Blockchain Papers

Liang Guo

Game-based teaching (GBT) has gained widespread adoption in modern education, yet teachers bear heavy burdens in designing GBT activities and interpreting student learning performance, while centralized educational data storage brings prominent security and credibility risks. To tackle the above bottlenecks, this paper proposes SmartTA, an integrated teaching assistant system combining GBT recommendation modules, automated machine learning (AutoML), and blockchain. Specifically, SmartTA supplies customized GBT cases and exam scoring suggestions for teachers, and leverages AutoML to automatically mine student learning behaviors with zero coding requirements. Three groups of experiments are conducted to validate the system: AutoML achieves a maximum prediction accuracy of 93% on six public educational datasets; the Hyperledger Fabric-based blockchain prototype enables data insertion with an average latency of approximately 2.2 seconds and query latency of approximately 150 ms; 20 frontline educational practitioners provide 85% positive user feedback. The experimental results suggest that SmartTA may help reduce teachers’ lesson preparation workload, support improved instructional quality, while enabling tamper-resistant data storage via blockchain. This study realizes the practical fusion of AutoML and blockchain for GBT scenarios, and establishes a novel, secure, data-driven teaching assistance paradigm that is accessible to non-technical educators.

Fuan Xiao, Jiahui Huang, Jia-Xin Huang, Jia-Xin Huang · 7 authors

Abstract Online Education in Higher Education is rapidly evolving through the integration of Large Language Model (LLM)-powered intelligent systems, which enable personalized tutoring, dynamic content generation, and automated assessment. However, the widespread adoption of LLMs in education is hampered due to their inherent limitations, including susceptibility to hallucinations, insufficient domain-specific knowledge validation, and output inconsistency. These deficiencies can lead to misleading or erroneous content, potentially causing significant negative learning outcomes. A core challenge lies in ensuring that such errors are immutably logged and traceable, thereby establishing a mechanism for accountability among the entities deploying these LLM services. To address these challenges, this paper proposes a novel framework that Integrates LLM with consortium blockchain for personalized and verifiable online education. Our design features a synergistic architecture in which LLM based services provide the intelligent educational interface, while a permissioned consortium blockchain serves as a secure and tamper proof ledger. This blockchain infrastructure records critical educational transactions ranging from learning process data and academic credentials to the outputs generated by the LLMs. This integration not only secures academic credentials but also establishes a fully auditable trail, making it possible to trace responsibility for educational deficiencies caused by AI errors. Collectively, this work demonstrates a robust and accountable framework for leveraging LLMs in education, effectively mitigating the risks of AI inaccuracies through the verifiable and immutable nature of consortium blockchain.

Mohammad M Maheri, Alex Davidson, Hamed Haddadi

Machine learning providers commonly distribute global models to edge devices, which subsequently personalize these models using local data. However, issues such as copyright infringements, biases, or regulatory requirements may require the verifiable removal of certain data samples across all edge devices. Ensuring that edge devices correctly execute such unlearning operations is critical to maintaining integrity. In this work, we introduce a verification framework leveraging zero-knowledge proofs, specifically zk-SNARKs, to confirm data unlearning on personalized edge-device models without compromising privacy. We have developed algorithms explicitly designed to facilitate unlearning operations that are compatible with efficient zk-SNARK proof generation, ensuring minimal computational and memory overhead suitable for constrained edge environments. Furthermore, our approach carefully preserves personalized enhancements on edge devices, maintaining model performance post-unlearning. Our results affirm the practicality and effectiveness of this verification framework, demonstrating verifiable unlearning with minimal degradation in personalization-induced performance improvements. Our methodology ensures verifiable, privacy-preserving, and effective machine unlearning across edge devices.

Habeeb Yusuf, Arthur Money, Damon Daylamani-Zad

Abstract The ever-changing global educational landscape, coupled with the advancement of Web3, is seeing rapid changes in the ways pedagogical artificially intelligent conversational agents are being developed and used to advance teaching and learning in higher education. Given the rapidly evolving research landscape, there is a need to establish what the current state of the art is in terms of the pedagogical applications and technological functions of these conversational agents and to identify the key existing research gaps, and future research directions, in the field. A literature survey of the state of the art of pedagogical AI conversational agents in higher education was conducted. The resulting literature sample (n = 92) was analysed using thematic template analysis, the results of which were used to develop a conceptual framework of pedagogical conversational agents in higher education. Furthermore, a survey of the state of the art was then presented as a function of the framework. The conceptual framework proposes that pedagogical AI conversational agents can primarily be considered in terms of their pedagogical applications and their pedagogical purposes , which include pastoral , instructional and cognitive , and are further considered in terms of mode of study and intent . The technological functions of the agents are also considered in terms of embodiment (embodied/disembodied) and functional type and features . This research proposes that there are numerous opportunities for future research, such as, the use of conversational agents for enhancing assessment, reflective practice and to support more effective administration and management practice. In terms of technological functions, future research would benefit from focusing on enhancing the level of personalisation and media richness of interaction that can be achieved by AI conversational agents.

Yi Zhang, Ziying Fan

This research paper explores the intersection of zero-knowledge proofs (ZKPs) and machine learning (ML), presenting a comprehensive overview of recent advancements, applications, and challenges in this fast growing area. The jointers of ZKPs and ML techniques shall go a meter further to fuse privacy, security, and integrity in a number of solutions, which include forming of groups for data sharing and safe machine learning. Through the investigation of the well-respected sites in that area and also the thorough description of formulas and their experimental outcome, this paper looks for the clarification of the current state of affairs and the possible future directions of ZKPs in the AI world. By inserting the verification mechanism of ZKPs into machine learning ecosystem, it allows devising novel solutions for the problems of privacy and confidentiality that have for long been not solved. With this approach, the concatenation of parties collectively performs the process of dealing with private inputs without revealing any of these data and this, in return, opens the possibilities of secure multi-party computation. Furthermore, ZKPs protect data sharing as it gives people the opportunity to construct confidential data and share them to model training without compromising any one’s private details. Being a part of the dynamic conversations, which focus on the game-changing capacity of transparent zero-knowledge proofs (ZKPs), this paper brings the role of ZKPs in preserving the confidentiality and integrity of artificial intelligence (AI) applications into the centre of attention. As scientists still fight to improve protocols and circumvent computational complications, ZKPs are likely to establishment as critical tools in the effort to increase ML systems in the digital sphere.