Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning appr...Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning approach that combines visual detection and temporal behaviour classification.The methodology utilises object detection models—You Only Look Once(YOLOv12),Faster Region-based Convolutional Neural Network(RCNN),and Single Shot Detector(SSD)MobileNet—integrated with classification models such as Convolutional Neural Networks(CNN),Bidirectional Gated Recurrent Unit(Bi-GRU),and CNN-LSTM(Long Short-Term Memory).Two distinct datasets were used:the Online Exam Proctoring(EOP)dataset from Michigan State University and the School of Computer Science,Duy Tan Unievrsity(SCS-DTU)dataset collected in a controlled classroom setting.A diverse set of cheating behaviours,including book usage,unauthorised interaction,internet access,and mobile phone use,was categorised.Comprehensive experiments evaluated the models based on accuracy,precision,recall,training time,inference speed,and memory usage.We evaluate nine detector-classifier pairings under a unified budget and score them via a calibrated harmonic mean of detection and classification accuracies,enabling deployment-oriented selection under latency and memory constraints.Macro-Precision/Recall/F1 and Receiver Operating Characteristic-Area Under the Curve(ROC-AUC)are reported for the top configurations,revealing consistent advantages of object-centric pipelines for fine-grained cheating cues.The highest overall score is achieved by YOLOv12+CNN(97.15%accuracy),while SSD-MobileNet+CNN provides the best speed-efficiency trade-off for edge devices.This research provides valuable insights into selecting and deploying appropriate deep learning models for maintaining exam integrity under varying resource constraints.展开更多
Cheat sheets are so named because they may be used by students without the instructor's knowledge to cheat on a test.Student learning is greatly enhanced by studying prior to an exam.Allowing students to prepare a...Cheat sheets are so named because they may be used by students without the instructor's knowledge to cheat on a test.Student learning is greatly enhanced by studying prior to an exam.Allowing students to prepare a cheat sheet for the exam helps structure this study time and deepens learning.The crib sheet is well defined:one double-sided page of A4.An award for the best and most creative cheat sheet allows the instructor to appreciate the students' efforts.Using the cheat sheet can not only reduces student anxiety during testing but also incease student learning efficiency.展开更多
Elements of correspondence (“coincidences”) between a student’s solutions to an assigned set of quantitative problems and the solutions manual for the course textbook may suggest that the stu-dent copied the work f...Elements of correspondence (“coincidences”) between a student’s solutions to an assigned set of quantitative problems and the solutions manual for the course textbook may suggest that the stu-dent copied the work from an illicit source. Plagiarism of this kind, which occurs primarily in fields such as the natural sciences, engineering, and mathematics, is often difficult to establish. This paper derives an expression for the probability that alleged coincidences in a student’s paper could be attributable to pure chance. The analysis employs the Principle of Maximum Entropy (PME), which, mathematically, is a variational procedure requiring maximization of the Shannon-Jaynes entropy function augmented by the completeness relation for probabilities and known information in the form of expectation values. The virtue of the PME as a general method of inferential reasoning is that it generates the most objective (i.e. least biased) probability distribution consistent with the given information. Numerical examination of test cases for a range of plausible conditions can yield outcomes that tend to exonerate a student who otherwise might be wrongfully judged guilty of cheating by adjudicators unfamiliar with the surprising properties of random processes.展开更多
The main objective of this research is to provide a solution for online exam systems by using face recognition to authenticate learners for attending an online exam. More importantly, the system continuously (with sho...The main objective of this research is to provide a solution for online exam systems by using face recognition to authenticate learners for attending an online exam. More importantly, the system continuously (with short time intervals), checks for learner identity during the whole exam period to ensure that the learner who started the exam is the same one who continued until the end and prevent the possibility of cheating by looking at adjacent PC or reading from an external paper. The system will issue an early warning to the learners if suspicious behavior has been noticed by the system. The proposed system has been presented to eight e-learning instructors and experts in addition to 32 students to gather feedback and to study the impact and the benefit of such system in e-learning environment.展开更多
Video games have been around for several decades and have had many advancements from the original start of video games. Video games started as virtual games that were advertised towards children, and these virtual gam...Video games have been around for several decades and have had many advancements from the original start of video games. Video games started as virtual games that were advertised towards children, and these virtual games created a virtual reality of a variety of genres. These genres included sports games, such as tennis, football, baseball, war games, fantasy, puzzles, etc. The start of these games was derived from a sports genre and now has a popularity in multiplayer-online-shooting games. The purpose of this paper is to investigate different types of tools available for cheating in virtual world making players have undue advantage over other players in a competition. With the advancement in technology, these video games have become more expanded in the development aspects of gaming. Video game developers have created long lines of codes to create a new look of video games. As video games have progressed, the coding, bugs, bots, and errors of video games have changed throughout the years. The coding of video games has branched out from the original video games, which have given many benefits to this virtual world, while simultaneously creating more problems such as bots. Analysis of tools available for cheating in a game has disadvantaged normal gamer in a fair contest.展开更多
In the relationship between electronic pricing and the market and consumers in daily life, this paper analyzes the fraud of electronic pricing, and studies the ways to deal with the fraud. We started to cooperate with...In the relationship between electronic pricing and the market and consumers in daily life, this paper analyzes the fraud of electronic pricing, and studies the ways to deal with the fraud. We started to cooperate with effective production sources to avoid the serious consequences of electronic fraud.展开更多
Cheating immune secret sharing in the unconditionally secure case are investigated in this paper.Constructionsof defining functions of cheating immune secret sharing on V_n are given,where n is any integer greater tha...Cheating immune secret sharing in the unconditionally secure case are investigated in this paper.Constructionsof defining functions of cheating immune secret sharing on V_n are given,where n is any integer greater than 5.Further-more,the obtained defining functions have good cryptographic properties.The nonlinearity of them is 2^(n-1)-2^(n/2+1) whenn≡0(mod 4)and 2^(n-1)-2^((?)n/2」+2) otherwise.And thedegree is「n/4(?).展开更多
In this paper an advanced threshold secret sharing scheme for identifyingcheaters is proposed by using authentication codes. The performance of the scheme is discussed. Theresults show that in the scheme the valid sha...In this paper an advanced threshold secret sharing scheme for identifyingcheaters is proposed by using authentication codes. The performance of the scheme is discussed. Theresults show that in the scheme the valid shareholders can not only identify the impersonation of anadversary, but also detect cheating of some valid shareholders . In particular one honestshareholder is able to detect cheating of other participants forming a collection, and theinformation rate of the scheme is higher than that of others.展开更多
With the development of cloud computing technology, data can be outsourced to the cloud and conveniently shared among users. However, in many circumstances, users may have concerns about the reliability and integrity ...With the development of cloud computing technology, data can be outsourced to the cloud and conveniently shared among users. However, in many circumstances, users may have concerns about the reliability and integrity of their data. It is crucial to provide data sharing services that satisfy these security requirements. We introduce a reliable and secure data sharing scheme, using the threshold secret sharing technique and the ChaumPedersen zero-knowledge proof. The proposed scheme is not only effective and flexible, but also able to achieve the semantic security property. Moreover, our scheme is capable of ensuring accountability of users’ decryption keys as well as cheater identification if some users behave dishonestly. The efficiency analysis shows that the proposed scheme has a better performance in terms of computational cost, compared with the related work. It is particularly suitable for application to protect users’ medical insurance data over the cloud.展开更多
Pay-for-grades programs aim to incentivize families and students to engage in specified behaviors given financial remittance.In addition to doubts over its effectiveness,educators worry that monetary incentives could ...Pay-for-grades programs aim to incentivize families and students to engage in specified behaviors given financial remittance.In addition to doubts over its effectiveness,educators worry that monetary incentives could skew student learning motivation and lead to academic cheating.Using a randomized control trial in 11 Chinese primary schools,we studied the effects of pay-for-grades programs on academic cheating.We randomly assigned 82 classrooms into treatment or control conditions,and used a statistical algorithm to determine the occurrence of cheating.While our data indicates a concerning level of cheating overall,our experiment did not find any relationship between academic cheating and the pay-for-grades program.Finally,we discuss the feasibility of such policies in improving learning outcomes and its policy implications.展开更多
文摘Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning approach that combines visual detection and temporal behaviour classification.The methodology utilises object detection models—You Only Look Once(YOLOv12),Faster Region-based Convolutional Neural Network(RCNN),and Single Shot Detector(SSD)MobileNet—integrated with classification models such as Convolutional Neural Networks(CNN),Bidirectional Gated Recurrent Unit(Bi-GRU),and CNN-LSTM(Long Short-Term Memory).Two distinct datasets were used:the Online Exam Proctoring(EOP)dataset from Michigan State University and the School of Computer Science,Duy Tan Unievrsity(SCS-DTU)dataset collected in a controlled classroom setting.A diverse set of cheating behaviours,including book usage,unauthorised interaction,internet access,and mobile phone use,was categorised.Comprehensive experiments evaluated the models based on accuracy,precision,recall,training time,inference speed,and memory usage.We evaluate nine detector-classifier pairings under a unified budget and score them via a calibrated harmonic mean of detection and classification accuracies,enabling deployment-oriented selection under latency and memory constraints.Macro-Precision/Recall/F1 and Receiver Operating Characteristic-Area Under the Curve(ROC-AUC)are reported for the top configurations,revealing consistent advantages of object-centric pipelines for fine-grained cheating cues.The highest overall score is achieved by YOLOv12+CNN(97.15%accuracy),while SSD-MobileNet+CNN provides the best speed-efficiency trade-off for edge devices.This research provides valuable insights into selecting and deploying appropriate deep learning models for maintaining exam integrity under varying resource constraints.
文摘Cheat sheets are so named because they may be used by students without the instructor's knowledge to cheat on a test.Student learning is greatly enhanced by studying prior to an exam.Allowing students to prepare a cheat sheet for the exam helps structure this study time and deepens learning.The crib sheet is well defined:one double-sided page of A4.An award for the best and most creative cheat sheet allows the instructor to appreciate the students' efforts.Using the cheat sheet can not only reduces student anxiety during testing but also incease student learning efficiency.
文摘Elements of correspondence (“coincidences”) between a student’s solutions to an assigned set of quantitative problems and the solutions manual for the course textbook may suggest that the stu-dent copied the work from an illicit source. Plagiarism of this kind, which occurs primarily in fields such as the natural sciences, engineering, and mathematics, is often difficult to establish. This paper derives an expression for the probability that alleged coincidences in a student’s paper could be attributable to pure chance. The analysis employs the Principle of Maximum Entropy (PME), which, mathematically, is a variational procedure requiring maximization of the Shannon-Jaynes entropy function augmented by the completeness relation for probabilities and known information in the form of expectation values. The virtue of the PME as a general method of inferential reasoning is that it generates the most objective (i.e. least biased) probability distribution consistent with the given information. Numerical examination of test cases for a range of plausible conditions can yield outcomes that tend to exonerate a student who otherwise might be wrongfully judged guilty of cheating by adjudicators unfamiliar with the surprising properties of random processes.
文摘The main objective of this research is to provide a solution for online exam systems by using face recognition to authenticate learners for attending an online exam. More importantly, the system continuously (with short time intervals), checks for learner identity during the whole exam period to ensure that the learner who started the exam is the same one who continued until the end and prevent the possibility of cheating by looking at adjacent PC or reading from an external paper. The system will issue an early warning to the learners if suspicious behavior has been noticed by the system. The proposed system has been presented to eight e-learning instructors and experts in addition to 32 students to gather feedback and to study the impact and the benefit of such system in e-learning environment.
文摘Video games have been around for several decades and have had many advancements from the original start of video games. Video games started as virtual games that were advertised towards children, and these virtual games created a virtual reality of a variety of genres. These genres included sports games, such as tennis, football, baseball, war games, fantasy, puzzles, etc. The start of these games was derived from a sports genre and now has a popularity in multiplayer-online-shooting games. The purpose of this paper is to investigate different types of tools available for cheating in virtual world making players have undue advantage over other players in a competition. With the advancement in technology, these video games have become more expanded in the development aspects of gaming. Video game developers have created long lines of codes to create a new look of video games. As video games have progressed, the coding, bugs, bots, and errors of video games have changed throughout the years. The coding of video games has branched out from the original video games, which have given many benefits to this virtual world, while simultaneously creating more problems such as bots. Analysis of tools available for cheating in a game has disadvantaged normal gamer in a fair contest.
文摘In the relationship between electronic pricing and the market and consumers in daily life, this paper analyzes the fraud of electronic pricing, and studies the ways to deal with the fraud. We started to cooperate with effective production sources to avoid the serious consequences of electronic fraud.
文摘Cheating immune secret sharing in the unconditionally secure case are investigated in this paper.Constructionsof defining functions of cheating immune secret sharing on V_n are given,where n is any integer greater than 5.Further-more,the obtained defining functions have good cryptographic properties.The nonlinearity of them is 2^(n-1)-2^(n/2+1) whenn≡0(mod 4)and 2^(n-1)-2^((?)n/2」+2) otherwise.And thedegree is「n/4(?).
文摘In this paper an advanced threshold secret sharing scheme for identifyingcheaters is proposed by using authentication codes. The performance of the scheme is discussed. Theresults show that in the scheme the valid shareholders can not only identify the impersonation of anadversary, but also detect cheating of some valid shareholders . In particular one honestshareholder is able to detect cheating of other participants forming a collection, and theinformation rate of the scheme is higher than that of others.
基金the National Key R&D Program of China (No. 2017YFB0802000)the National Natural Science Foundation of China (Nos. 61772326 and 61572303)+4 种基金the Research Fund for International Young Scientists, China (No. 61750110528)National Cryptography Development FYind for the 13th Five- Year Plan, China (No. MMJJ20170216), the Foundation of State Key Laboratory of Information Security, China (No. 2017-MS- 03)the Fundamental Research Funds for the Central Universities, China (No. GK201702004)the Scientific Research Program Funded by Shaanxi Provincial Education Department, China (No. 16JK1109), the Provincial Natural Science Foundation Research Project of Shaanxi, China (No. 2017JQ6029)the Doctoral Scientific Fund Project of Shaanxi University of Science & Technology, China (No. BJ11-12).
文摘With the development of cloud computing technology, data can be outsourced to the cloud and conveniently shared among users. However, in many circumstances, users may have concerns about the reliability and integrity of their data. It is crucial to provide data sharing services that satisfy these security requirements. We introduce a reliable and secure data sharing scheme, using the threshold secret sharing technique and the ChaumPedersen zero-knowledge proof. The proposed scheme is not only effective and flexible, but also able to achieve the semantic security property. Moreover, our scheme is capable of ensuring accountability of users’ decryption keys as well as cheater identification if some users behave dishonestly. The efficiency analysis shows that the proposed scheme has a better performance in terms of computational cost, compared with the related work. It is particularly suitable for application to protect users’ medical insurance data over the cloud.
文摘Pay-for-grades programs aim to incentivize families and students to engage in specified behaviors given financial remittance.In addition to doubts over its effectiveness,educators worry that monetary incentives could skew student learning motivation and lead to academic cheating.Using a randomized control trial in 11 Chinese primary schools,we studied the effects of pay-for-grades programs on academic cheating.We randomly assigned 82 classrooms into treatment or control conditions,and used a statistical algorithm to determine the occurrence of cheating.While our data indicates a concerning level of cheating overall,our experiment did not find any relationship between academic cheating and the pay-for-grades program.Finally,we discuss the feasibility of such policies in improving learning outcomes and its policy implications.
