Research

Online Abuse Detection

Team members: Ebuka Okpala, Song Liao

Projects:

  • Cyber-Hostility and COVID-19: In this project, the new wave of cyber-hostility occasioned by COVID-19 is investigated through exploration and analysis of data from prominent social media sites over a twelve-month period. COVID-19-related cyber-hostility targeting people based on race/ethnicity, age, social class, immigrant status, and political ideology has emerged on social media. Through this project, insights are provided into COVID-19-related cyber-hostility and, more broadly, light is shed on how people respond online to unexpected societal calamities.

  • Learning Platform and Education Curriculum for Artificial Intelligence-Driven Socially-Relevant Cybersecurity: The goal of this project is to transform recent research outcomes in emerging social-cybersecurity into an educational format. This project will develop hands-on labs that cover different dimensions of AI-driven social-cybersecurity and demonstrate the interplay between AI and cybersecurity. The hands-on labs will be integrated into a cloud-based open learning platform, which contains 1) the project team’s homegrown and classic AI-driven cyberharassment detection algorithms; 2) adversarial attacks against these AI algorithms and defenses; and 3) social issues and bias mitigation in AI models. AI-Cybersecurity Lab

Selected Publications:

  • Mingqi Li, Song Liao, Ebuka Okpala, Max Tong, Matthew Costello, Long Cheng, Hongxin Hu and Feng Luo, “COVID-HateBERT: a Pre-trained Language Model for COVID-19 related Hate Speech Detection”, IEEE International Conference on Machine Learning and Applications (ICMLA), December 13-16, 2021.

  • Matthew Costello, Long Cheng, Feng Luo, Hongxin Hu, Song Liao, Nishant Vishwamitra, Mingqi Li and Ebuka Okpala, “COVID-19: A Pandemic of Anti-Asian Hate”, Journal of Hate Studies, 2021.

  • Nishant Vishwamitra, Hongxin Hu, Feng Luo, Long Cheng, “Towards Understanding and Detecting Cyberbullying in Real-world Images”, Proceedings of the 28th Network and Distributed System Security Symposium (NDSS), 2021. (Acceptance rate: 87/573 = 15.2%).

  • Nishant Vishwamitra, Ruijia Roger Hu, Feng Luo, Long Cheng, Matthew Costello, Yin Yang, “On Analyzing COVID-19-related Hate Speech Using BERT Attention”, IEEE International Conference on Machine Learning and Applications (ICMLA), 2020.

Security and Privacy in IoT/CPS

Team members: Song Liao, Jeffrey Young, Christin Wilson, Huixing Deng

Selected Publications:

  • Hongda Li, Qiqing Huang, Fei Ding, Hongxin Hu, Long Cheng, Guofei Gu and Ziming Zhao, “Understanding and Detecting Remote Infection on Linux-based IoT Devices”, In 17th ACM ASIA Conference on Computer and Communications Security (AsiaCCS), 2022. (Acceptance rate: 54/294 = 18.4%). (Best Paper Award).

  • Jeffrey Young, Song Liao, Long Cheng, Hongxin Hu, Huixing Deng, “SkillDetective: Automated Policy-Violation Detection of Voice Assistant Applications in the Wild”, USENIX Security Symposium, 2022.

  • Wenbo Ding, Hongxin Hu, Long Cheng, “IoTSafe: Enforcing Safety and Security Policy with Real IoT Physical Interaction Discovery”, Proceedings of the 28th Network and Distributed System Security Symposium (NDSS), 2021. (Acceptance rate: 87/573 = 15.2%).

  • Long Cheng, Christin Wilson, Song Liao, Jeffrey Young, Daniel Dong, Hongxin Hu, “Dangerous Skills Got Certified: Measuring the Trustworthiness of Skill Certification in Voice Personal Assistant Platforms”, ACM Conference on Computer and Communications Security (CCS), 2020. (Acceptance rate: 121/715 = 16.9%).

  • Song Liao, Christin Wilson, Long Cheng, Hongxin Hu and Huixing Deng, “Measuring the Effectiveness of Privacy Policies for Voice Assistant Applications”, Annual Computer Security Applications Conference, (ACSAC), Dec 7-11, 2020. (Acceptance rate: 23%). (Distinguished Paper Award).

Network Security

Team members: Douglas Everson, John Anderson

Projects:

  • Network Attack Surface Analysis

  • Zero Trust

Selected Publications:

  • Douglas Everson, Long Cheng, Zhenkai Zhang, “Log4Shell: Redefining the Web Attack Surface”, 4th Workshop on Measurements, Attacks, and Defenses for the Web (MADWeb 2022), co-located with NDSS 2022.

  • Douglas Everson, Long Cheng, “Compressing Network Attack Surfaces for Practical Security Analysis”, IEEE Secure Development Conference (SecDev), 2021.

  • Douglas Everson, Long Cheng, “Network Attack Surface Simplification for Red and Blue Teams”, IEEE Secure Development Conference (SecDev), 2020.

Program Anomaly Detection

Selected Publications:

  • Long Cheng, Salman Ahmed, Hans Liljestrand, Thomas Nyman, Haipeng Cai, Trent Jaeger, N. Asokan, Danfeng (Daphne) Yao, “Exploitation Techniques for Data-Oriented Attacks with Existing and Potential Defense Approaches”, ACM Transactions on Privacy and Security (TOPS), April 2021.

  • Long Cheng, Hans Liljestrand, Md Salman Ahmed, Thomas Nyman, Danfeng (Daphne) Yao, Trent Jaeger, N. Asokan, “Exploitation Techniques and Defenses for Data-Oriented Attacks”, IEEE Secure Development 2019 (SecDev), McLean, VA, USA, 2019

  • Long Cheng, Ke Tian, Danfeng (Daphne) Yao, Lui Sha, Raheem A. Beyah, “Checking is Believing: Event-Aware Program Anomaly Detection in Cyber-Physical Systems”, in IEEE Transactions on Dependable and Secure Computing (TDSC), 2019

  • Long Cheng, Ke Tian, Danfeng Yao. “Enforcing Cyber-Physical Execution Semantics to Defend Against Data- Oriented Attacks”, in Annual Computer Security Applications Conference (ACSAC). Puerto Rico, US. Dec. 2017. (Acceptance rate: 19.7%).