Y
Yuede Ji
Researcher at George Washington University
Publications - 26
Citations - 258
Yuede Ji is an academic researcher from George Washington University. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 7, co-authored 20 publications receiving 158 citations. Previous affiliations of Yuede Ji include University of North Texas & Jilin University.
Papers
More filters
Journal ArticleDOI
Detection of Forwarding-Based Malicious URLs in Online Social Networks
TL;DR: This work is the first to analyze forwarding-based features in OSNs and offers a valuable contribution to this area of research.
Journal ArticleDOI
Combating the evasion mechanisms of social bots
TL;DR: This study comprehensively analyzes the evasion mechanisms used by existing social bots and validate those mechanisms by applying three state-of-the-art detection approaches to the collected traces and proposes a new detection approach that incorporates nine newly identified features and two new correlation mechanisms.
Proceedings Article
Detecting Lateral Movement in Enterprise Computer Networks with Unsupervised Graph {AI}
TL;DR: This paper presents a technique for detecting lateral movement of Advanced Persistent Threats inside enterpriselevel computer networks using unsupervised graph learning, and applies this technique to authentication data derived from two contrasting data sources: a small-scale simulated environment, and a large-scale real-world environment.
Proceedings ArticleDOI
iSpan: parallel identification of strongly connected components with spanning trees
Yuede Ji,Hang Liu,H. Howie Huang +2 more
TL;DR: A new paradigm of identifying SCCs with simple spanning trees is advocated, since SCC detection requires only the knowledge of connectivity among the vertices, which is able to significantly outperform current state-of-the-art DFS and BFS-based methods.
Proceedings ArticleDOI
BugGraph: Differentiating Source-Binary Code Similarity with Graph Triplet-Loss Network
Yuede Ji,Lei Cui,H. Howie Huang +2 more
TL;DR: BugGraph as discussed by the authors uses a triplet loss network on the attributed control flow graph to produce a similarity ranking for source-binary code similarity detection, achieving 90% and 75% true positive rate for syntax equivalent and similar code, respectively, an improvement of 16% and 24% over state-of-theart methods.