News 소식

paper Two papers accepted at IC-EEECS 2026 — the NER–LLM consolidation pipeline for metadata extraction from Korean public-domain rights documents, and the KLUE-BERT B-I-O training-data composition analysis.

lab Recruiting graduate students — Soongsil 2026 fall (후기) graduate admissions: applications June 8–16, interviews June 26, results July 21 (grad.ssu.ac.kr).

paper Research impact: the FAST flash translation layer paper (ACM TECS 2007) has passed 700 citations.

paper Revised manuscript on lightweight on-device vishing detection submitted to IEEE Access (revise-and-resubmit).

paper Multimodal audio–text Korean vishing detection presented at KCC 2025, with four student co-authors.

project The lab joins the Muhayu-led MCST/KOCCA R&D consortium building copyright-metadata AI for openly licensed works (with HM Company; demand organizations: Korea Copyright Commission and KCISA).

paper IEEE Access publishes our study on enhancing voice-phishing detection with multilingual back-translation and SMOTE.

dataset Augmented Korean voice-phishing detection dataset released on IEEE DataPort (CC BY-NC-SA 4.0, DOI 10.21227/163c-0542).

patent Korean patent granted: "Deep learning-based voice phishing detection apparatus and method" (KR 10-2640315, filed 2022 with Soongsil University IACF).

paper Journal paper published in KIPS Transactions on Software and Data Engineering — exploiting the KoBERT Korean language model to improve voice-phishing detection (accuracy 99.60%).

award Outstanding Paper Award (우수논문상) at KCC 2022 for the attention-based CNN-BiLSTM Korean voice-phishing detection model.

paper An attention-based CNN-BiLSTM model for Korean voice-phishing detection presented at KCC 2022 in Jeju.

award Encouragement Paper Award (장려논문상) at KIPS ACK 2021 (Yeosu) for our machine-learning study of Korean voice-phishing text classification.

dataset KorCCVi — the first labeled Korean voice-phishing transcript dataset — introduced alongside a real-time AI detection technique at KCC 2021 (Jeju).