logo EECS Rising Stars 2023

Chen Ling

Understanding and Mitigating Toxicity in Cyber-Security: Using a Multi-Modal, Cross-Platform, and Mixed-Method Approach

Research Abstract:

Since the start of the COVID-19 pandemic, social media have become even more important in our social lives, and this trend will have a long-term impact. At the same time, the speed and scale of online information spread may reduce the quality of the content, and expose social media to risk. Moderation is an important challenge. Current moderation systems of social media are facing a constantly changing ecosystem. In particular, abusive attacks are shaped by technology and social events. Different online communities have different characteristics and often abuse unfolds across multiple communities. There is therefore a need to investigate how well-existing moderation systems work. At the same time, we need to know how moderation could be improved. Previous research on analyzing social interactions focused on text information, developing Natural Language Processing (NLP) tools, looking at propagation patterns, etc. However, people do not only post text but also include images and videos on social media In fact, viral online content is often spread through visual, and audible formats, including image memes or short videos. The research community lacks computational tools to model and track this multi-modal content at scale. My research aims to help social media improve its usability and security, providing solutions to reduce the risks of users from abusive attacks. To achieve this, I measure current abusive behavior online to get a better understanding of it and develop solutions from two perspectives: one is to improve platform design, and the other is to improve the moderation system. My research helps us better understand online abusive behavior and provides a foundation for developing automated mitigations.


Chen Ling is a Ph.D. Candidate in the ECE Department at Boston University working with Prof. Gianluca Stringhini. She studies security and social computing, with a focus on harassment, misinformation, and its moderation. She uses a multi-modal, cross-platform, and mixed-method approach to help social media improve its usability and security, providing solutions to reduce the risks of users from abusive attacks. Her work has been published in top-tier journals and conferences, including IEEE S&P, ACM CSCW, AAAI ICWSM, and has been reported by Wired, New Scientist, and the Washington Post. Chen is the recipient of the 2022 Meta PhD fellowship in Security and Privacy, a Hariri student Fellow at Boston University, and was a visiting scholar at Max Planck Institute supported by a fellowship.