Search

A large language model refers to a deep learning model characterized by extensive parameters and pretraining on a large-scale corpus, utilized for processing natural language text and generating high-quality text output. The increasing deployment of large language models has brought significant attention to their associated privacy and security issues. Recent experiments have demonstrated that training data can be extracted from these models due to their memory effect. Initially, research on large language model training data extraction focused primarily on non-targeted methods. However, following the introduction of targeted training data extraction by Carlini et al., prefix-based extraction methods to generate suffixes have garnered considerable interest, although current extraction precision remains low. This paper focuses on the targeted extraction of training data, employing various methods to enhance the precision and speed of the extraction process. Building on the work of Yu et al., we conduct a comprehensive analysis of the impact of different suffix generation methods on the precision of suffix generation. Additionally, we examine the quality and diversity of text generated by various suffix generation strategies. The study also applies membership inference attacks based on neighborhood comparison to the extraction of training data in large language models, conducting thorough evaluations and comparisons. The effectiveness of membership inference attacks in extracting training data from large language models is assessed, and the performance of different membership inference attacks is compared. Hyperparameter tuning is performed on multiple parameters to enhance the extraction of training data. Experimental results indicate that the proposed method significantly improves extraction precision compared to previous approaches. [ABSTRACT FROM AUTHOR]

Depression is one of the most common mental illnesses and seriously affects all aspects of life. Running exercise has been suggested to prevent or alleviate the occurrence and development of depression; however, the underlying mechanisms of these effects remain unclear. Independent studies have indicated that astrocytes play essential roles and that the medial prefrontal cortex (mPFC) is an important brain region involved in the pathology underlying depression. However, it is unknown whether running exercise achieves antidepressant effects by affecting the number of astrocytes and glutamate transport function in the mPFC. Here, animal models of depression were established using chronic unpredictable stress (CUS), and depression‐like behavior was assessed by the sucrose preference test. After successfully establishing the depression model, experimental animals performed running exercise. Glial fibrillary acidic protein‐positive (GFAP+) cell number in the mPFC was precisely quantified using immunohistochemical and stereological methods, and the densities of bromodeoxyuridine‐positive (BrdU+) and BrdU+/GFAP+ cells in the mPFC were measured using a semiquantitative immunofluorescence assay. Changes in glutamate transporter gene expression in mPFC astrocytes were detected by mRNA sequencing and qRT–PCR. We found that running exercise reversed CUS‐induced decreases in sucrose preference, increased astrocyte number and the density of newborn astrocytes, and reversed decreases in gene expression levels of GFAP, S100b, and the glutamate transporters GLT‐1 and GLAST in the mPFC of CUS animals. These results suggested that changes in astrocyte number and glutamate transporter function may be potential meditators of the effects of running exercise in the treatment of depression. [ABSTRACT FROM AUTHOR]

Aerial acoustic communication attracts substantial attention for its simplicity and cost-effectiveness. Unfortunately, the preferred inaudible transmission has to strike a balance between the transmission rate and communication range, when the Bit-Error-Rate (BER) is under a certain threshold. Additionally, the performance of previous proposals can be deteriorated by dynamic channel conditions including near-far problem, device heterogeneity, and multipath fading. To this end, we propose a High-speed, long-range, and Robust Chirp Spread Spectrum (HRCSS) scheme for inaudible aerial acoustic communication under dynamic channels. HRCSS innovates in the definition of a loose orthogonality condition, and it leverages this orthogonality to overlap multiple chirp carriers in a single time duration to form a data symbol representing multiple bits, thereby substantially promoting the data rate. To further enhance system robustness in long communication ranges and dynamic channel conditions, we construct a lightweight rate adaptation algorithm and design a simple yet efficient normalization method. Experiment results reveal that HRCSS achieves a significant improvement in data rate over existing methods: it delivers 500 bps data rate with a BER of 0.24 percent at 10 m, and achieves 125 bps with zero BER at 20 m. Meanwhile, HRCSS can work adaptively under dynamic channel conditions while still retaining a BER below 3 percent. [ABSTRACT FROM AUTHOR]

The emerging large-scale low earth orbit (LEO) broadband satellite networks manifest great potentials in distributing videos across the globe via efficient multicast techniques. However, existing work only studied IP multicast (IPMC) for LEO constellations, which suffers from limited scalability and tree performance. In this paper, we employ the promising software defined multicast (SDM) techniques in large-scale LEO constellations to empower satellite-based Internet video distribution. We present a multi-layer rectilinear Steiner tree (ML-RST) construction algorithm for multicast routing in large-scale LEO constellations. We extend the spanning graph and edge substitution to three-dimensional (3D) scenes. Based on multi-layer spanning graphs and multi-layer edge substitution approaches, we manage to efficiently construct ML-RSTs with ${O}$ (${n}$ log ${n}$) complexity. Experimental results show that our approach can achieve an average 10% improvement in bandwidth saving compared with existing algorithms. [ABSTRACT FROM AUTHOR]

Recent years have witnessed a paradigm shift from centralized cloud computing to decentralized edge computing. As a key enabler technique in edge computing, computation offloading migrates computation-intensive tasks from resource-limited devices to nearby devices, optimizing service latency and energy consumption. In this paper, we investigate the problem of offloading task graphs in edge computing scenarios. Previous work based on list-scheduling heuristics is likely to suffer from severe processor time wastage due to intricate task dependencies and data transfer requirements. To this end, we propose a novel offloading algorithm, referred to as Iterative Dynamic Critical Path Scheduling (IDCP). IDCP minimizes the makespan by iteratively migrating tasks to keep shortening the dynamic critical path. Through IDCP, what is managed are essentially the sequences among tasks, including task dependencies and scheduled sequences on processors. Since we only schedule sequences here, the actual start time of each task is not fixed during the scheduling process, which effectively helps to avoid unfavorable schedules. Such flexibilities also offer us much space for continuous scheduling optimizations. Our experimental results show that our algorithm significantly outperforms existing list-scheduling heuristics in various scenarios, which demonstrates the effectiveness and competitiveness of our algorithm. [ABSTRACT FROM AUTHOR]

Temperature is an important data source for weather forecasting, agriculture irrigation, anomaly detection, etc. While temperature measurement can be achieved via low-cost yet standalone hardware with reasonable accuracy, integrating thermal sensing into ubiquitous computing devices is highly non-trivial due to the design requirement for specific heat isolation and proper device layout. In this paper, we present the first integrated thermometer using commercial-off-the-shelf acoustic-enabled devices. Our software sonic thermometer (SST) utilizes on-board dual microphones on commodity mobile devices to estimate sound speed, which has a known relation with temperature. To precisely measure temperature via sound speed, we propose a chirp mixing approach to circumvent low sampling rates on commodity hardware and design a pipeline of signal processing blocks to handle channel distortions. SST, for the first time, empowers ubiquitous computing devices with thermal sensing capability. It is portable and cost-effective, making it competitive with current thermometers using dedicated hardware. SST is potential to facilitate many interesting applications such as large-scale distributed thermal sensing, yielding high temporal/spatial resolutions with unimaginable low costs. We implement SST on a commodity platform and results show that SST achieves a median accuracy of 0.5∘ C even at varying humidity levels. [ABSTRACT FROM AUTHOR]

This paper studies a scheduling problem of task graphs on a non-dedicated networked computing platform. The networked platform is characterized by a set of fully connected processors such as a multiprocessor system that can be shared by multiple tasks. Therefore, the computation and communication capacities of the computing platform dynamically fluctuate. To deal with this fluctuations for high performance task graph computing, we propose an online dynamic resilience scheduling algorithm called Adaptive Scheduling Algorithm (ASA) that bears certain distinct features compared to existing algorithms. First, the proposed algorithm deliberately assigns tasks to idle processors in multiple rounds to prevent any unfavorable decisions and also to avoid inefficient assignments of certain key tasks to slow processors. Second, the algorithm adopts task duplication as an attempt to minimize serious increase of schedule length due to unexpected processor slowdown. Finally, a look-ahead message transmission policy is applied to save communication time and further improve the overall performance. Performance evaluation results are presented to demonstrate the effectiveness and competitiveness of our approaches when compared with the existing algorithms. [ABSTRACT FROM PUBLISHER]

Mobile crowdsensing leverages mobile devices (e.g., smart phones) and human mobility for pervasive information exploration and collection; it has been deemed as a promising paradigm that will revolutionize various research and application domains. Unfortunately, the practicality of mobile crowdsensing can be crippled due to the lack of incentive mechanisms that stimulate human participation. In this paper, we study incentive mechanisms for a novel Mobile Crowdsensing Scheduling (MCS) problem, where a mobile crowdsensing application owner announces a set of sensing tasks, then human users (carrying mobile devices) compete for the tasks based on their respective sensing costs and available time periods, and finally the owner schedules as well as pays the users to maximize its own sensing revenue under a certain budget. We prove that the MCS problem is NP-hard and propose polynomial-time approximation mechanisms for it. We also show that our approximation mechanisms (including both offline and online versions) achieve desirable game-theoretic properties, namely truthfulness and individual rationality, as well as \mathcal O(1) performance ratios. Finally, we conduct extensive simulations to demonstrate the correctness and effectiveness of our approach. [ABSTRACT FROM AUTHOR]

In this paper, we study the problem of co-migrating a set of service replicas residing on one or more redundant virtual servers in clouds in order to satisfy a sequence of mobile batch-request demands in a cost effective way. With such a migration, we can not only reduce the service access latency for end users but also minimize the network costs for service providers. The co-migration can be achieved at the cost of bulk-data transfer and increases the overall monetary costs for the service providers. To gain the benefits of service migration while minimizing the overall costs, we propose a co-migration algorithm Migk for multiple servers, each hosting a service replicas. Migk is a randomized algorithm with a competitive cost of O(\frac\gamma\, \log \,n\min \lbrace \frac1\kappa ,\frac\mu \lambda \,+\,\mu \rbrace ) to migrate $\kappa$ services in a static $n$ -node network where $\gamma$ is the maximal ratio of the migration costs between any pair of neighbor nodes in the network, and where $\lambda$ and $\mu$ represent the maximum wired transmission cost and the wireless link cost respectively. For comparison, we also study this problem in its static off-line form by proposing a parallel dynamic programming (hereafter DP) based algorithm that integrates the branch&bound strategy with sampling techniques in order to approximate the optimal DP results. We validate the advantage of the proposed algorithms via extensive simulation studies using various requests patterns and cloud network topologies. Our simulation results show that the proposed algorithms can effectively adapt to mobile access patterns to satisfy the service request sequences in a cost-effective way. [ABSTRACT FROM PUBLISHER]

Time-triggered communication protocols, such as time-triggered protocol (TTP) and FlexRay, have the potential to solve many system integration and concurrent engineering issues in the aerospace industry. This paper investigates the scheduling of periodic applications on time-triggered systems. A novel scheduling problem is formulated to capture a unique feature commonly existing in the safety-critical time-triggered systems, i.e., in task graphs running in such systems, some nodes (i.e., tasks and messages) are strictly periodic while others are not. To address the problem, a novel scheduling algorithm called synchronized highest level first (SHLF) algorithm is presented. Moreover, to further improve schedulability, this paper also proposes two rescheduling and backtracking approaches, namely release time deferment (RTD) procedure and backtracking and priority promotion (BPP) procedure. Performance evaluation results are presented to demonstrate the effectiveness and competitiveness of our approaches when compared with existing algorithms. [ABSTRACT FROM PUBLISHER]

High-performance computing (HPC) systems, including Clusters, Grids and the most recent Clouds, have emerged as attractive platforms to tackle various applications. One significant type of applications in the HPC systems is workflow computation, which has been applied in various scientific and engineering domains. The workflow computation frequently produces intermediate result files, which become garbage after being used and are usually cleaned up without making any contribution to future computation. In this paper, we argue that such garbage data could be useful in the future computation and should not be immediately cleaned up. This is because workflow computation usually contains multiple instances that may share some common data products produced in the past. This sharing scheme provides opportunities to reuse the historical data to speed-up subsequent computation and simplify re-computation due to faulty or crashed runs. To this end, we propose a novel approach, referred to as garbage data manager (GDM), for the workflow computation in HPC systems. The GDM organizes and manages the garbage data for batch schedulers to enhance the performance of subsequent computation. The essence of the GDM is to record the history of computation by constructing a dataflow graph on per instance (run) basis and set up inheritance relationships between the different instances of the same workflow, called run-tree, to achieve the data reuse. Our simulation results demonstrate that exploiting the garbage data is an effective way of improving the workflow computation. [ABSTRACT FROM PUBLISHER]

The scheduling of tasks with deadlines on clusters is a key issue for offering quality-of-service (QoS) assurance. A critical challenge in real-time task scheduling is to handle various types of applications. This paper investigates the scheduling problem for processing a set of tasks comprising both divisible and indivisible real-time tasks on cluster systems. Indivisible tasks are characterized by the property that they need to be processed on their entirety on a single processor while divisible tasks can be distributed across several processing nodes by exploiting the underlying data parallelism. We propose a dynamic (on-line) real-time scheduling algorithm referred to as Hybrid Loads Push-Pull Scheduling (HLPPS) algorithm for handling a set of tasks comprising both divisible and indivisible real-time tasks on cluster systems. HLPPS is shown to efficiently exploit the parallelism in divisible tasks without undermining the schedulability of indivisible tasks and thereby optimize the overall performance. We consider two distinct network platforms - tightly coupled and loosely coupled clusters in designing the strategy. We conduct extensive performance evaluation studies to quantify the performance of the proposed algorithm under a variety of scenarios. [ABSTRACT FROM AUTHOR]

Content distribution networks (CDNs) built on clouds have recently started to emerge. Compared to conventional CDNs, cloud-based CDNs have the benefit of cost efficient hosting services without owning infrastructure. However, resource provisioning and replica placement in cloud CDNs involve a number of challenging issues, mainly due to the dynamic nature of demand patterns. To deal with this dynamic nature, this paper proposes a set of novel algorithms to solve the joint problem of resource provisioning and caching (i.e., replica placement) for cloud-based CDNs with an emphasis on handling the dynamic demand patterns. Firstly, we propose a provisioning and caching algorithm framework called Differential Provisioning and Caching (DPC) algorithm, which aims to rent cloud resources to build CDNs and whereby to cache contents so that the total rental cost can be minimized while all demands are served. DPC consists of 2 steps. Step 1 first maximizes total demands supported by unexpired resources. Then, step 2 minimizes the total rental cost for new resources to serve all remaining demands. For each step we design both greedy and iterative heuristics, each with different advantages over the existing approaches. Moreover, to dynamically adjusts the placement of contents and route maps, we further propose the Caching and Request Balancing (CRB) algorithm, which is light-weight and thus can be frequently executed as a companion of DPC to maximize the total demands. Performance evaluation results are presented to demonstrate the effectiveness and competitiveness of our approaches when compared to existing algorithms. [ABSTRACT FROM PUBLISHER]

As time-triggered communication protocols [e.g., time-triggered controller area network (TTCAN), time-triggered protocol (TTP), and FlexRay] are widely used on vehicles, the scheduling of tasks and messages on in-vehicle networks becomes a critical issue for offering quality-of-service (QoS) guarantees to time-critical applications on vehicles. This paper studies a holistic scheduling problem for handling real-time applications in time-triggered in-vehicle networks where practical aspects in system design and integration are captured. The contributions of this paper are multifold. First, it designs a novel scheduling algorithm, referred to as Unfixed Start Time (UST) algorithm, which schedules tasks and messages in a flexible way to enhance schedulability. In addition, to tolerate assignment conflicts and further improve schedulability, it proposes two rescheduling and backtracking methods, namely, Rescheduling with Offset Modification (ROM) and Backtracking and Priority Promotion (BPP) procedures. Extensive performance evaluation studies are conducted to quantify the performance of the proposed algorithm under a variety of scenarios. [ABSTRACT FROM PUBLISHER]

Grids have been extensively deployed to handle various scientific and engineering applications that can be structured as bag-of-tasks (BoT). The scheduling of BoT applications on Grids is an important issue for achieving high performance. Grid scheduling involves a number of challenging issues, mainly due to the dynamic nature of the Grid. To deal with this dynamic nature, in this paper, we propose an online scheduling algorithm called prudent algorithm with replication (PAR) for scheduling Grid applications. PAR is shown to prudently make scheduling decisions in such a way that it can tolerate inaccurate performance predictions. Another point to note is that PAR adopts task duplication as an attempt to reduce serious schedule increases. Moreover, since the applications to be performed may widely vary in terms of their required hardware and software, we also capture the loads' various processing requirements in our algorithms, a unique feature that is applicable for running proprietary applications only on certain eligible processing nodes. Thus, in our problem formulation each application can only be processed by certain processors as both the applications and processing nodes are heterogeneous. We then present a task selection policy, referred to as requirement-aware load selection (RALS) policy to handle the contention of multiple applications that have various processing requirements but share the same computing resources. Based on RALS and PAR, we develop two scheduling algorithms: requirement-aware prudent algorithm with replication (RAPAR), and requirement-aware knowledge-free algorithm with replication (RAKAR). RAPAR and RAKAR address the scheduling of multiple BoT applications with heterogeneous processing requirements on Grids. RAPAR works in scenarios where inaccurate performance prediction information is provided whereas RAKAR works without any prediction information. Performance evaluation results are presented to demonstrate the effectiveness and competitiveness of our approaches when compared to existing algorithms. [ABSTRACT FROM AUTHOR]

Multiple blind sound source localization is the key technology for a myriad of applications such as robotic navigation and indoor localization. However, existing solutions can only locate a few sound sources simultaneously due to the limitation imposed by the number of microphones in an array. To this end, this paper proposes a novel multiple blind sound source localization algorithms using Source seParation and BeamForming (SPBF). Our algorithm overcomes the limitations of existing solutions and can locate more blind sources than the number of microphones in an array. Specifically, we propose a novel microphone layout, enabling salient multiple source separation while still preserving their arrival time information. After then, we perform source localization via beamforming using each demixed source. Such a design allows minimizing mutual interference from different sound sources, thereby enabling finer AoA estimation. To further enhance localization performance, we design a new spectral weighting function that can enhance the signal-to-noise-ratio, allowing a relatively narrow beam and thus finer angle of arrival estimation. Simulation experiments under typical indoor situations demonstrate a maximum of only 4 ∘ even under up to 14 sources. [ABSTRACT FROM AUTHOR]