Zhibo Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Zhibo Sun has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Ruoyu Wang
Arizona State University, Tempe, AZ, USA
3 shared publications - Tiffany Bao
Arizona State University, Tempe, AZ, USA
3 shared publications - Adam Doupé
Arizona State University, Tempe, AZ, USA
2 shared publications - Adam Oest
Arizona State University, United States of America
2 shared publications - Gail-Joon Ahn
Arizona State University, Tempe, AZ, USA
2 shared publications - Hong Zhang
Hebei University
2 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5926-5940
Learning Less While Asking More: How LLM-Based Assistance Shapes Vulnerability Learning
Large language model assistants have become a popular way to learn about software vulnerabilities, yet whether they effectively support this process remains unclear. We present a controlled within-subject study with 70 participants comparing LLM-based assistance with web search across five dimensions of vulnerability understanding. We find that LLM-based assistance is associated with smaller measured learning gains than web search, with the disadvantage concentrated in reasoning-oriented dimensions such as understanding causes, runtime behavior, and security consequences. Process analysis reveals that LLM sessions involve broader but faster-shifting queries, earlier movement toward solution-seeking, and reduced sustained engagement with explanatory content. Despite these smaller measured gains, participants consistently perceive LLM assistance as more helpful, clearer, and more efficient, yet report comparable workload to web search. These findings reveal a gap between perceived support and measured learning gains. Motivated by this gap, we design VulnScaffold, a scaffolded LLM-based learning system that restructures query formulation, response organization, and reflective practice. A preliminary evaluation suggests promising improvements in both learning outcomes and user experience, helping address the gap identified in LLM-based learning.
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5926-5940
Open AccessLearning Less While Asking More: How LLM-Based Assistance Shapes Vulnerability Learning
Large language model assistants have become a popular way to learn about software vulnerabilities, yet whether they effectively support this process remains unclear. We present a controlled within-subject study with 70 participants comparing LLM-based assistance with web search across five dimensions of vulnerability understanding. We find that LLM-based assistance is associated with smaller measured learning gains than web search, with the disadvantage concentrated in reasoning-oriented dimensions such as understanding causes, runtime behavior, and security consequences. Process analysis reveals that LLM sessions involve broader but faster-shifting queries, earlier movement toward solution-seeking, and reduced sustained engagement with explanatory content. Despite these smaller measured gains, participants consistently perceive LLM assistance as more helpful, clearer, and more efficient, yet report comparable workload to web search. These findings reveal a gap between perceived support and measured learning gains. Motivated by this gap, we design VulnScaffold, a scaffolded LLM-based learning system that restructures query formulation, response organization, and reflective practice. A preliminary evaluation suggests promising improvements in both learning outcomes and user experience, helping address the gap identified in LLM-based learning.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
I Can SE Clearly Now: Investigating the Effectiveness of GUI-based Symbolic Execution for Software Vulnerability Discovery
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessI Can SE Clearly Now: Investigating the Effectiveness of GUI-based Symbolic Execution for Software Vulnerability Discovery
- Open Access
- 30 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 49-64
From Victims to Defenders: An Exploration of the Phishing Attack Reporting Ecosystem
Reporting phishing attacks can significantly shorten the time required to take down their operations and deter further victimization by the same phishing websites. However, little research has been conducted to understand the phishing reporting ecosystem and its effectiveness. In this paper, we comprehensively evaluate the phishing reporting ecosystem to identify the critical challenges people face and their concerns when reporting smishing, vishing, and phishing email attacks. First, we analyze the existing security advice and channels for reporting phishing attacks in both the public and private sectors. Then, we conduct a scenario-based experiment involving 89 participants to investigate what factors affect a participant’s decision to report a phishing attack and what challenges they face in preparing the report. Third, we report phishing attacks ourselves and monitor the status of the reported phishing websites to empirically measure how reports are acted upon and how that affects the reported phishing websites. Finally, we propose approaches under five major concern categories to mitigate the challenges that we discover in the phishing reporting ecosystem.
- 30 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 49-64
Open AccessFrom Victims to Defenders: An Exploration of the Phishing Attack Reporting Ecosystem
Reporting phishing attacks can significantly shorten the time required to take down their operations and deter further victimization by the same phishing websites. However, little research has been conducted to understand the phishing reporting ecosystem and its effectiveness. In this paper, we comprehensively evaluate the phishing reporting ecosystem to identify the critical challenges people face and their concerns when reporting smishing, vishing, and phishing email attacks. First, we analyze the existing security advice and channels for reporting phishing attacks in both the public and private sectors. Then, we conduct a scenario-based experiment involving 89 participants to investigate what factors affect a participant’s decision to report a phishing attack and what challenges they face in preparing the report. Third, we report phishing attacks ourselves and monitor the status of the reported phishing websites to empirically measure how reports are acted upon and how that affects the reported phishing websites. Finally, we propose approaches under five major concern categories to mitigate the challenges that we discover in the phishing reporting ecosystem.
- Open Access
- 19 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 55-65
Nothing Personal: Understanding the Spread and Use of Personally Identifiable Information in the Financial Ecosystem
Online services leverage various authentication methods with differing usability and reliability trade-offs, such as password-based or multi-factor authentication (MFA). However, financial service providers face a unique challenge; authenticating the user's legal identity, which involves verifying Personally Identifiable Information (PII), which we call PII-based authentication (PII-BA). These methods assume that PII is private; however, identity theft victimizes millions annually and exposes their PII to criminals. In this paper, we investigate the potential of identity fraud that breaks PII-BA with stolen PII in the financial ecosystem. First, we measure what PII is used in PII-BA across five different financial services for 17 U.S. financial institutions. We subsequently collect data where PII and associated illegal services are available for purchase by monetizers (who perform identity fraud via obtained stolen PII)operating within the underground economy and paste sites. Finally, we analyze how monetizers can make money from stolen PII by either breaking PII-BA or directly monetizing the PII with the associated cost. Our study reveals that payment processing companies (PPCs) impose lower PII requirements for password/username recovery service PII-BA compared to commercial banks. Consequently, criminals can bypass this PII-BA service across all PPCs by paying 3.5-50 as opposed to 10.5-600 for banks. We also outline potential mitigations which could be an essential step in addressing identity fraud resulting from PII-BA in the financial ecosystem.
- 19 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 55-65
Open AccessNothing Personal: Understanding the Spread and Use of Personally Identifiable Information in the Financial Ecosystem
Online services leverage various authentication methods with differing usability and reliability trade-offs, such as password-based or multi-factor authentication (MFA). However, financial service providers face a unique challenge; authenticating the user's legal identity, which involves verifying Personally Identifiable Information (PII), which we call PII-based authentication (PII-BA). These methods assume that PII is private; however, identity theft victimizes millions annually and exposes their PII to criminals. In this paper, we investigate the potential of identity fraud that breaks PII-BA with stolen PII in the financial ecosystem. First, we measure what PII is used in PII-BA across five different financial services for 17 U.S. financial institutions. We subsequently collect data where PII and associated illegal services are available for purchase by monetizers (who perform identity fraud via obtained stolen PII)operating within the underground economy and paste sites. Finally, we analyze how monetizers can make money from stolen PII by either breaking PII-BA or directly monetizing the PII with the associated cost. Our study reveals that payment processing companies (PPCs) impose lower PII requirements for password/username recovery service PII-BA compared to commercial banks. Consequently, criminals can bypass this PII-BA service across all PPCs by paying 3.5-50 as opposed to 10.5-600 for banks. We also outline potential mitigations which could be an essential step in addressing identity fraud resulting from PII-BA in the financial ecosystem.
- Top Cited PapersOpen Access
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 64375-64387
RTIDS: A Robust Transformer-Based Approach for Intrusion Detection System
Due to the rapid growth in network traffic and increasing security threats, Intrusion Detection Systems (IDS) have become increasingly critical in the field of cyber security for providing secure communications against cyber adversaries. However, there exist many challenges for designing a robust, efficient and accurate IDS, especially when dealing with high-dimensional anomaly data with unforeseen and unpredictable attacks. In this paper, we propose a Robust Transformer-based Intrusion Detection System (RTIDS) reconstructing feature representations to make a trade-off between dimensionality reduction and feature retention in imbalanced datasets. The proposed method utilizes positional embedding technique to associate sequential information between features, then a variant stacked encoder-decoder neural network is used to learn low-dimensional feature representations from high-dimensional raw data. Furthermore, we apply self-attention mechanism to facilitate network traffic type classifications. Extensive experiments reveal the effectiveness of the proposed RTIDS on two publicly available real traffic intrusion detection datasets named CICIDS2017 and CIC-DDoS2019 with F1-Score of 99.17% and 98.48% respectively. A comparative study with classical machine learning algorithm support vector machine (SVM) and deep learning algorithms that include recurrent neural network (RNN), fuzzy neural network (FNN), and long short-term memory network (LSTM) is conducted to demonstrate the validity of the proposed method.
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 64375-64387
Top Cited PapersOpen AccessRTIDS: A Robust Transformer-Based Approach for Intrusion Detection System
Due to the rapid growth in network traffic and increasing security threats, Intrusion Detection Systems (IDS) have become increasingly critical in the field of cyber security for providing secure communications against cyber adversaries. However, there exist many challenges for designing a robust, efficient and accurate IDS, especially when dealing with high-dimensional anomaly data with unforeseen and unpredictable attacks. In this paper, we propose a Robust Transformer-based Intrusion Detection System (RTIDS) reconstructing feature representations to make a trade-off between dimensionality reduction and feature retention in imbalanced datasets. The proposed method utilizes positional embedding technique to associate sequential information between features, then a variant stacked encoder-decoder neural network is used to learn low-dimensional feature representations from high-dimensional raw data. Furthermore, we apply self-attention mechanism to facilitate network traffic type classifications. Extensive experiments reveal the effectiveness of the proposed RTIDS on two publicly available real traffic intrusion detection datasets named CICIDS2017 and CIC-DDoS2019 with F1-Score of 99.17% and 98.48% respectively. A comparative study with classical machine learning algorithm support vector machine (SVM) and deep learning algorithms that include recurrent neural network (RNN), fuzzy neural network (FNN), and long short-term memory network (LSTM) is conducted to demonstrate the validity of the proposed method.