatively important system indicators are selected and the indicator weights are calculated. Analyse the existing problems and put forward optimization suggestions; innovative research methods, this paper uses supply chain management performance indicators to measure the level of supply chain management optimization, combined with factor analysis to find out the factors that affect the supply chain optimization of cross-border e-commerce importers. Analysing the implementation effect of cross-border e-commerce policy system, exploring effective policy "combinations" to promote the development of cross-border e-commerce, and realizing the quantitative analysis of the whole process of cross-border e-commerce policy from policy choice, policy implementation to the response to international trade shocks is an effective way to ensure that the policy system is formulated scientifically and rationally and to solve the problem of police inefficiency and maladaptation.

With the advancement of urbanization in our country, the improvement of urban environment has been widely concerned. Urban landscape architecture plays an important role in improving urban living environment. The emergence of big data provides a new research perspective for human settlements. Big data has been widely used in urban and rural planning, architectural design, less used in landscape architecture. At present, the impact of big data technology on landscape planning and design research is analyzed in this paper. At the same time, how to apply big data technology in landscape planning and design is explored in this paper. This study can provide new ideas for the planning and design of urban landscape architecture.

The traditional teaching mode of simulation experiment of international trade practice specialty has the disadvantages of low authenticity, practicality and unsatisfactory teaching effect, which is difficult to meet the training requirements of high-quality foreign trade talents. Based on this, this paper puts forward the ability based "experiential" teaching mode: Taking the cultivation of students' actual ability as the direction and taking practice as the center, so that students can experience the real working state and requirements of foreign trade posts, complete the system integration of knowledge and enhance professional quality and ability in the process of dealing with actual business. According to the ability structure that international trade students should have, it is very important to design a reasonable teaching mode of international trade simulation experiment course. Under the guidance of the concept of applied talents, this paper analyzes the abilities of students required for international trade professional posts under the background of economic globalization. Combined with the teaching objectives of international trade simulation experiment course, it puts forward the structure framework of international trade practice ability, and explores the teaching practice and teaching mode of International trade simulation experiment course. The experiment reveals that the teaching mode is effective and reliable.

Distance education is an important part of network education. The development of distance education technology has greatly affected the overall development of network education in China. However, there are still some defects in the current distance education system, such as the courseware editing is not convenient enough, the communication between teachers and students is smooth enough. Therefore, this paper puts forward the research on the interaction of teaching media in Distance Education Based on computer cooperative work. In this paper, the characteristics of distance education system and related factors are studied in depth. Through the research results, this paper believes that distance education teaching traditional education has distinct characteristics, while emphasizing autonomy, it also requires that the learning system has good interactive performance. Aiming at the problem of interaction in distance education, this paper analyzes the interaction based on computer cooperative work. This paper focuses on the analysis of the advantages of interactive multimedia network teaching, the interactive analysis of teaching system, and the social interaction of distance education. Through the investigation, we can see that the teaching subject of distance education has changed from teacher to student in traditional education, and students occupy the dominant position. The analysis shows that the interactivity of distance education tests the rationality of the teaching mode and plays a role in cultivating students' self-learning ability.

As China's financial market continues to open to the outside world, and the demand for compound talents keeps increasing. It has provided a huge opportunity for the research of investment discipline and the reform of English teaching. In the paper, the postgraduate group is taken as the targeted students of the “Portfolio and Risk Analysis” course. This paper explores and summarizes from three aspects of teaching design, teaching methods and teaching evaluation, which aims at delivering compound talents with practical knowledge for the financial market.

Searching for targets from a group of Unmanned Aerial Vehicles (UAVs) is a complex problem, whose applications range from the localization of military targets to search and rescue missions. Determining the best locations to search within the mission scenario requires to consider the dynamics of the UAVs and of its onboard sensors, and the uncertainty of the problem, usually related with the target initial location and dynamics, and with the sensor likelihood. Besides, what is best is not always the same (e.g. it can be maximizing the detection probability and/or minimizing the target detection time, while ensuring communications, smooth trajectories, energy saving, etc). These makes the evaluation of UAVs target-search strategies a complex system itself. In this paper, we tackle this problem using the Discrete Event System Specification (DEVS) to exploit its modular and hierarchical design, and to improve the reusability and scalability of our evaluation system. DEVS also provides simple and clear semantics to manage the complexities of the system, represents an explicit separation between the model specification and the corresponding simulation, and helps us to debug and verify our model, as the results of the paper show.

Discrete models such as cellular automata may be ported from one platform or language onto another to improve performances, for instance by rewriting legacy Matlab code into C++ or adding optimizations into a Python implementation. Although such transformations can offer benefits such as scalability or maintainability, they also have the risk of introducing bugs. While standard verification techniques can always be applied, this situation presents a unique opportunity since the two implementations can be directly compared based on their simulation runs. Although comparing average results across runs of a same configuration is a common practice, our paper shows that many bugs would not be detected at this aggregate level. We thus propose comparing implementations of cellular automata by analyzing their outputs as images. In this paper, we examine the detection of several implementation errors using five different techniques (supervised/unsupervised image processing, decision trees, random forests, or deep learning) across three different cellular automata models (forest fire, tumor, HIV). We show that in some models, random forests can detect 4 out of 5 erroneous runs, although the accuracy depends both on the model and on the nature of the errors.

The explication of socio-technical challenges like privacy concerns, data transparency and control, accountability issues and lack of trust, posed by personal data leverage in media research has been of interest recently. While many of these challenges have been studied and often discussed in various disciplines ranging from policy to technology to sociology, effective responses that alleviate them are yet to be realised. This calls for holistic approaches that enable inter-disciplinary perspectives and methodologies that speak to these wider challenges in more comprehensive and thus, effective manners. Human Data Interaction, such a cross-disciplinary branch of knowledge, inspired by HCI, seeks to alleviate said challenges through three overarching principles : data legibility, negotiability and agency. But, given the emergent nature of this ‘fledgeling’ domain, the practical realization of these theortical tenets are yet to be operationalized. This paper reports the design of one such initiative that integrates the principles of HDI, supported by wider research, into the design of a novel, data driven media experience : a Cross Media Profiler. The first half of the paper presents the socio-technical challenges confronting the turn to personal data use in media experiences, rationalizes the need and scope for interdisciplinary approaches like HDI here and reviews wider literature that is in line with the principles of HDI. The rest of the paper reports the design of the CMP, particularly the realization of the HDI principles within this particular media service proposition. We intend for this design intervention to be leveraged in formative and evaluative studies that test user response to the design decisions made and their effectiveness in alleviating socio-technical challenges while also contributing to the current knowledge base supporting HDI.

To protect the password from visual attacks, most password entry screens use a password masking scheme that displays a series of placeholder characters (e.g., dots and asterisks) instead of the actual password. Recent research has however shown the security provided by this form of password masking to be weak against keystroke timing-analytics attacks. The underlying idea behind these attacks is that, even when a password is masked as described above, the timing between consecutive placeholder characters gives away information about the password since the relative locations of characters on the keyboard dictate how fast fingers move between them. In this paper we argue that, for security-sensitive applications, password masking mechanisms ought to hide the true intervals between password characters in order to overcome these kinds of attacks. Making adjustments to these timings however has the potential to pose usability issues given the fact that the typing would not perfectly align with the display of typed content. The paper proposes 3 different password masking schemes and undertakes a usability evaluation on them. Our early results suggest that user receptiveness to two of the schemes is not much worse than that seen with the conventional (insecure) scheme.

Quick, print this page!1 Otherwise, the information in this document might be digitally manipulated, and initial creative intention and contribution will be changed. You will lose your access to this document when the database containing this paper is decommissioned or compromised. This paper highlights the relevance of features from analogue media in an increasingly fragile digital world. Digital content can be altered to change its meaning or be deleted altogether. In analogue media, this is much more difficult without anyone noticing. Just imagine the impact if YouTube was decommissioned and all its content was rendered unavailable. In this paper, we outline concrete commercial examples and insight from the research of issues with distribution, storage, and manipulation of digital media and its impact on users. We conclude with strategies to preserve content, access, and artistic freedom in an increasingly digital future.

A person's name embodies identity. During user studies in Human Computer Interaction (HCI), persons are often renamed (pseudonymization) to hide their identity for privacy and ethical reasons. Pseudonymization occurs mostly as a “silent” affair of due diligence. Researchers barely give substantial information to the process nor reveal a reflexive position nor acknowledge the underlying elements of power and identity negotiation. As HCI advances in mitigating the design of biased technologies and breaking oppressive structures, I argue, in this paper, the need for the field to re-consider research requirements such as pseudonymization as possible to embody oppressive structures and erase identity. I present a review of papers from the 2020 CHI Conference on Human Factors in Computing Systems (CHI ‘20) that illustrate how silent the HCI approach is. My argument is built on Critical Race Theory, questioning the objectivity of such technical requirements. I use personal narratives to bolster this argument, ending with a call to the HCI community to acknowledge the power and privilege in renaming participants with three recommendations for consideration.

Tracking drinking behaviors and digitally presenting the information can motivate people's daily water intake. In this paper, we present MossWater, a living interface designed to visualize the daily water intake and so as to motivate people to drink water more frequently and proactively. The system utilizes living interface as an unobtrusive ambient display to evoke empathy. Caring and watering the moss is designed as a metaphor for caring for people's health by regularly drinking, which invokes people's feeling of empathy to motivate their healthier behaviors. This paper also presents the results of a user study exploring the usability of MossWater and users' feedbacks to this living interface. Our system is expected to promote the welfare of both human and nature in the long-term.

The centrality of the biometric point of sale (POS) machine in the administration of food security in Indian's public distribution system (PDS) invites scrutiny for its primacy as a non-negotiable artifact in the monthly PDS process. In this paper, I critically examine how the POS machine emerges as a site for varying imaginaries of a technologically-mediated welfare system for the three primary stakeholders of the PDS, consisting of the beneficiaries, dealers, and state administrators. Drawing on ethnographic fieldwork, the paper traces the histories of interaction and portraitures that the three stakeholders bring to their description and interpretation of the POS machine. It shows that an active POS machine provokes the stakeholders in the PDS to view it as an artifact that invites engagement on practical, moral, and knowledge dimensions. The varying ‘biographies’ that stakeholders narrate of the POS machine, collectively reveal the design, disposition, and functioning of a social justice infrastructure that rests on the compulsions of biometric technologies to improve inclusion and deter corruption in welfare delivery.

There is a developing recognition of the social and economic costs entailed in global supply chains. In this paper, we report on efforts to provide alternative, more sustainable and resilient models of production. Community Supported Agricultures (CSAs) address this problem but require new means of exchange which, we suggest, offer a design opportunity for sustainable HCI research. This paper presents a two months participatory observation in a food movement, a German CSA which developed a distribution system involving their own currency. Based on our ethnographic observations, we focus our discussion on (1) the solidaristic principles upon which the movement is based and (2) techniques of mediating between consumers’ wishes and the constraints of local agricultural production. By relating to the continued development of CSAs, we identify three interrelated innovation gaps and discuss new software architectures aimed at resolving the problems which arise as the movement grows.

The rise of autonomous systems in cities, such as automated vehicles (AVs), requires new approaches for prototyping and evaluating how people interact with those systems through context-based user interfaces, such as external human-machine interfaces (eHMIs). In this paper, we present a comparative study of three prototype representations (real-world VR, computer-generated VR, real-world video) of an eHMI in a mixed-methods study with 42 participants. Quantitative results show that while the real-world VR representation results in higher sense of presence, no significant differences in user experience and trust towards the AV itself were found. However, interview data shows that participants focused on different experiential and perceptual aspects in each of the prototype representations. These differences are linked to spatial awareness and perceived realism of the AV behaviour and its context, affecting in turn how participants assess trust and the eHMI. The paper offers guidelines for prototyping and evaluating context-based interfaces through simulations.

This paper turns to one of HCI's central value systems, i.e. its commitments to usefulness and the ideal that technology enables social progress, productivity, and excellence. Specifically, we examine how the seemingly “positive” ideal to make technology “useful” – i.e. to build systems and devices that advance social and technological progress – masks various forms of violence and injustice such as colonial othering, racist exclusions, and exploitation. Drawing from ethnographic research, we show how design and computing methods from design thinking to agile theory and entrepreneurial approaches in tech production and higher education are the latest techniques in the cultivation of useful bodies on behalf of the state, the corporation, the university, and the economy. Aligning with feminist, critical race and critical computing commitments, this paper offers a genealogical approach to show how injustice and violence endure, despite and because of a narrative of progress and positive change.