Soojin Yoon

Soojin Yoon, Sungho Ko, Tongyoung Kim et al.

Cross-lingual entity alignment (EA) enables the integration of multiple knowledge graphs (KGs) across different languages, providing users with seamless access to diverse and comprehensive knowledge. Existing methods, mostly supervised, face challenges in obtaining labeled entity pairs. To address this, recent studies have shifted towards self-supervised and unsupervised frameworks. Despite their effectiveness, these approaches have limitations: (1) Relation passing: mainly focusing on the entity while neglecting the semantic information of relations, (2) Isomorphic assumption: assuming isomorphism between source and target graphs, which leads to noise and reduced alignment accuracy, and (3) Noise vulnerability: susceptible to noise in the textual features, especially when encountering inconsistent translations or Out-of-Vocabulary (OOV) problems. In this paper, we propose ERAlign, an unsupervised and robust cross-lingual EA pipeline that jointly performs Entity-level and Relation-level Alignment by neighbor triple matching strategy using semantic textual features of relations and entities. Its refinement step iteratively enhances results by fusing entity-level and relation-level alignments based on neighbor triple matching. The additional verification step examines the entities' neighbor triples as the linearized text. This Align-then-Verify pipeline rigorously assesses alignment results, achieving near-perfect alignment even in the presence of noisy textual features of entities. Our extensive experiments demonstrate that the robustness and general applicability of ERAlign improved the accuracy and effectiveness of EA tasks, contributing significantly to knowledge-oriented applications.

JongHun Jung, Hwan-Kuk Kim, Soojin Yoon

Recent web-based cyber attacks are evolving into a new form of attacks such as private information theft and DDoS attack exploiting JavaScript within a web page. These attacks can be made just by accessing a web site without distribution of malicious codes and infection. Script-based cyber attacks are hard to detect with traditional security equipments such as Firewall and IPS because they inject malicious scripts in a response message for a normal web request. Furthermore, they are hard to trace because attacks such as DDoS can be made just by visiting a web page. Due to these reasons, it is expected that they could result in direct damages and great ripple effects. To cope with these issues, in this article, a proposal is made for techniques that are used to detect malicious scripts through real-time web content analysis and to automatically generate detection signatures for malicious JavaScript.