Zhiyuan Sun

The blockchain technology has been used for recording state transitions of smart contracts - decentralized applications that can be invoked through external transactions. Smart contracts gained popularity and accrued hundreds of billions of dollars in market capitalization in recent years. Unfortunately, like all other programs, smart contracts are prone to security vulnerabilities that have incurred multimillion-dollar damages over the past decade. As a result, many automated threat mitigation solutions have been proposed to counter the security issues of smart contracts. These threat mitigation solutions include various tools and methods that are challenging to compare. This survey develops a comprehensive classification taxonomy of smart contract threat mitigation solutions within five orthogonal dimensions: defense modality, core method, targeted contracts, input-output data mapping, and threat model. We classify 133 existing threat mitigation solutions using our taxonomy and confirm that the proposed five dimensions allow us to concisely and accurately describe any smart contract threat mitigation solution. In addition to learning what the threat mitigation solutions do, we also show how these solutions work by synthesizing their actual designs into a set of uniform workflows corresponding to the eight existing defense core methods. We further create an integrated coverage map for the known smart contract vulnerabilities by the existing threat mitigation solutions. Finally, we perform the evidence-based evolutionary analysis, in which we identify trends and future perspectives of threat mitigation in smart contracts and pinpoint major weaknesses of the existing methodologies. For the convenience of smart contract security developers, auditors, users, and researchers, we deploy a regularly updated comprehensive open-source online registry of threat mitigation solutions.

Smart contract

10.48550/arxiv.2302.07347

Cite

Citations (0)

DoubleUp Roll: Double-spending in Arbitrum by Rolling It Back

Zhiyuan Sun Zihao Li Xinghao Peng Xiapu Luo Muhui Jiang

Optimistic rollup protocols are widely adopted as the most popular blockchain scaling solutions. As a dominant implementation, Arbitrum has boasted a total locked value exceeding 18 billion USD, highlighting the significance of optimistic rollups in blockchain ecosystem. Despite their popularity, little research has been done on the security of optimistic rollup protocols, and potential vulnerabilities on them remain unknown.

Popularity

Value (mathematics)

10.1145/3658644.3690256

Cite

Citations (0)

Research on the Academic Early Warning Model of Distance Education based on Student Behavior Data in the Context of COVID-19

International Journal of Advanced Computer Science and Applications (2022)

Yi Qu Zhiyuan Sun Libin Liu

The COVID-19 epidemic has caused great impact on the entire society, and the spread of novel coronavirus has brought a lot of inconvenience to the education industry. To ensure the sustainability of education, distance education plays a significant role. During the process of distance education, it is necessary to examine the learning situation of students. This study proposes an academic early warning model based on long- and short-term memory (LSTM), which firstly extracts and classifies students’ behavior data, and then uses the optimized LSTM to establish an academic early warning model. The precision rate of the optimized LSTM algorithm is 0.929, the recall rate is 0.917 and the F value is 0.923, showing a higher degree of convergence than the basic LSTM algorithm. In the actual case analysis, the accuracy rate of the academic early warning system is 92.5%. The LSTM neural network shows high performance after parameter optimization, and the academic early warning model based on LSTM also has high accuracy in the actual case analysis, which proves the feasibility of the established academic early warning model.

Early warning system

10.14569/ijacsa.2022.0131074

Cite

Citations (2)

Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games

Findings of the Association for Computational Linguistics: ACL 2022 (2024)

Dekun Wu Haochen Shi Zhiyuan Sun Bang Liu

10.18653/v1/2024.findings-acl.490

Cite

Citations (0)

Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games

arXiv (Cornell University) (2023)

Dekun Wu Haochen Shi Zhiyuan Sun Bang Liu

In this study, we explore the application of Large Language Models (LLMs) in "Jubensha" (Chinese murder mystery role-playing games), a novel area in AI-driven gaming. We introduce the first Chinese dataset specifically for Jubensha, including character scripts and game rules, to foster AI agent development in this complex narrative environment. Our work also presents a unique multi-agent interaction framework using LLMs, allowing AI agents to autonomously engage in the game, enhancing the dynamics of Jubensha gameplay. To evaluate these AI agents, we developed specialized methods targeting their mastery of case information and reasoning skills. Furthermore, we incorporated the latest advancements in in-context learning to improve the agents' performance in critical aspects like information gathering, murderer detection, and logical reasoning. The experimental results validate the effectiveness of our proposed methods. This work aims to offer a fresh perspective on understanding LLM capabilities and establish a new benchmark for evaluating large language model-based agents to researchers in the field.

Benchmark (surveying)

10.48550/arxiv.2312.00746

Cite

Citations (0)

Security Threat Mitigation for Smart Contracts: A Comprehensive Survey

ACM Computing Surveys (2023)

Nikolay Ivanov Chenning Li Qiben Yan Zhiyuan Sun Zhichao Cao

The blockchain technology has been used for recording state transitions of smart contracts - decentralized applications that can be invoked through external transactions. Smart contracts gained popularity and accrued hundreds of billions of dollars in market capitalization in recent years. Unfortunately, like all other programs, smart contracts are prone to security vulnerabilities that have incurred multimillion-dollar damages over the past decade. As a result, many automated threat mitigation solutions have been proposed to counter the security issues of smart contracts. These threat mitigation solutions include various tools and methods that are challenging to compare. This survey develops a comprehensive classification taxonomy of smart contract threat mitigation solutions within five orthogonal dimensions: defense modality, core method, targeted contracts, input-output data mapping, and threat model. We classify 133 existing threat mitigation solutions using our taxonomy and confirm that the proposed five dimensions allow us to concisely and accurately describe any smart contract threat mitigation solution. In addition to learning what the threat mitigation solutions do, we also show how these solutions work by synthesizing their actual designs into a set of uniform workflows corresponding to the eight existing defense core methods. We further create an integrated coverage map for the known smart contract vulnerabilities by the existing threat mitigation solutions. Finally, we perform the evidence-based evolutionary analysis, in which we identify trends and future perspectives of threat mitigation in smart contracts and pinpoint major weaknesses of the existing methodologies. For the convenience of smart contract security developers, auditors, users, and researchers, we deploy a regularly updated comprehensive open-source online registry of threat mitigation solutions.

Smart contract

10.1145/3593293

Cite

Citations (30)

Using Emotions as Intrinsic Motivation to Accelerate Classic Reinforcement Learning

Chengxiang Lu Zhiyuan Sun Zhongzhi Shi Bao-Xiang Cao

Aiming at the need for autonomous learning in reinforcement learning (RL), a quantitative emotion-based motivation model is proposed by introducing psychological emotional factors as the intrinsic motivation. The curiosity is used to promote or hold back agents' exploration of unknown states, the happiness index is used to determine the current state-action's happiness level, the control power is used to indicate agents' control ability over its surrounding environment, and together to adjust agents' learning preferences and behavioral patterns. To combine intrinsic emotional motivations with classic RL, two methods are proposed. The first method is to use the intrinsic emotional motivations to explore unknown environment and learn the environment transitioning model ahead of time, while the second method is to combine intrinsic emotional motivations with external rewards as the ultimate joint reward function, directly to drive agents' learning. As the result shows, in the simulation experiments in the rat foraging in maze scenario, both methods have achieved relatively good performance, compared with classic RL purely driven by external rewards.

Curiosity

10.1109/isai.2016.0077

Cite

Citations (6)

Multi-focus image fusion with enhancement filtering for robust vascular quantification using photoacoustic microscopy

Optics Letters (2022)

Wangting Zhou Jiangshan He Yu Li Zhiyuan Sun Jiangbo Chen

Accurate identification and quantification of microvascular patterns are important for clinical diagnosis and therapeutic monitoring using optical-resolution photoacoustic microscopy (OR-PAM). Due to its limited depth of field, conventional OR-PAM may not fully reveal microvascular patterns with enough details in depth range, which affects the segmentation and quantification. Here, we propose a robust vascular quantification approach via combining multi-focus image fusion with enhancement filtering (MIFEF). The multi-focus image fusion is constructed based on multi-scale gradients and image matting to improve image fusion quality by considerably achieving accurate focus measurement for initial segmentation as well as decision map refinement. The enhancement filtering identifies the vessels and handles noise without deforming microvasculature. The performance of the MIFEF were evaluated employing a leaf phantom, mouse livers and brains. The proposed method for OR-PAM can significantly facilitate the clinical provision of optical biopsy of vascular-related diseases.

10.1364/ol.459629

Cite

Citations (6)

Research on the Curriculum System of Top-up Degree Programs under the Background of New Engineering and Technical Disciplines

New explorations in education and teaching. (2024)

Zhiyuan Sun Kun Liu Yadongyang Zhu

In response to the new round of technological revolution and industrial transformation, and to support and serve innovation-driven development, new engineering talents focus on the cultivation of practical and innovative abilities. At present, the proportion of upgrading from junior college to undergraduate in China has reached 20%. More and more vocational school graduates have the opportunity to receive high-quality undergraduate education, become skilled professionals. But the cultivation of this group of students is often overlooked by many universities. This study analyses the issues existing in the undergraduate curriculum system of local applied universities in undertaking vocational education. It is pointed out that the application of ordinary undergraduate curriculum systems is not suitable for vocational-to-bachelor s students and cannot meet the training objectives of higher vocational and technical talents. To cultivate new engineering vocational and technical talents, aiming at the current issues in the theoretical and practical settings of the curriculum system, this study proposes to use employment as a guide in the vocational-to-bachelor s curriculum system, set bridging courses to consolidate professional foundations, implement multiple training programs to promote student development, and collaborate with enterprises to carry out project-based practical training. It is necessary to optimize the construction of the curriculum system from theoretical and practical, and fully leverage the advantages of students strong practical abilities, which will reserve high-level vocational and technical talents for the new round of technological and industrial revolution.

Degree (music)

10.18686/neet.v2i2.3913

Cite

Citations (0)

Multitask learning-powered large-volume, rapid photoacoustic microscopy with non-diffracting beams excitation and sparse sampling

Photonics Research (2024)

Xueli Chen Wangting Zhou Zhen Yuan Zhiyuan Sun Zhong Ji

10.1364/prj.544960

Cite

Citations (0)