SYNTHETIQ X: Research Platform for Defending and Preventing Spread of Fake Information JST K Program: AI Security

JAPANESE SITE MAP
  1. Home
  2. Achievements

Achievements

Refereed journal papers　|　Refereed conference papers　|　Preprints　|　Books, book chapters, and research reports　|　Invited talks　|　Oral Presentation, Poster・demo　|　Media coverage(Press release/ News release)　|　Media coverage(Online articles)　|　Media coverage(TV / Radio)　|　Media coverage(Newspapers)　|　Media coverage(Others)　|　Patents　|　Awards　|　Others

Refereed journal papers

  1. C.-C. Chang and I. Echizen, "Steganography beyond space-time with chain of multimodal AI,", Scientific Reports, 2025
  2. S. Liang, H. Nguyen, S. Ikehata, J. Yamagishi, I. Echizen, "3D Morphable Master Face: Towards Controllable Wolf Attacks against 2D and 3D Face Recognition Systems,", EURASIP Journal of Information Security, APSIPA Transactions on Signal and Information Processing, 2025
  3. S. Xu, C.-C. Chang, H, H. Nguyen, I. Echizen, "Reversible anonymization for privacy of facial biometrics via cyclic learning,", EURASIP Journal of Information Security, 2024
  4. A. MaungMaung, I. Echizen and H. Kiya, "Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-Trained Models,", IEEE Open Journal of Signal Processing, vol. 5, pp. 902-913, 2024, doi: 10.1109/OJSP.2024.3419569,
  5. T. Ouyang, Y. Seo, and I. Echizen, "Textual out-of-distribution (OOD) detection for LLM quality assurance,", Knowledge-Based Systems, Elsevier, 2025, Feb. 2025,
  6. C. C. Chang and I. Echizen, "Steganography in Game Actions,", IEEE Access, 2025, Jan. 2025,
  7. T. Ouyang, A. MaungMaung, K. Konishi, Y. Seo, I. Echizen, "Stability Analysis of ChatGPT-Based Sentiment Analysis in AI Quality Assurance,", Electronics 2024, 13(24), Dec. 2024,

Refereed conference papers

  1. T. Spinde, L. Lin, S. Hinterreiter, and I. Echizen, "Leveraging Large Language Models for Automated Definition Extraction with TaxoMatic A Case Study on Media Bias," ICWSM 2025,
  2. R. Shukla, H. Kaur, and I. Echizen, "Analyzing Face Image Inpainting with Attribute-Driven Generative Network," IJCNN 2025,
  3. Y. Sun, F. Savonuzzi, C.-C. Chang, X. Zhang, and I. Echizen, "VIP: Versatile Identity Protection with Dual-property Watermarking System," IJCNN 2025,
  4. Y. Guo, Z. Dou, H. Nguyen, C.-C. Chang, S. Sugawara, and I. Echizen, "Measuring Human Involvement in AI-Generated Text: A Case Study on Academic Writing," IJCNN 2025,
  5. F. Waseda, C.-C. Chang, and I. Echizen, "Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off," ICLR 2025,
  6. E. Bao, C. C. Chang, H. Wang, I. Echizen, "Purification-Agnostic Proxy Learning for Agentic Copyright Watermarking against Adversarial Evidence Forgery," Proc. 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025), Apr. 2025, Link
  7. R. Shulka, H. PKaur, I. Echizen, "Parallel Prints: Generating Realistic Cancelable Fingerprint Templates," Proc. 2025 WACV Workshop on Synthetic Realities and Data in Biometric Analysis and Security (WACVW 2025), Feb. 2025,
  8. H. Nguyen, G. Delvecchio, I. Echizen, "Zero-Shot Warning Generation for Misinformative Multimodal Content," Proc. 2025 WACV Workshop on Artificial Intelligence for Multimedia Forensics and Disinformation Detection (WACVW 2025), Feb. 2025,
  9. F. Hsieh, H. H. Nguyen, A. MaungMaung, D. Usynin, I. Echizen, "Mitigating Backdoor Attacks using Activation-Guided Model Editing," Proceedings of the Asian Conference on Computer Vision (ACCV) Workshops, 2024, pp. 302-318, Dec. 2024, Link
  10. Y. Ji, I. Echizen, "StrucTrans: Zero-Query Structural Adversarial Attack Transferred from Masked Autoencoders to Image Classifiers," Proc. the 23rd IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom 2024), Dec. 2024,
  11. R. Disabato, A. MaungMaung, H. Nguyen, I. Echizen, "Transfer-Based Adversarial Attack Against Multimodal Models by Exploiting Perturbed Attention Region," Proc. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2024, Dec. 2024,
  12. H-Quoc Nguyen-Son, S. Hidano, K. Fukushima, S. Kiyomoto, I. Echizen, "OneWORD: Adversarial Text Detection and Prediction Restoration Using One-Word Perturbation," Proc. 31st International Conference on Neural Information Processing (ICONIP 2024), Dec. 2024,

Books, book chapters, and research reports

    Invited talks

    1. Isao Echizen, "Real or Fake? Frontiers of Countering Fake Media in the Age of Infodemics", Invited talk at overview session, APSIPA ASC 2024, Macau, December 6, 2024, Link

    Oral Presentation, Poster・demo

    Media coverage(Press release/ News release)

    Media coverage(Online articles)

    1. Isao Echizen, NIKKEI ASIA, 30 years after subway sarin attack, Japan faces lone wolves aided by AI, March 21, 2025
    2. Kazutoshi Sasahara, Junichi Yamagishi, Isao Echizen, the japantimes, Japan launches industry and academia tie-up to combat online disinformation, January 27, 2025
    3. Isao Echizen, NIKKEI ASIA, Voters across Asia contend with AI-generated fake videos and images , January 18, 2025
    4. Isao Echizen, The Mainichi Japan's National Daily, Fake scientific papers made with AI used names of 3 Japan researchers, January 15, 2025

    Media coverage(TV / Radio)

    Media coverage(Newspapers)

    Media coverage(Others)

    Patents

    Awards

    Others