Detecting text generated by Large Language Models (LLMs) is crucial, yet current detectors often struggle to generalize in open-world settings.We introduce Learning2Rewrite, a novel framework to detect LLM-generated text with exceptional generalization to unseen domains.Capitalized on the finding that LLMs inherently modify LLM-generated content less than human-written text when rewriting, we train an LLM to amplify this disparity, yielding a more distinguishable and generalizable edit distance across diverse text distributions.Extensive experiments on data from 21 independent domains and four major LLMs (GPT-3.5,GPT-4, Gemini, and Llama-3) demonstrate that our detector outperforms state-of-the-art detection methods by up to 23.04% in AU-ROC for in-distribution tests, 35.10% for outof-distribution tests, and 48.66% under adversarial attacks.Our unique training objective ensures better generalizability compared to directly training for classification, even when leveraging the same amount of tunable parameters.Our findings suggest that reinforcing LLMs' inherent rewriting tendencies offers a robust and scalable solution for detecting LLMgenerated text.

Weiliang Zhao, Daniel Ben-Levi, Wei Hao, Junfeng Yang, Chengzhi Mao. 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.

Trust prediction provides valuable support for decision making, information dissemination, and product promotion in online social networks. As a complex concept in the social network community, trust relationships among people can be established virtually based on: 1) their interaction behaviors, e.g., the ratings and comments that they provided; 2) the contextual information associated with their interactions, e.g., location and culture; and 3) the relative temporal features of interactions and the time periods when the trust relationships hold. Most of the existing works only focus on some aspects of trust, and there is not a comprehensive study of user trust development that considers and incorporates 1)-3) in trust prediction. In this article, we propose a context-aware deep trust prediction model C-DeepTrust to fill this gap. First, we conduct user feature modeling to obtain the user's static and dynamic preference features in each context. Static user preference features are obtained from all the ratings and reviews that a user provided, while dynamic user preference features are obtained from the items rated/reviewed by the user in time series. The obtained context-aware user features are then combined and fed into the multilayer projection structure to further mine the context-aware latent features. Finally, the context-aware trust relationships between users are calculated by their context-aware feature vector cosine similarities according to the social homophily theory, which shows a pervasive property of social networks that trust relationships are more likely to be developed among similar people. Extensive experiments conducted on two real-world datasets show the superior performance of our approach compared with the representative baseline methods.

Detecting and understanding the differences among process models is important for business improvement. Most of the existing work in analysing the differences between two process models employs an edit script approach, i.e., using a sequence of edit operations that transform one to another by applyingdeleteorinsertoperations. However, describing process differences this way is hard for users to understand and interpret. To overcome the problem, we propose a pattern-based method for process difference detection namedProDiff. We specify a set of process difference patterns as Single-Entry-Single-Exit (SESE) fragments of a process model. Process differences are detected by decomposing process models into different levels of SESE fragments, based on whichProDifflocates the positions of differences and provides assistance for users to carry out further analysis. A case study is provided to show the effectiveness and extensibility of the proposed method.

Breast cancer has become one of the most common malignant tumors in women worldwide, and it seriously threatens women’s physical and mental health. In recent years, with the development of Artificial Intelligence(AI) and the accumulation of medical data, AI has begun to be deeply integrated with mammography, MRI, ultrasound, etc. to assist physicians in disease diagnosis. However, the existing breast cancer diagnosis model based on Computer Vision(CV) is greatly affected by the image quality; on the other hand, the breast cancer diagnosis model based on Natural Language Processing(NLP) cannot effectively extract the semantic information of the mammography report. The lack of model interpretability also makes the existing diagnostic models have low confidence. In this paper, we proposed Breast Cancer Causal XAI Diagnostic Model(BCCXDM). Specifically, we first structured the mammography report. Then find the causal graph based on the structured table. We combine the existing tabular learning method TabNet with causal graphs(Causal-TabNet) to enable reasoning in the graphs to preserve the correlation between features. More importantly, we use GNN and node transition probability to aggregate node information. We evaluate our model on the real-world mammography report, and compare it with other popular interpretable methods. The experimental results show that our interpretable results are closer to the diagnostic criteria of clinicians.

A redundancy-based strategy is widely employed by assigning each task to multiple workers and then inferring the correct answer (called truth) for each task in crowdsourcing. Most existing truth inference methods are designed for the situation with a fairly big number of answers for each task (referred to as high redundancy). However, the high redundancy unavoidably leads to a high cost. In this work, we propose a novel truth inference approach called TWLR based on worker representations for the situation with a small number of answers for each task (referred to as low redundancy). We develop a deep model to learn the representations of workers considering both answers and worker-task relations. For each task, we identify the worker with the highest quality, and select his/her answer as the predicted answer. To the best of our knowledge, this is the first work to perform truth inference by utilizing deep learning techniques to deal with the low redundancy situation in crowdsourcing. We have conducted a set of experiments against 7 real-world datasets to show the accuracy improvement of our truth inference approach by comparing with 11 baseline methods.

Crowdsourcing platforms are widely used for requesters to find workers for general tasks. The answers to general tasks are usually open and not constrained by multiple choices. For the general tasks, the worker performance prediction models can facilitate the task assignment process in crowdsourcing. Worker performance prediction is affected by the three roles: the worker, the requester, and the task. The existing worker performance prediction models mainly consider the features of tasks and workers. However, these models rarely consider the features of requesters. And the existing worker performance prediction models for multiple-choice tasks are not suitable for general tasks as they are built based on the workers' accuracy on choices. In this work, we propose a worker performance prediction model by taking account of features of workers, tasks, and requesters to help requesters select workers for their general tasks on crowdsourcing platforms. We design a relationship learning module to learn the low dimension relationship representations of workers, tasks, and requesters. Furthermore, we design a performance learning model to predict workers' performance based on the features and relationship representations of workers, tasks, and requesters. A set of experiments against the realworld dataset from the Zhubajie platform has been conducted. Experimental results show that the proposed approach has better prediction results than the existing baseline methods.

The safety driving-related content demands of vehicle users increase rapidly, especially with the development of autonomous driving. It is significantly necessary to obtain the safety-related transportation information of an area when vehicles are drove there, whether or not they are controlled by human being. However, vehicular content caching can bring issues in distributed-fashion, such as high response delay and low content response ratio because of the poor traffic condition and the obstructions of buildings. As a consequence, we adopt UAVs (Unmanned Aerial Vehicles) to assist the driving safety-related content caching for vehicles. Besides, since the power energy and the caching storage of UAVs are limited, it is needed to design an optimal caching scheme to guarantee the driving safety-related content demands of vehicle users as well as reduce the energy consumption of UAVs. In this article, we propose a novel deep Q-learning based air-assisted vehicular caching scheme to respond to the driving safety-related content requests of vehicle users. First, a three-layered content response architecture is introduced, where an airship is leveraged to take charge of the scheduling of UAVs to improve the content response. Then, a multi-objective mathematical model is built to describe the specific problem of the proposed scheme. Finally, deep Q-learning is applied to solve the multi-objective problem by learning from the history content requests of vehicle users. Extensive experiments have been conducted which show the proposed scheme outperforms its counterparts in terms of content hit ratio, response delay, being scheduling probability and packet buffering time.

To provide efficient networking services at the edge of Internet-of-Vehicles (IoV), Software-Defined Vehicular Network (SDVN) has been a promising technology to enable intelligent data exchange without giving additional duties to the resource constrained vehicles. Compared with conventional centralized SDVNs, hybrid SDVNs combine the centralized control of SDVNs and self-organized distributed routing of Vehicular Ad-hoc NETworks (VANETs) to mitigate the burden on the central controller caused by the frequent uplink and downlink transmissions. Although a wide variety of routing protocols have been developed, existing protocols are designed for specific scenarios without considering flexibility and adaptivity in dynamic vehicular networks. To address this problem, we propose an efficient online sequential learning-based adaptive routing scheme, namely, Penicillium reproduction-based Online Learning Adaptive Routing scheme (POLAR) for hybrid SDVNs. By utilizing the computational power of edge servers, this scheme can dynamically select a routing strategy for a specific traffic scenario by learning the pattern from network traffic. Firstly, this paper applies Geohash to divide the large geographical area into multiple grids, which facilitates the collection and processing of real-time traffic data for regional management in controller. Secondly, a new Penicillium Reproduction Algorithm (PRA) with outstanding optimization capabilities is designed to improve the learning effectiveness of Online Sequential Extreme Learning Machine (OS-ELM). Finally, POLAR is deployed in control plane to generate decision-making model (i.e., routing policy). Based on the real-time featured data, this scheme can choose the optimal routing strategy for a specific area. Extensive simulation results show that POLAR is superior to a single traditional routing protocol in terms of packet delivery ratio and latency.

Trust relationship prediction among people provides valuable supports for decision making, information dissemination, and product promotion in online social networks. Network embedding has achieved promising performance for link prediction by learning node representations that encode intrinsic network structures. However, most of the existing network embedding solutions cannot effectively capture the properties of a trust network that has directed edges and nodes with in/out links. Furthermore, there usually exist rich user attributes in trust networks, such as ratings, reviews, and the rated/reviewed items, which may exert significant impacts on the formation of trust relationships. It is still lacking a network embedding-based method that can adequately integrate these properties for trust prediction. In this work, we develop an AtNE-Trust model to address these issues. We firstly capture user embedding from both the trust network structures and user attributes. Then we design a deep multi-view representation learning module to further mine and fuse the obtained user embedding. Finally, a trust evaluation module is developed to predict the trust relationships between users. Representation learning and trust evaluation are optimized together to capture high-quality user embedding and make accurate predictions simultaneously. A set of experiments against the real-world datasets demonstrates the effectiveness of the proposed approach.

General tasks on crowdsourcing platforms attract more and more workers with different skills and experiences. Existing approaches only leverage the information from tasks with feedback to evaluate worker ability. However, there are millions of tasks without feedback on the platforms. The participating behavior of workers involved in these tasks has not been exploited. In this work, we propose a worker ability model PB-Worker to support general tasks on crowdsourcing platforms. We model the worker latent relation and task latent relation by exploiting the worker participating behavior. To the best of our knowledge, this is the first work to consider the worker participating behavior. Our model is a semi-supervised model that can cover tasks with feedback and tasks without feedback. We employ the ladder network to generate the representations of workers and employ the neural network to predict the worker ability scores. A set of experiments against the real-world dataset from the Zhubajie platform has been conducted. Experimental results show that the output quality of the proposed approach is better than the existing baseline methods.

User Interfaces (UI) are the bridge to connect Business Processes (BPs) and end users. The implementation of UIs normally needs a lot of manual efforts of developers. Aiming to resolve this issue, this work proposes a UI derivation method with a role-enriched BP (REBP) model as its foundation. This process model has the capability to present the details of task control flow and data operations in tasks. A set of control flow patterns and data operation patterns is identified. For each participant role, tasks of a process are abstracted and aggregated, then data relationships are extracted according to the identified control flow patterns and data operation patterns. A set of mandatory and recommended rules has been developed for deriving the UI logic from a BP. The solution for the UI derivation has been provided and implemented in the prototype. This proposed UI derivation method can provide help for the analysis, design, and maintenance of UI components of BPs.

The overwhelming amount of information continuously flowing through the Twitter environment makes topic derivation essential. It indeed plays a valuable role in a variety of Twitter-based applications, including content recommendations, news summarization, market analysis, etc. Topic derivation methods are typically based on semantic features of tweet contents. Because tweets are short by nature, such methods suffer from data sparsity. To alleviate this problem, this paper proposes a topic derivation method that incorporates tweet text similarity and interactions measures. Besides the tweet contents, the approach takes into account several types of interactions amongst tweets: Tweets which mention the same people, replies and retweets. Topic derivation is done through a two-step matrix factorization process. We conducted a number of experiments on several Twitter datasets to reveal both the individual and integrated effects of the various features being considered. Our experimental results against TREC2014 and our self collected tweetMarch datasets demonstrate that the proposed method is able to provide more than 30 percent improvement compared to other advanced topic derivation methods.

Software-Defined Vehicular Networks (SDVNs) technology has been attracting significant attention as it can make Vehicular Ad Hoc Network (VANET) more efficient and intelligent. SDVN provides a flexible architecture which can decouple the network management from data transmission. Compared to centralized SDVN, hybrid SDVN is even more flexible and has less overhead. This hybrid technology can eliminate the burden on the central controller by moving regional routing tasks from the central controller to local controllers or vehicular nodes. In the literature, different routing protocols have been reported for SDVNs. However, these existing routing protocols lack flexibility and adaptive approaches to deal with changing and dynamic traffic conditions. Thus, this paper proposes a new software-defined routing method, namely, Novel Adaptive Routing and Switching Scheme (NARSS), deployed in the controller. This adaptive method can dynamically select routing schemes for a specific traffic scenario. To achieve this, this paper firstly presents a method for collecting road network information to describe traffic condition where the method extracts the feature data used to generate the routing scheme switching model. Secondly, we train the feature data through an artificial neural network with high training speed and accuracy. Finally, we use the model as a basis for establishing the NARSS and deploy it in the controller. Simulation results show that the proposed scheme outperforms the single traditional routing protocol in terms of both packet delivery ratio and end-to-end delay.

Trust prediction in online social networks is crucial for information dissemination, product promotion, and decision making. Existing work on trust prediction mainly utilizes the network structure or the low-rank approximation of a trust network. These approaches can suffer from the problem of data sparsity and prediction accuracy. Inspired by the homophily theory, which shows a pervasive feature of social and economic networks that trust relations tend to be developed among similar people, we propose a novel deep user model for trust prediction based on user similarity measurement. It is a comprehensive data sparsity insensitive model that combines a user review behavior and the item characteristics that this user is interested in. With this user model, we firstly generate a user's latent features mined from user review behavior and the item properties that the user cares. Then we develop a pair-wise deep neural network to further learn and represent these user features. Finally, we measure the trust relations between a pair of people by calculating the user feature vector cosine similarity. Extensive experiments are conducted on two real-world datasets, which demonstrate the superior performance of the proposed approach over the representative baseline works.

Trust evaluation of people and information on Twitter is critical for maintaining a healthy online social environment. How to evaluate the trustworthiness of users and tweets becomes a challenging question. In this demo, we show how our proposed CoTrRank approach deal with this problem. This approach models users and tweets in two coupled networks and calculate their trust values in different trust spaces. In particular, our solution provides a configurable way when mapping the calculated raw evidences to the trust values. The CoTrRank demo system has an interactive interface to show how our proposed approach produces more effective and adaptive trust evaluation results comparing with baseline methods.

When Influence Maximization (IM) is applied to social network to maximise the network coverage, it becomes an effective mechanism for marketing applications. In this paper, we focus on a specific influence maximization problem, i.e., selecting a set of seeds on twitter to maximise information propagation, which can be used for information reaching out in marketing campaigns. The proposed approach is taking into the consideration of social ties, user interactions, and information propagation on Twitter. The influence probability is calculated according to users' action history including tweet, favourite, mention/reply, and retweet. An information diffusion model is proposed with the capability to simulate the dynamic process of information spread on Twitter. A concise heuristic algorithm is developed for influence maximization accordingly. Experimental results and analysis are provided based on a real Twitter network including 3,292 users in Darwin city in Australia.

Interactions among tweets, i.e., mentions, retweets, replies, are important factors contributing to the quality of topic derivation on Twitter. If applied correctly, the incorporation of tweet interactions can significantly improve the quality of topic derivation in comparison with approaches that are mainly based on the content similarity analysis. However, how interactions can be measured and integrated with content similarity for topic derivation remains a challenge. In previous work, the strength of tweet-to-tweet relationship has been computed by simply adding measures for content similarity, mentions, and reply-retweets. This simple linear addition does not accurately reflect the various impacts these factors have on tweet relationships. In order to address this issue, we propose a joint probability model that can effectively integrate the effects of the content similarity, mentions, and reply-retweets to measure the tweet relationship for the purpose of topic derivation. The proposed method is based on matrix factorization techniques, which enables a flexible implementation on a distributed system in an incremental manner. Experimental results show that the proposed model results in a significant improvement in the quality of topic derivation over existing methods.

The task abstraction and aggregation in a business process can help to (1) obtain customized descriptions of a business process for different users, and (2) derive user interfaces of a business process related to the participating users. This paper proposes an approach for task abstraction and aggregation of a business process based on a role-enriched business process model. For each user role, tasks of a business process are abstracted and aggregated according to the identified control flow patterns. A set of elementary operations for task abstraction and aggregation in business process are specified. The algorithm for deriving the abstracted and aggregated business process is developed. The structural consistency between the business process and the abstracted and aggregated business process has been analyzed. The derived abstracted and aggregated business processes with the proposed approach can be used to support analysing, developing, and updating software components such as user interfaces related to different user roles.

To keep up with the trend of globalization and informatization, an increasing number of enterprises decide to run their business process in a service-based manner with the help of Web Service technology. In order to manage such service-based business process (SBP), it is vital that the dependencies among the internal process and the exposed external services are correctly developed and maintained. SBP is dynamic by nature, therefore it is necessary to develop a practical and robust method to verify the correctness of SBP. In an SBP, complex dependencies exist not only between internal process and involved services but also within their components (activities, data, operations, etc.). The complex dependencies make the correctness verification for SBP a challenging task. In this work, we develop a correctness verification approach to handle this task. A Petri net based model is proposed with a hierarchical structure to cover the characteristics of SBPs. This model can support the control flow patterns that are necessary for SBPs. A set of correctness properties for SBP are identified which any SBP developers shall consider, and the respective verification methods are developed.

In this article, we propose a comprehensive approach for Quality of Service (QoS) calculation in service composition. Differing from the existing work on QoS aggregations that represent QoS as single values, discrete values with frequencies, or standard statistical distributions, the proposed approach has the capability to handle any type of QoS probability distribution. A set of formulae and algorithms are developed to calculate the QoS of a composite service according to four identified basic patterns as sequential, parallel, conditional, and loop. We demonstrate that the proposed QoS calculation method is much more efficient than existing simulation methods. It has a high scalability and builds a solid foundation for real-time QoS analysis and prediction in service composition. Experiment results are provided to show the effectiveness and efficiency of the proposed method.

Quality of service (QoS) is a major concern in the design and management of a composite service. In this paper, a systematic approach is proposed to calculate QoS for composite services with complex structures, taking into consideration of the probability and conditions of each execution path. Four types of basic composition patterns for composite services are discussed: sequential, parallel, loop, and conditional patterns. In particular, QoS solutions are provided for unstructured conditional and loop patterns. We also show how QoS-based service selection can be conducted based on the proposed QoS calculation. Experiments have been conducted to show the effectiveness of the proposed method.

Opportunistic network is a type of challenged network where an end-to-end path between the source and the destination doesn't exist. The dissemination of the data relies on the encounters of nodes. Link duration time is a main factor in determining the transmission capacity between two encounter nodes in the opportunistic network. Besides, inter-contact time plays a key role in forwarding algorithms and has an obvious effect on the delivery delay. In this paper, according to statistical analysis and numerical methods, statistical characteristics of wireless link in random waypoint (RWP) are analyzed from aspects of contact duration time and inter-contact time with different moving speed and transmission radiuses of the nodes. Complementary Cumulative Distribution Functions (CCDF) of the contact duration time and inter-contact time of the nodes are provided by numerical methods.

Business collaboration is about coordinating the flow of information among organizations and linking their business processes into a cohesive whole. Collaborative business processes are time critical within and across organizations and can become unreliable due to temporal inconsistency where processes cannot execute according to the agreed temporal policies. It is necessary to have a mechanism to manage temporal consistency in service-oriented business collaboration. In this paper, we propose a model named Timed Choreographical Business Transaction Net (TiCoBTx-Net) based on Hierarchical Colored Petri Net for individual business participants to specify and manage the temporal consistency in business collaboration. A series of temporal polices are formalized and checked in TiCoBTx-Net to enforce the temporal consistency at design time and runtime. A verification mechanism is also developed to clarify the status of temporal inconsistencies. Finally, the implementation details of the proposed mechanism is provided.

The increasing processing power, storage and support of multiple network interfaces are promising the mobile devices to host services and participate in service discovery network. A few efforts have been taken to facilitate provisioning mobile Web services. However they have not addressed the issue about how to host heavy-duty services on mobile devices with limited computing resources in terms of processing power and memory. In this paper, we propose a framework which partitions the workload of complex services in a distributed environment and keeps the Web service interfaces on mobile devices. The mobile device is the integration point with the support of backend nodes and other Web services. The functions which require the resources of the mobile device and interaction with the mobile user are executed locally. The framework provides support for hosting mobile Web services involving complex business processes by partitioning the tasks and delegating the heavy-duty tasks to remote servers. We have analyzed the proposed framework using a sample prototype. The experimental results have shown a significant performance improvement by deploying the proposed framework in hosting mobile Web services.

In this paper, we propose an approach to deal with the change management for service oriented business processes. Beyond existing work, the proposed approach highlights the dependencies between services and business processes. A service oriented business process model is devised for capturing the major characteristics of change management in service oriented context. The taxonomy for the changes associated with services and business processes is presented. A set of change impact patterns are specified and the functions for calculating impact scopes of a change are defined. With the help of the change taxonomy and the change impact patterns, the ripple effect of changes of the business processes and services can be clearly analyzed. This research provides a step progress for change management in the service oriented environment.

In this paper, a QoS Distribution estimation Tool (QoSDIST) is developed to estimate the QoS distributions for service compositions. QoSDIST can generate QoS probability distributions for component web services. When estimating the QoS probability distribution for a service composition, QoSDIST does not put any constraints on the representation of the QoSs of component web services, i.e., the QoS of a component web service can be in single value, discrete values with frequencies, standard statistical distribution, or any general distribution regardless of its shape, which can not be done by any existing approaches. Moreover, QoSDIST can deal with commonly used composition patterns, including loop with arbitrary exit points.

Trust and reputation for web services emerges as an important research issue in web service selection. Current web service trust models either do not integrate different important sources of trust (subjective and objective for example), or do not focus on satisfying different user's requirements about different quality of service (QoS) attributes such as performance, availability etc. In this paper, we propose a Bayesian network trust and reputation model for web services that can overcome such limitations by considering several factors when assessing web services' trust: direct opinion from the truster, user rating (subjective view) and QoS monitoring information (objective view). Our comprehensive approach also addresses the problems of users' preferences and multiple QoS-based trust by specifying different conditions for the Bayesian network and targets at building a reasonable credibility model for the raters of web services.

In this paper, we propose a novel approach for Web search based on the statistical information of local setting data of web browsers in a community. The members of the community share their local setting data of browsers and this enables them to take advantage of the peer community members's opinions in their Web search. Then we develop a new scheme that combines PageRank's link-based ranking scores with our proposed community based popularity scores for web sites. This hybrid scheme provides a rank- ordering method for search query results that integrates the content consumers' opinions with the content producers' opinions in a balanced manner. The users' opinions of web sites provide a solid starting point of trust for combatting web spam and improving the quality of Web search.

In this paper, we propose a comprehensive trust management approach for Web services that covers the analysis/modelling of trust relationships and the development of trust management layer in a consistent manner. The specific characteristics of trust relationships in Web services are discussed. We introduce a separated trust management layer for Web services that can hold computing components for trust management tasks. A trust management architecture for Web services is proposed for building up the trust management layer. The proposed trust management architecture for Web services deals with trust requirements, trust evaluation, and trust consumption in Web services under a unified umbrella and it provides a solid foundation upon which may evolve the trust management layer for Web services.

To be adaptive to the traffic variations in some real-time sensor applications, AC-MAC is proposed by Jin Ai et al. Based on Sensor Medium Access Control (S-MAC), AC-MAC introduces an adaptive duty cycle scheme within the framework of S-MAC. However, frequent transceiver state switches can lead to the increasing consumption of energy. In order to solve this problem, we focus our research on how to reduce the number of transceiver state switch. By combining AC-MAC with the Dynamic Power Management, it brings in a new protocol, an Adaptive Coordinated MAC Protocol based on Dynamic Power Management for Wireless Sensor Networks, AC-MAC/DPM, which not only guarantees low delay or high throughput, but also reduces the potential energy consumption when the traffic load is high.

This paper presents a new model to analyze the channel access delay of 802.11 DCF. Based on this analytical model, the average channel access delay of 802.11 DCF is derived. By means of simulation, the correctness of the analysis is validated, and the channel access delay of 802.11 DCF is further evaluated.

In this paper, we explore how to make RWBO+BEB support service differentiation. An analytical model is proposed to analyze how to choose the minimum contention windows according to the bandwidth ratios of stations. Based on the analysis, a novel service differentiated backoff algorithm for IEEE 802.11 DCF, named DS-RWBO, is proposed. The simulation results indicate that DS-RWBO can allocate the wireless bandwidth according to the bandwidth ratio of each station.

This paper proposes a fair electronic gambling scheme for the Internet. The proposed scheme provides a unique link between payment and gambling outcome so that the winner can be ensured to get the payment. Since an optimal fair exchange method is used in gambling message exchange the proposed system guarantees that no one can successfully cheat during a gambling process. Our system requires an off-line Trusted Third Party (TTP). If a cheating occurs, the TTP can resolve the problem and make the gambling process fair.