Reinforcement Learning (RL) has shown significant promise in automated portfolio management; however, effectively balancing risk and return remains a central challenge, as many models fail to adapt to dynamically changing market conditions. We propose Meta-controlled Agents for a Risk-aware System (MARS), a novel framework addressing this through a multi-agent, risk-aware approach. MARS replaces monolithic models with a Heterogeneous Agent Ensemble, where each agent’s unique risk profile is enforced by a Safety-Critic network to span behaviors from capital preservation to aggressive growth. A high-level Meta-Adaptive Controller (MAC) dynamically orchestrates this ensemble, shifting reliance between conservative and aggressive agents to minimize drawdown during downturns while seizing opportunities in bull markets. This two-tiered structure leverages behavioral diversity rather than explicit feature engineering to ensure a disciplined portfolio robust across market regimes. Experiments on major international indexes confirm that our framework significantly reduces maximum drawdown and volatility while maintaining competitive returns.

Unauthorized screen capturing and dissemination pose severe security threats such as data leakage and information theft. Several studies propose robust watermarking methods to track the copyright of Screen-Camera (SC) images, facilitating post-hoc certification against infringement. These techniques typically employ heuristic mathematical modeling or supervised neural network fitting as the noise layer, to enhance watermarking robustness against SC. However, both strategies cannot fundamentally achieve an effective approximation of SC noise. Mathematical simulation suffers from biased approximations due to the incomplete decomposition of the noise and the absence of interdependence among the noise components. Supervised networks require paired data to train the noise-fitting model, and it is difficult for the model to learn all the features of the noise. To address the above issues, we propose Simulation-to-Real (S2R). Specifically, an unsupervised noise layer employs unpaired data to learn the discrepancy between the modeled simulated noise distribution and the real-world SC noise distribution, rather than directly learning the mapping from sharp images to real-world images. Learning this transformation from simulation to reality is inherently simpler, as it primarily involves bridging the gap in noise distributions, instead of the complex task of reconstructing fine-grained image details. Extensive experimental results validate the efficacy of the proposed method, demonstrating superior watermark robustness and generalization compared to state-of-the-art methods.

Recently, new paradigms of camouflaged object detection (COD), such as referring COD (Ref-COD) and collaborative COD (Co-COD), have been proposed to enhance task performance. However, there remains a lack of in-depth exploration of how to utilize reference information more effectively. In this paper, we introduce in-context learning camouflaged object detection (ICL-COD) as a novel paradigm of COD, which leverages camouflaged image samples and their corresponding annotations as visual examples to guide the model in better perceiving camouflage and recognizing camouflaged objects. We propose the ICL-Camo network, with the design of a context mining module (CMM) to mine fine-grained contextual information contained in the visual examples, and a context guiding module (CGM) that utilizes the contextual information mined from the examples as guidance to shift the attention of the target image features on potential camouflaged regions, thus enhancing its perception of camouflaged objects. Extensive experiments conducted on the COD benchmarks and other relevant tasks demonstrate the effectiveness of our proposed ICL-COD paradigm and ICL-Camo network. Code and results are available at: https://github.com/h0t-zer0/ICL-Camo.

The mathematical capabilities of AI systems are complex and multifaceted. Most existing research has predominantly focused on the correctness of AI-generated solutions to mathematical problems. In this work, we argue that beyond producing correct answers, AI systems should also be capable of, or assist humans in, developing novel solutions to mathematical challenges. This study explores the creative potential of Large Language Models (LLMs) in mathematical reasoning, an aspect that has received limited attention in prior research. We introduce a novel framework and benchmark, CreativeMath, which encompasses problems ranging from middle school curricula to Olympic-level competitions, designed to assess LLMs' ability to propose innovative solutions after some known solutions have been provided. Our experiments demonstrate that, while LLMs perform well on standard mathematical tasks, their capacity for creative problem-solving varies considerably. Notably, the Gemini-1.5-Pro model outperformed other LLMs in generating novel solutions. This research opens a new frontier in evaluating AI creativity, shedding light on both the strengths and limitations of LLMs in fostering mathematical innovation, and setting the stage for future developments in AI-assisted mathematical discovery.

The management of heavy traffic demands has been significantly improved by employing synchronized traffic signal control at multiple intersections. Multi-agent Reinforcement Learning (MARL) techniques have been widely utilized to achieve this coordination. However, these approaches predominantly depend on manually crafted features from adjacent intersections, which impedes their generalization to new scenarios. Furthermore, while displaying high accuracy for specific traffic flow patterns, these methods often lack the necessary robustness for other patterns. In this study, our objective is to develop an effective signal timing plan by directly learning the minimal required communication between intersections from traffic data. We introduce a novel, comprehensive approach that combines multi-agent reinforcement learning with a learned communication mechanism. Our model incorporates a coordinated actor network and a centralized critic network to address the challenges of non-stationarity. We conducted extensive experiments comparing our model with other commonly used non-RL and benchmark MARL techniques. The evaluation results show that our proposed model, which relies only on local sensory input and a single message from neighboring intersections, excels in managing various traffic flow patterns. Furthermore, our model outperforms competing approaches in terms of robustness, resilience, and overall performance.

Virtual Reality (VR) headsets, while integral to the evolving digital ecosystem, present a critical challenge: the occlusion of users' eyes and portions of their faces, which hinders visual communication and may contribute to social isolation. To address this, we introduce RevAvatar, an innovative framework that leverages AI methodologies to enable reverse pass-through technology, fundamentally transforming VR headset design and interaction paradigms. RevAvatar integrates state-of-the-art generative models and multimodal AI techniques to reconstruct high-fidelity 2D facial images and generate accurate 3D head avatars from partially observed eye and lower-face regions. This framework represents a significant advancement in AI4Tech by enabling seamless interaction between virtual and physical environments, fostering immersive experiences such as VR meetings and social engagements. Additionally, we present VR-Face, a novel dataset comprising 200,000 samples designed to emulate diverse VR-specific conditions, including occlusions, lighting variations, and distortions. By addressing fundamental limitations in current VR systems, RevAvatar exemplifies the transformative synergy between AI and next-generation technologies, offering a robust platform for enhancing human connection and interaction in virtual environments.

Junyi Ye, Ankan Dash, Wenpeng Yin, Guiling Wang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Camouflaged Object Detection (COD) aims to segment objects resembling their environment. To address the challenges of extensive annotations and complex optimizations in supervised learning, recent prompt-based segmentation methods excavate insightful prompts from Large Vision-Language Models (LVLMs) and refine them using various foundation models. These are subsequently fed into the Segment Anything Model (SAM) for segmentation. However, due to the hallucinations of LVLMs and insufficient image-prompt interactions during the refinement stage, these prompts often struggle to capture well-established class differentiation and localization of camouflaged objects, resulting in performance degradation. To provide SAM with more informative prompts, we present UpGen, a pipeline that prompts SAM with generative prompts without requiring training, marking a novel integration of generative models with LVLMs. Specifically, we propose the Multi-Student-Single-Teacher (MSST) knowledge integration framework to alleviate hallucinations of LVLMs. This framework integrates insights from multiple sources to enhance the classification of camouflaged objects. To enhance interactions during the prompt refinement stage, we are the first to leverage generative models on real camouflage images to produce SAM-style prompts without fine-tuning. By capitalizing on the unique learning mechanism and structure of generative models, we effectively enable image-prompt interactions and generate highly informative prompts for SAM. Our extensive experiments demonstrate that UpGen outperforms weakly-supervised models and its SAM-based counterparts. We also integrate our framework into existing weakly-supervised methods to generate pseudo-labels, resulting in consistent performance gains. Moreover, with minor adjustments, UpGen shows promising results in open-vocabulary COD, referring COD, salient object detection, marine animal segmentation, and transparent object segmentation.

Efforts to predict stock market outcomes have yielded limited success due to the inherently stochastic nature of the market, influenced by numerous unpredictable factors. Many existing prediction approaches focus on single-point predictions, lacking the depth needed for effective decision-making and often overlooking market risk. To bridge this gap, we proposeRAGIC, a novel risk-aware framework for stockintervalprediction to quantify uncertainty. Our approach leverages a Generative Adversarial Network (GAN) to produce future price sequences infused with randomness inherent in financial markets.RAGIC’s generator detects the risk perception of informed investors and captures historical price trends globally and locally. Then therisk-sensitive intervalsis built upon the simulated future prices from sequence generation through statistical inference, incorporatinghorizon-wiseinsights. The interval’s width is adaptively adjusted to reflect market volatility. Importantly, our approach relies solely on publicly available data and incurs only low computational overhead.RAGIC’s evaluation across globally recognized broad-based indices demonstrates its balanced performance, offering both accuracy and informativeness. Achieving a consistent 95% coverage,RAGICmaintains a narrow interval width. This promising outcome suggests that our approach effectively addresses the challenges of stock market prediction while incorporating vital risk considerations.

Edge intelligence enables resource-demanding Deep Neural Network (DNN) inference without transferring original data, addressing concerns about data privacy in consumer Inter-net of Things (IoT) devices. For privacy-sensitive applications, deploying models in hardware-isolated trusted execution environments (TEEs) becomes essential. However, the limited secure memory in TEEs poses challenges for deploying DNN inference, and alternative techniques like model partitioning and offloading introduce performance degradation and security issues. In this paper, we present a novel approach for advanced model deployment in TrustZone that ensures comprehensive privacy preservation during model inference. We design a memory-efficient management method to support memory-demanding inference in TEEs. By adjusting the memory priority, we effectively mitigate memory leakage risks and memory overlap conflicts, resulting in 32 lines of code alterations in the trusted operating system. Additionally, we leverage two tiny libraries: S-Tinylib (2,538 LoCs), a tiny deep learning library, and Tinylibm (827 LoCs), a tiny math library, to support efficient inference in TEEs. We implemented a prototype on Raspberry Pi 3B+ and evaluated it using three well-known lightweight DNN models. The experimental results demonstrate that our design significantly improves inference speed by 3.13 times and reduces power consumption by over 66.5% compared to non-memory optimization method in TEEs.

The Finance Day at KDD 2024 will take place on August 26th in Barcelona, Spain. Following the success of the inaugural event last year, the second edition highlights the significant role of AI in transforming the financial industry. This special day serves as a forum for discussion of innovations at the intersection of AI and finance. An exciting lineup of 12 influential speakers from nine different countries will be featured, representing a mix of government organizations, leading banks, innovative hedge funds, and top academic institutions. These experts will delve into a range of topics, from cutting-edge FinTech innovations to ethical considerations in machine learning, providing a comprehensive overview of the finance and AI. The distinguished speakers include Avanidhar Subrahmanyam from UCLA, Henrike Mueller from the Financial Conduct Authority, Claudia Perlich from Two Sigma, Eyke Hüllermeier from Ludwig-Maximilians-Universität München, Senthil Kumar from Capital One, Stefan Zohren from the University of Oxford, Dumitru Roman from SINTEF ICT, Kubilay Atasu from TU Delft, Xiao-Ming Wu from Hong Kong Polytechnic University, Yongjae Lee from UNIST, Jundong Li from the University of Virginia, and Milos Blagojevic from BlackRock.

Summary Recently, Kubernetes is widely used to manage and schedule the resources of microservices in cloud‐native distributed applications, as the most famous container orchestration framework. However, Kubernetes preferentially schedules microservices to nodes with rich and balanced CPU and memory resources on a single node. The native scheduler of Kubernetes, called Kube‐scheduler, may cause resource fragmentation and decrease resource utilization. In this paper, we propose a deep reinforcement learning enhanced Kubernetes scheduler named DRS. We initially frame the Kubernetes scheduling problem as a Markov decision process with intricately designed state , action , and reward structures in an effort to increase resource usage and decrease load imbalance. Then, we design and implement DRS mointor to perceive six parameters concerning resource utilization and create a thorough picture of all available resources globally. Finally, DRS can automatically learn the scheduling policy through interaction with the Kubernetes cluster, without relying on expert knowledge about workload and cluster status. We implement a prototype of DRS in a Kubernetes cluster with five nodes and evaluate its performance. Experimental results highlight that DRS overcomes the shortcomings of Kube‐scheduler and achieves the expected scheduling target with three workloads. With only 3.27% CPU overhead and 0.648% communication delay, DRS outperforms Kube‐scheduler by 27.29% in terms of resource utilization and reduces load imbalance by 2.90 times on average.

Traffic signal control is safety-critical for our daily life. Roughly one-quarter of road accidents in the U.S. happen at intersections due to problematic signal timing, urging the development of safety-oriented intersection control. However, existing studies on adaptive traffic signal control using reinforcement learning technologies have focused mainly on minimizing traffic delay but neglecting the potential exposure to unsafe conditions. We, for the first time, incorporate road safety standards as enforcement to ensure the safety of existing reinforcement learning methods, aiming toward operating intersections with zero collisions. We have proposed a safety-enhanced residual reinforcement learning method (SafeLight) and employed multiple optimization techniques, such as multi-objective loss function and reward shaping for better knowledge integration. Extensive experiments are conducted using both synthetic and real-world benchmark datasets. Results show that our method can significantly reduce collisions while increasing traffic mobility.

The rapid development of intelligent transportation systems and connected vehicles has highlighted the need for secure and efficient key management systems (KMS). In this paper, we introduce VDKMS (Vehicular Decentralized Key Management System), a novel Decentralized Key Management System designed specifically as an infrastructure for Cellular Vehicular-to-Everything (V2X) networks, utilizing a blockchain-based approach. The proposed VDKMS addresses the challenges of secure communication, privacy preservation, and efficient key management in V2X scenarios. It integrates blockchain technology, Self-Sovereign Identity (SSI) principles, and Decentralized Identifiers (DIDs) to enable secure and trustworthy V2X applications among vehicles, infrastructures, and networks. We first provide a comprehensive overview of the system architecture, components, protocols, and workflows, covering aspects such as provisioning, registration, verification, and authorization. We then present a detailed performance evaluation, discussing the security properties and compatibility of the proposed solution, as well as a security analysis. Finally, we present potential applications in the vehicular ecosystem that can leverage the advantages of our approach.

In watermarking, the watermark embedding strength is crucial, and the introduction of the strength factor can adjust the trade-off between the quality of the encoded image and the accuracy of the recovered message, thus enabling good imperceptibility and robustness of the encoded image. In traditional watermarking methods, the strength factor is selected in relation to the cover image, and based on different images, different strength factors are manually selected or algorithmically derived to adjust the visual effect of the watermarked image. However, due to the subjectivity and inflexibility of traditional algorithms, they can not achieve the effect of adaptive adjustment of watermarked images. Recently, watermarking methods combined with deep learning have gradually occupied the mainstream of this field. In the testing stage, to balance the overall robustness and imperceptibility, the strength factor is no longer selected based on the cover image as in traditional methods. Instead, it is set to a universal value. Therefore, the watermarking method based on deep learning is still in the primary stage of the trial-and-error method. To solve the subjectivity of the hand-designed embedding strength algorithm of the traditional watermarking methods and the low elasticity of the strength factor of the learning method so as to realize the adaptive embedding of watermarks, we propose an adaptive watermarking method with separate training. The proposed method adds a new component, the Adaptor, compared to other frameworks. The Adaptor can adaptively select strength factors to control the embedding strength of the watermark relying on the cover image and secret message. A two-stage training method is used to maintain the stability of the training and to achieve the best results for each component. With the results obtained from our experiments, our proposed method can find the appropriate strength factor and optimize it, resulting in improved robustness and imperceptibility of the watermark. The proposed method shows better results compared to the current state-of-the-art algorithms.

Peer-to-peer (P2P) content delivery is up-and-coming to provide benefits comprising cost-saving and scalable peak-demand handling compared with centralized content delivery networks (CDNs), and also complementary to the popular decentralized storage networks such as Filecoin. However, reliable P2P delivery demands proper enforcement of delivery fairness, i.e., the deliverers should be rewarded in line with their in-time delivery. Unfortunately, most existing studies on delivery fairness are on the basis of non-cooperative game-theoretic assumptions that are arguably unrealistic in the ad-hoc P2P setting. We propose an expressive yet still minimalist security requirement for desired fair P2P content delivery, and give two efficient blockchain-enabled and monetary-incentivized solutions${\mathsf {FairDownload}}$and${\mathsf {FairStream}}$for P2P downloading and P2P streaming scenarios, respectively. Our designs not only ensure delivery fairness where deliverers are paid (nearly) proportional to their in-time delivery, but also guarantee exchange fairness where content consumers and content providers are also fairly treated. The fairness of each party can be assured even when other two parties collude to arbitrarily misbehave. Our protocols provide a general design of fetching content chunk from any specific position so the delivery can be resumed in the presence of unexpected interruption. Further, our systems are efficient in the sense of achieving asymptotically optimal on-chain costs and optimal delivery communication. We implement the prototype and deploy on the Ethereum Ropsten network. Extensive experiments in both LAN and WAN settings are conducted to evaluate the on-chain costs as well as the efficiency of downloading and streaming. Experimental results show the practicality and efficiency of our protocols.

Blockchain-based Internet of Things (BC-IoT) brings the advantages of blockchain into traditional IoT systems. In BC-IoT, the smart contract has been widely used for automatic, trusted, and decentralized applications. Smart contracts require frequent adjust and fast update due to various reasons, such as inevitable code bugs, changes of applications, or security requirements. However, previous smart contract architecture and updating mechanism are low speed and cause high overhead, because they are based on recompilation and redeployment in BC-IoT. Meanwhile, smart contract execution is so time consuming due to contract instruction dispatching and operand loading in the stack-based Ethereum virtual machine (EVM). To address these issues, we propose a new smart contract architecture and optimization mechanism for BC-IoTs, ATOM, which provides architectural supports to update contract economically and fast executing in instructionwise for the first time, to the best of our knowledge. We design a compact Application-oriented Instruction (AoI) set to describe application operations. We can construct the bytecode of smart contract from application by directly assembling templates prebuilt upon the AoIs rather than by compilation. We also present an optimized mechanism for AoI execution to enable access addressable storage place rather than the indirect access through stack. We perform ATOM on a BC-IoT testbed based on private Ethereum and Hyperledger Burrow. The experimental results highlight that ATOM is more efficient than state-of-the-art approaches. ATOM can reduce update latency by 62.7%, ledger size by 70%, and gas usage by 90% on average, respectively. Compared with the traditional smart contract architecture, ATOM can improve EVM Memory access efficiency significantly by up to$10\times $and achieve improvement of execution efficiency with up to$1.6\times $.

Though the retailer gift card has been an ultra-practical marketing tactic to attract customers to spend more, it, on the contrary, also places a great number of customers in troublesome situations due to its current limitations. First, dealing with unwanted gift cards is often time-consuming, costly, or even risky due to the frequent occurrences of gift card resale frauds. Worse still, the issuance and redemption of gift cards happen inside the retailer as in a “black-box,” indicating that a compromised retailer can cheat customers (or even third-party auditors) to deny the issuances of some unredeemed gift cards. This paper proposes a practical middle-layer solution based on blockchain to address the fundamental issues of the existing gift card system, with incurring minimal changes to the current infrastructure.

A fundamental open question for oracles in blockchain environments is a determination of the amount of trust to be placed in the oracle. Oracles serve as intermediaries between a trusted blockchain environment and the untrusted external environment from where the oracles fetch data. As such, it is important to understand the uncertainty introduced by the oracle in the trusted blockchain environment and the implications of this uncertainty on blockchain performance. This paper develops a model for commoditization of trust. The model provides for dynamic trust environments that incorporates oracle selfishness. The work also considers the equilibrium behavior for the demand and supply for trust and introduces elastic incentives for increasing the trust. These results are used to determine optimum size of the network that can be served by an oracle with varying degrees of selfishness. Key consequences and challenges of incorporating oracles in trusted distributed ledger environments are presented.

With the rapid popularity of blockchain, decentralized human intelligence tasks (HITs) are proposed to crowdsource human knowledge without relying on vulnerable third-party platforms. However, the inherent limits of blockchain cause decentralized HITs to face a few "new" challenges. For example, the confidentiality of solicited data turns out to be the sine qua non, though it was an arguably dispensable property in the centralized setting. To ensure the "new" requirement of data privacy, existing decentralized HITs use generic zero-knowledge proof frameworks (e.g., SNARK), but scarcely perform well in practice, due to the inherently expensive cost of generality.We present a practical decentralized protocol for HITs, which also achieves the fairness between requesters and workers. At the core of our contributions, we avoid the powerful yet highlycostly generic zk-proof tools and propose a special-purpose scheme to prove the quality of encrypted data. By various nontrivial statement reformations, proving the quality of encrypted data is reduced to efficient verifiable decryption, thus making decentralized HITs practical. Along the way, we rigorously define the ideal functionality of decentralized HITs and then prove the security due to the ideal/real paradigm.We further instantiate our protocol to implement a system called Dragoon1, an instance of which is deployed atop Ethereum to facilitate an image annotation task used by ImageNet. Our evaluations demonstrate its practicality: the on-chain handling cost of Dragoon is even less than the handling fee of Amazon's Mechanical Turk for the same ImageNet HIT.

Multi-valued validated asynchronous Byzantine agreement (MVBA), proposed in the elegant work of Cachin et al. (CRYPTO '01), is fundamental for critical fault-tolerant services such as atomic broadcast in the asynchronous network. It was left as an open problem to asymptotically reduce the O(ℓn2 + λn2 + n3) communication (where n is the number of parties, ℓ is the input length, and λ is the security parameter). Recently, Abraham et al. (PODC '19) removed the n3 term to partially answer the question when input is small. However, in other typical cases, e.g., building atomic broadcast through MVBA, the input length ℓ ≥ λn, and thus the communication is dominated by the ℓn2 term and the problem raised by Cachin et al. remains open.

Understanding people's transportation modes is beneficial for empowering many intelligent transportation systems, such as supporting urban transportation planning. Yet, current methodologies in collecting travelers' transportation modes are costly and inaccurate. Fortunately, the increasing sensing and computing capabilities of smartphones and their high penetration rate offer a promising approach to automatic transportation mode detection via mobile computation. This paper introduces a light-weighted and energy-efficient transportation mode detection system using only accelerometer sensors in smartphones. The system collects accelerometer data in an efficient way and leverages a deep learning model to determine transportation modes. Different architectures and classification methods are tested with the proposed deep learning model to optimize the system design. Performance evaluation shows that the proposed new approach achieves a better accuracy than existing work in detecting people's transportation modes.

Traditional embedding approaches associate a real-valued embedding vector with each symbol or data point, which is equivalent to applying a linear transformation to ``one-hot" encoding of discrete symbols or data objects. Despite simplicity, these methods generate storage-inefficient representations and fail to effectively encode the internal semantic structure of data, especially when the number of symbols or data points and the dimensionality of the real-valued embedding vectors are large. In this paper, we propose a regularized autoencoder framework to learn compact Hierarchical K-way D-dimensional (HKD) discrete embedding of symbols or data points, aiming at capturing essential semantic structures of data. Experimental results on synthetic and real-world datasets show that our proposed HKD embedding can effectively reveal the semantic structure of data via hierarchical data visualization and greatly reduce the search space of nearest neighbor retrieval while preserving high accuracy.

In spite of its importance, passenger demand prediction is a highly challenging problem, because the demand is simultaneously influenced by the complex interactions among many spatial and temporal factors and other external factors such as weather. To address this problem, we propose a Spatio-TEmporal Fuzzy neural Network (STEF-Net) to accurately predict passenger demands incorporating the complex interactions of all known important factors. We design an end-to-end learning framework with different neural networks modeling different factors. Specifically, we propose to capture spatio-temporal feature interactions via a convolutional long short-term memory network and model external factors via a fuzzy neural network that handles data uncertainty significantly better than deterministic methods. To keep the temporal relations when fusing two networks and emphasize discriminative spatio-temporal feature interactions, we employ a novel feature fusion method with a convolution operation and an attention layer. As far as we know, our work is the first to fuse a deep recurrent neural network and a fuzzy neural network to model complex spatial-temporal feature interactions with additional uncertain input features for predictive learning. Experiments on a large-scale real-world dataset show that our model achieves more than 10% improvement over the state-of-the-art approaches.

In today's society, there are plenty of services available, and customers are facing bigger challenge in choosing them than ever before. Therefore, it is important to build a reliable reputation mechanism for selecting a credible service. To address the challenges of reputation evaluation, including the diverse and dynamic natures of services, incompleteness of user feedback, and intricacy of malicious ratings, a High-reliability Multi-faceted Reputation evaluation mechanism for online services (HMRep) is proposed. First, HMRep starts with addressing the incomplete feedback and estimates missing ratings based on both the service quality and a user's rating behavior. Second, HMRep identifies and removes malicious collusive raters and irresponsible raters to improve the accuracy of reputation calculation. Further, the reputation calculation is based on the user credibility and incorporates historical information to reflect the change of the services. Finally, we provide a multi-faceted evaluation method to satisfy some specific needs of customers who are only concerned about a subset of a services features. Experimental results verify the design of HMRep, and reveal HMRep can effectively defend against malicious ratings, and accurately calculate the reputation values of services. HMRep can be applied in lots of sectors for different kinds of services, especially those complex ones.

We design and implement the first private and anonymous decentralized crowdsourcing system ZebraLancer, and overcome two fundamental challenges of decentralizing crowdsourcing, i.e. data leakage and identity breach. First, our outsource-then-prove methodology resolves the tension between blockchain transparency and data confidentiality, which is critical in crowdsourcing use-case. ZebraLancer ensures: (i) a requester will not pay more than what data deserve, according to a policy announced when her task is published via the blockchain; (ii) each worker indeed gets a payment based on the policy, if he submits data to the blockchain; (iii) the above properties are realized not only without a central arbiter, but also without leaking the data to the open blockchain. Furthermore, the transparency of blockchain allows one to infer private information about workers and requesters through their participation history. On the other hand, allowing anonymity will enable a malicious worker to submit multiple times to reap rewards. ZebraLancer overcomes this problem by allowing anonymous requests/submissions without sacrificing the accountability. The idea behind is a subtle linkability: if a worker submits twice to a task, anyone can link the submissions, or else he stays anonymous and unlinkable across tasks. To realize this delicate linkability, we put forward a novel cryptographic concept, i.e. the common-prefix-linkable anonymous authentication. We remark the new anonymous authentication scheme might be of independent interest. Finally, we implement our protocol for a common image annotation task and deploy it in a test net of Ethereum. The experiment results show the applicability of our protocol with the existing real-world blockchain.

Improving safety and convenience is always the top priority in designing today's intelligent transportation system. In this paper, we study the problem of how to manage vehicle traffic at intersections by jointly considering safety, driver's comfort, and efficiency, in vehicular ad hoc networks. We propose a distributed intersection management protocol (DIMP), which distributedly coordinates vehicle traffic from different directions by making vehicles exchange critical driving information and adaptively react based on the information. DIMP dynamically guides vehicles to adjust their speed in a way such that both safety and driver's comfort are satisfied. By following DIMP, vehicles can pass the intersections safely and efficiently at a comfortable speed during acceleration/deceleration. We extensively evaluate DIMP, and the evaluation results show that DIMP is both effective and efficient in managing vehicle traffic at intersections.

Knowledge of people's transportation mode is important in many civilian areas, such as urban transportation planning. Current methodologies in collecting travelers' transportation modes are costly and inaccurate. The increasing sensing and computing capabilities of smartphones and their high penetration rate enable automatic transportation mode detection. This paper designs and implements a light-weight and energy-efficient transportation mode detection application only using the accelerometer sensor on smartphones. In this application, we collect accelerometer data in an efficient way and build a convolutional neural network to determine transportation modes. Different architectures and different classification methods are tested within our convolutional neutral networks in our tests and the best combination is selected for this transportation mode detection application. Performance evaluation shows that the proposed convolutional neural network can achieve the highest accuracy in detecting transportation modes.

Scalable and diagnosable are the two most crucial needs for voice call quality assessment in mobile networks. However, while these two requirements are widely accepted by mobile carriers, they do not receive enough attention during the development. Current related research mainly focuses on audio feature analysis, which is costly, sensitive to language and tones, and infeasible to be applied to large-scale mobile networks. In this paper, we revisit this problem, and for the first time explore wireless network, the causal factor that directly impacts the mobile voice quality but yet lacks attention for decades. We design CrowdMi, a wireless analytical tool that model the mobile voice quality by crowdsourcing and mining the network indicators of cellphones. CrowdMi mines hundreds of network indicators to build a causal relationship between voice quality and network conditions, and carefully calibrates the model according to the widely accepted perceptual objective listening quality assessment (POLQA) voice assessment standard. We implement a light-load CrowdMi Client App in Android smartphones, which automatically collects data through user crowdsourcing and outputs to the CrowdMi Server in our data center that runs the mining algorithm. We conduct a pilot trial in VoLTE network in different geographical areas and network coverages. The trial shows that the CrowdMi does not require any additional hardware or human effort, and has very high model accuracy and strong diagnosability.

Sensor nodes deployed outdoors are subject to environmental detriments and often need to cache data for an extended period of time. This paper introduces sensor nodes which are robust to environmental damages, and proposes to utilize Network Coding to back up data in the robust sensors for future data retrieval in an energy efficient way. Our goal is to help regular sensors select robust sensors to back up their data with low energy consumption, such that when needed, all the data can be retrieved by querying only a subset of robust sensors. We formally formulate this backup problem, theoretically prove its NP-Completeness, discover two novel theoretical guidelines for problem solving, and propose two algorithms accordingly to tackle this NP-C problem. The guidelines are based on random linear network coding and provide lower bounds of the number of robust sensors that each regular sensor should choose for data backup, such that the required fault tolerance is provided. A centralized algorithm and a distributed algorithm are developed based on the guidelines such that regular sensors can back up their data efficiently. Both analysis and simulation show our algorithms are effective in achieving fault tolerance, low energy consumption, and high retrieval efficiency.

Sensor nodes deployed outdoors for field surveillance are subject to environmental detriments. In this article, we propose a heterogeneous sensor network composed of sensor nodes with different environmental survivability to make it robust to environmental damage and keep it at a reasonable cost. We, for the first time, study the scheduling problem in such heterogeneous sensor networks for critical location surveillance applications. Our goal is to monitor all the critical points for as long as possible under different environmental conditions. We identify the underlying problem, theoretically prove its NP-complete nature, and propose a novel adaptive greedy scheduling algorithm to solve the problem. The algorithm incorporates several heuristics to schedule the activity of both regular and robust sensors to monitor all the critical points, while at the same time minimizing and balancing the network energy consumption. Simulation results show that our algorithm efficiently solves the problem and outperforms other alternatives.

Nowadays, distracted driving is becoming a very dangerous epidemic on the roadways. A lot of activities may lead to distracted driving, such as texting, making phone calls, using GPS or road maps, eating, using in-car entertainment systems, etc. As the number of smartphones is rapidly growing year by year, using smartphone is by far the most dangerous and alarming driver distraction. In this paper, we design an app on iPhone for reducing the smartphone-related distracted driving, which can run in the background and can lock the smartphone screen with no passwords required when it detects that the user is driving. After the user finishes driving, the lock will be removed immediately. We also describe a DTM algorithm to detect the transportation mode and give the performance analysis of our system. The results show that our system can save more energy than other related applications.

GPS navigators have been widely adopted by drivers. However, due to the sensibility of GPS signals to terrain, vehicles cannot get their locations when they are inside a tunnel or on a road surrounded by high-rises where satellite signal is blocked. This incurs safety and convenience problems. To address the issue, we propose a novel Grid-based On-road localizaTion system (GOT), where vehicles with and without accurate GPS signals self-organize into a Vehicular Ad Hoc Network (VANET), exchange location and distance information and help each other to calculate an accurate position for all the vehicles inside the network. The location information can be exchanged among vehicles one or multiple hops away in this paper. We explore fuzzy geometric relationship among vehicles, and apply a novel grid-based mechanism to evaluate the geometric relationships and calculate vehicle locations. Simulation shows our GOT system is effective and efficient in calculating vehicular positions.

Existing multipath routing protocols for MANET ignore the topology-exposure problem. This paper analyzes the threat of topology-exposure and proposes a Topology-Hiding Multipath Routing protocol (THMR). THMR doesn't allow packets to carry routing information, so malicious nodes cannot deduce topology information and launch various attacks based on that. The protocol can also establish multiple node-disjoint routes in a route discovery attempt and exclude unreliable routes before transmitting packets. We formally prove that THMR is loop-free and topology-hiding. Simulation results show that our protocol has better capability of finding routes and can greatly increase the capability of delivering packets in the scenario where there are attackers at the cost of low routing overhead.

Efficient data dissemination to a fixed number of receivers in VANET is a new issue and is challenging considering the dynamic nature of VANET. We aim to accurately control the number of receivers, achieve low dissemination delay and incur only small communication overhead. To achieve the goal, we design DOVE (Data Dissemination to A Fixed Number of Receivers in VANET) inspired by processor scheduling, which treats roads as processors to optimize the workload assignment and improves the efficiency of on-road dissemination. DOVE reaches the desired number of receivers with little inaccuracy and minimizes the dissemination delay with low communication overhead. We enhance our protocol with workload backup to deal with vehicles' quitting the network. We utilize the unique characteristics of VANET and propose heuristics accordingly to significantly reduce the dissemination delay and overhead. Simulation results show that our scheme disseminates data to all the pre-given number of receivers in a very light overhead and low delay.

Packet dropping and modification are common attacks that can be launched by an adversary to disrupt communication in wireless multihop sensor networks. Many schemes have been proposed to mitigate or tolerate such attacks, but very few can effectively and efficiently identify the intruders. To address this problem, we propose a simple yet effective scheme, which can identify misbehaving forwarders that drop or modify packets. Extensive analysis and simulations have been conducted to verify the effectiveness and efficiency of the scheme.

When wireless sensors are deployed to monitor the working or life conditions of people, the data collected and processed by these sensors may reveal privacy of people. The actual content of sensory data should be concealed to preserve the privacy, but the data concealment feature may be abused by compromised sensors to modify or ill-process data without being caught. Hence, reconciling privacy preservation and intrusion detection, which apparently conflict with each other, is important. This paper studies this problem in the context of sensory data aggregation, a fundamental primitive for efficient operation of sensor networks. A scheme is proposed that can detect ill-performed aggregation without knowing the actual content of sensory data, and therefore allow sensory data to be kept concealed. The results show that, the actual content of raw and aggregated sensory data can be well concealed. Meanwhile, most of ill-performed aggregations can be detected; the ill-performed aggregations that can escape from being detected have only negligible impact on the final aggregation results.

Improving driving safety is one major objective of forming vehicular ad hoc networks (VANETs). Existing VANETs usually assume drivers detect and report safety-related road conditions. However, drivers may not be willing to perform these duties; even they are, these duties may distract them from driving and thus make driving unsafe. To address the problem, this paper proposes an automatic detection system. By taking advantage of the communication capability of roadside sensors, the proposed system can automatically detect and locate problematic road conditions without any human intervention under varying traffic densities. Extensive simulations have been conducted to verify the efficiency of the proposed system.

GPS navigators have been widely adopted by drivers. However, due to the sensibility of GPS signals to terrain, vehicles cannot get their locations when they are inside a tunnel or on a road surrounded by high-rises where the satellite signal is blocked. This incurs the safety and convenience problems. To address the issue, we propose a novel Grid-based On-road localizaTion system (GOT), where vehicles with or without accurate GPS signals self-organize into a vehicular ad hoc network (VANET), exchange location and distance information and help each other to calculate an accurate position for all the vehicles inside the network. GOT uniquely evaluates some fuzzy geometric relationship among vehicles and employs a grid-based approach to calculate vehicle's locations, by which GOT solves the issues of lack of beacon nodes and error propagation that are the two major challenges in on-road localization. Simulation shows our GOT system is very effective and efficient in calculating the vehicular positions.

Conserving the energy for motion is an important yet not-well-addressed problem in mobile sensor networks. In this article, we study the problem of optimizing sensor movement for energy efficiency. We adopt a complete energy model to characterize the entire energy consumption in movement. Based on the model, we propose an optimal trapezoidal velocity schedule for minimizing energy consumption when the road condition is uniform; and a corresponding velocity schedule for the variable road condition by using continuous-state dynamic programming. Considering the variety in motion hardware, we also design one velocity schedule for simple microcontrollers, and one velocity schedule for relatively complex microcontrollers, respectively. Simulation results show that our velocity planning may have significant impact on energy conservation.

When deployed for long-term tasks, the energy required to support sensor nodes' activities is far more than the energy that can be preloaded in their batteries. No matter how the battery energy is conserved, once the energy is used up, the network life terminates. Therefore, guaranteeing long-term energy supply has persisted as a big challenge. To address this problem, we propose a node reclamation and replacement (NRR) strategy, with which a mobile robot or human labor called mobile repairman (MR) periodically traverses the sensor network, reclaims nodes with low or no power supply, replaces them with fully charged ones, and brings the reclaimed nodes back to an energy station for recharging. To effectively and efficiently realize the strategy, we develop an adaptive rendezvous-based two-tier scheduling scheme (ARTS) to schedule the replacement/reclamation activities of the MR and the duty cycles of nodes. Extensive simulations have been conducted to verify the effectiveness and efficiency of the ARTS scheme.

As wireless power charging technology emerges, some basic principles in sensor network design are changed accordingly. Existing sensor node deployment and data routing strategies cannot exploit wireless charging technology to minimize overall energy consumption. Hence, in this paper, we (a) investigate the impact of wireless charging technology on sensor network deployment and routing arrangement, (b) formalize the deployment and routing problem, (c) prove it as NP-complete, (d) develop heuristic algorithms to solve the problem, and (e) evaluate the performance of the solutions through extensive simulations. To the best of our knowledge, this is the first effort on adapting sensor network design to leverage wireless charging technology.

To address energy constraint problem in sensor networks, node reclamation and replacement strategy has been proposed for networks accessible to human beings and robots. The major challenge in realizing the strategy is how to minimize the system maintenance cost, especially the frequency in replacing sensor nodes with limited number of backup nodes. New duty cycle scheduling schemes are required in order to address the challenge. Tong et al. have proposed a staircase-based scheme to address the problem based on ideal assumptions of sensor nodes that are free of failure and have regular energy consumption rate. Since sensor nodes are often deployed in outdoor unattended environment, node failures are inevitable. Energy consumption rates of sensor nodes are irregular due to manufacture or environmental reasons. Hence, this paper proposes several new schemes to achieve reliable scheduling for node reclamation and replacement. Extensive simulations have been conducted to verify that the proposed scheme is effective and efficient.

One major goal of the vehicular ad hoc network (VANET) is to improve driving safety. However, the VANET may not guarantee timely detection of dangerous road conditions or maintain communication connectivity when the network density is low (e.g., in rural highways), which may pose as a big threat to driving safety. Towards addressing the problem, we propose to integrate the VANET with the inexpensive wireless sensor network (WSN). That is, sensor nodes are deployed along the roadside to sense road conditions, and to buffer and deliver information about dangerous conditions to vehicles regardless of the density or connectivity of the VANET. Along with the concept of VANET-WSN integration, new challenges arise and should be addressed. In this paper, we investigate these challenges and propose schemes for effective and efficient vehicle-sensor and sensor-sensor interactions. Prototype of the designed system has been implemented and tested in the field. Extensive simulations have also been conducted to evaluate the designed schemes. The results demonstrate various design tradeoffs, and indicate that satisfactory safety and energy efficiency can be achieved simultaneously when system parameters are appropriately chosen.

The authors study the design of heterogeneous two-tier wireless sensor networks (WSNs), where one tier of nodes is more robust and computationally intensive than the other tier. The authors find the ratios of densities of nodes in each tier to maximise coverage and network lifetime. By employing coverage processes and optimisation theory, the authors show that any topology of WSN derived from random deployments can result in maximum coverage for the given node density and power constraints by satisfying a set of conditions. The authors show that network design in heterogeneous WSNs plays a key role in determining key network performance parameters such as network lifetime. The authors discover a functional relationship between the redundancy, density of nodes in each tier for active coverage and the network lifetime. This relationship is much less pronounced in the absence of heterogeneity. The results of this work can be applied to network design of multi-tier networks and for studying the optimal duty cycles for power saving states for nodes in each tier.

This article studies clustered wireless sensor networks (WSNs), a realistic topology resulting from common deployment methods. We study coverage in naturally clustered networks of wireless sensor nodes, as opposed to WSNs where clustering is facilitated by selection. We show that along with increasing the vacancy in random placement of nodes in a WSN, it also alters the connectivity properties in the network. We analyze varying levels of redundancy to determine the probability of coverage in the network. The phenomenon of clustering in networks of wireless sensor nodes raises interesting questions for future research and development. The article provides a foundation for the design to optimize network performance with the constraint of sensing coverage.

Hierarchical architectures are more and more widely adopted for organizing wireless sensor networks. In such architectures, middle-tier nodes take important roles, and preventing a malicious node from impersonating a middle-tier node and injecting falsified messages becomes critical. In this paper, we propose an energy efficient, distributed scheme to secure the multicast messages from the middle-tier nodes. Our scheme does not require a priori knowledge about the hierarchical relation between middle-tier nodes and lowest-tier nodes, and is adaptive to changes of this relation. Extensive simulations are conducted to evaluate our scheme, and the results show that the scheme is energy efficient.

To deal with the problem of hostile environments, we proposed to construct heterogeneous sensor networks composed of both regular nodes and robust nodes, where robust nodes are better equipped for hostile environments and hence are more expensive than regular nodes. We study the problem of network design in heterogeneous wireless sensor networks that involves optimization of network costs associated with different classes of nodes versus maximizing coverage and network lifetime. We consider the design of heterogeneous networks with the objectives of minimizing costs and maximizing network lifetime. The association we present in heterogeneous sensor network design between optimizing the number of nodes in each class with cost constraints and network lifetime for corresponding network composition maybe of independent interest in the design of networks in general.

When deployed for long-term tasks, the energy required to support sensor nodes' activities is far more than the energy that can be preloaded in their batteries. No matter how the battery energy is conserved, once the energy is used up, the network life terminates. Therefore, guaranteeing long- term energy supply has persisted as a big challenge. To address this problem, we propose a node replacement and reclamation (NRR) strategy, with which a mobile robot or human labor called mobile repairman (MR) periodically traverses the sensor network, reclaims nodes with low or no power supply, replaces them with fully-charged ones, and brings the reclaimed nodes back to an energy station for recharging. To effectively and efficiently realize the strategy, we develop an adaptive rendezvous- based two-tier scheduling (ARTS) scheme to schedule the replacement/reclamation activities of the MR and the duty cycles of nodes. Extensive simulations have been conducted to verify the effectiveness and efficiency of the ARTS scheme.

Packet dropping and modification are common attacks that can be launched by an adversary to disrupt communication in wireless multi-hop sensor networks. Many schemes have been proposed to mitigate the attacks but none can effectively and efficiently identify the intruders. To address the problem, we propose a simple yet effective scheme, which can identify misbehaving forwarders that drop or modify packets. Extensive analysis and simulations using ns2 simulator have been conducted and verified the effectiveness and efficiency of the scheme.

Numerous authentication schemes have been proposed in the past for protecting communication authenticity and integrity in wireless sensor networks. Most of them however have following limitations: high computation or communication overhead, no resilience to a large number of node compromises, delayed authentication, lack of scalability, etc. To address these issues, we propose in this paper a novel message authentication approach which adopts a perturbed polynomial-based technique to simultaneously accomplish the goals of lightweight, resilience to a large number of node compromises, immediate authentication, scalability, and non-repudiation. Extensive analysis and experiments have also been conducted to evaluate the scheme in terms of security properties and system overhead.

Constructing a sensor network with a mix of mobile and static sensors can achieve a balance between sensor coverage and sensor cost. In this paper, we design two bidding protocols to guide the movement of mobile sensors in such sensor networks to increase the coverage to a desirable level. In the protocols, static sensors detect coverage holes locally by using Voronoi diagrams and bid mobile sensors to move. Mobile sensors accept the highest bids and heal the largest holes. Simulation results show that our protocols achieve suitable trade-off between coverage and sensor cost

Abstract-Adequate coverage is very important for sensor networks to fulfill the issued sensing tasks. In many working environments, it is necessary to make use of mobile sensors, which can move to the correct places to provide the required coverage. In this paper, we study the problem of placing mobile sensors to get high coverage. Based on Voronoi diagrams, we design two sets of distributed protocols for controlling the movement of sensors, one favoring communication and one favoring movement. In each set of protocols, we use Voronoi diagrams to detect coverage holes and use one of three algorithms to calculate the target locations of sensors it holes exist. Simulation results show the effectiveness of our protocols and give insight on choosing protocols and calculation algorithms under different application requirements and working conditions.

Recently there has been a great deal of research on using mobility in sensor networks to assist in the initial deployment of nodes. Mobile sensors are useful in this environment because they can move to locations that meet sensing coverage requirements. This paper explores the motion capability to relocate sensors to deal with sensor failure or respond to new events. We define the problem of sensor relocation and propose a two-phase sensor relocation solution: redundant sensors are first identified and then relocated to the target location. We propose a Grid-Quorum solution to quickly locate the closest redundant sensor with low message complexity, and propose to use cascaded movement to relocate the redundant sensor in a timely, efficient and balanced way. Simulation results verify that the proposed solution outperforms others in terms of relocation time, total energy consumption, and minimum remaining energy.

Conserving the energy for motion is an important yet not-well-addressed problem in mobile sensor networks. In this paper, we study the problem of optimizing sensor movement for energy efficiency. We adopt a complete energy model to characterize the entire energy consumption in movement. Based on the model, we propose an optimal velocity schedule for minimizing energy consumption when the road condition is uniform; and a near optimal velocity schedule for the variable road condition by using continuous-state dynamic programming. Considering the variety in motion hardware, we also design one velocity schedule for simple microcontrollers, and one velocity schedule for relatively complex microcontrollers, respectively. Simulation results show that our velocity planning may have significant impact on energy conservation

Sensor deployment is an important issue in designing sensor networks. We design and evaluate distributed self-deployment protocols for mobile sensors. After discovering a coverage hole, the proposed protocols calculate the target positions of the sensors where they should move. We use Voronoi diagrams to discover the coverage holes and design three movement-assisted sensor deployment protocols, VEC (vector-based), VOR (Voronoi-based), and minimax based on the principle of moving sensors from densely deployed areas to sparsely deployed areas. Simulation results show that our protocols can provide high coverage within a short deploying time and limited movement.

To provide satisfactory coverage is very important in many sensor network applications such as military surveillance. In order to obtain the required coverage in harsh environments, mobile sensors are helpful since they can move to cover the area not reachable by static sensors. Previous work on mobile sensor deployment is based on a round by round process, where sensors move iteratively until the maximum coverage is reached. Although these solutions can deploy mobile sensors in a distributed way, the mobile sensors may move in a zig-zag way and waste a lot of energy compared to moving directly to the final location. To address this problem, we propose a proxy-based sensor deployment protocol. Instead of moving iteratively, sensors calculate their target locations based on a distributed iterative algorithm, move logically, and exchange new logical locations with their new logical neighbors. Actual movement only occurs when sensors determine their final locations. Simulation results show that the proposed protocol can significantly reduce the energy consumption compared to previous work, while maintaining similar coverage.

In some harsh environments, manually deploying sensors is impossible. Alternative methods may lead to imprecise placement resulting in coverage holes. To provide the required high coverage in these situations, we propose to deploy sensor networks composed of a mixture of mobile and static sensors in which mobile sensors can move from dense areas to sparse areas to improve the overall coverage. This paper presents a bidding protocol to assist the movement of mobile sensors. In the protocol, static sensors detect coverage holes locally by using Voronoi diagrams, and bid for mobile sensors based on the size of the detected hole. Mobile sensors choose coverage holes to heal based on the bid. Simulation results show that our algorithm provides suitable tradeoff between coverage and sensor cost.