森研究室の戸田宇亮君と森による論文「セキュリティ用オープンLLMエージェントシステムのエンジニアリングガイド」が、2026年暗号と情報セキュリティシンポジウム（SCIS2026）において SCIS論文賞 を受賞しました。おめでとうございます！表彰式は SCIS2027（2027年1月）の会期中に行われる予定です。
戸田 宇亮, 森 達哉, 「セキュリティ用オープンLLMエージェントシステムのエンジニアリングガイド」, 2026年暗号と情報セキュリティシンポジウム（SCIS2026）, 3G3-1, 2026年1月.
We are thrilled to announce that our workshop paper entitled “Large-Scale Analysis of Malware Distribution via Fake Game Cheats and Cracked Software on YouTube” has been accepted for publication in the 5th Workshop on Attackers and Cyber-Crime Operations (WACCO 2026), co-located with IEEE EuroS&P 2026. Congratulations Yamagishi-kun!
In this work, we present VIPER (VIdeo Platform Exploitation Reconnaissance), an automated system that continuously monitors YouTube for malware distribution campaigns masquerading as game cheats or cracked software—a class of threat we term VidCrackBait. VIPER iteratively updates its search queries to track evolving attack patterns and harvests video metadata via the YouTube Data API v3. Over five months, VIPER collected 104,974 videos from 38,855 unique channels, identifying 6,976 distinct fully qualified domain names embedded in descriptions and comments. Our analysis reveals that attackers target popular competitive games with recurring title/description/thumbnail patterns, and we identify 396 intermediate YouTube channels that post no content but serve as persistent relay nodes—forming multi-stage redirection chains that link YouTube to messaging platforms, file-hosting services, and social media.
Rei Yamagishi, Shota Fujii, and Tatsuya Mori, "Large-Scale Analysis of Malware Distribution via Fake Game Cheats and Cracked Software on YouTube." In Proc. of the 5th Workshop on Attackers and Cyber-Crime Operations (WACCO 2026), co-located with IEEE EuroS&P 2026, Venice, Italy, Jun 2026.
森研究室の掛林諒平君と森による論文「Text-to-Imageモデルに対するデータ汚染攻撃の多言語環境での脆弱性要因と防御手法の提案」が、2025年度 情報通信システムセキュリティ研究賞（ICSS研究賞）を受賞しました。おめでとうございます！
掛林 諒平, 森 達哉, 「Text-to-Imageモデルに対するデータ汚染攻撃の多言語環境での脆弱性要因と防御手法の提案」, 電子情報通信学会 ICSS研究会（2026年3月研究会, 沖縄県立博物館・美術館）, 2026年3月.
We’re excited to welcome one new PhD student, five new master’s students, and seven new undergraduate students to our lab!
We are thrilled to announce that our conference paper entitled “Cross-Lingual Vulnerabilities of Text-to-Image Models: Evaluating Data Poisoning Attacks Across Ten Languages” has been accepted for publication in the 28th International Conference on Pattern Recognition (ICPR 2026). Congraturations Kakebayashi-kun!
Ryohei Kakebayashi and Tatsuya Mori, "Cross-Lingual Vulnerabilities of Text-to-Image Models: Evaluating Data Poisoning Attacks Across Ten Languages." In Proc. of the 28th International Conference on Pattern Recognition (ICPR 2026) Lyon, France, Sep 2026. Published in Springer LNCS.