I am Hoang-Quoc Nguyen-Son, working at the National Institute Of Information And Communications Technology (NICT). I obtained my Doctorate degree in 2015 from the Informatics Department at The Graduate University for Advanced Studies (SOKENDAI), Japan, under the guidance of Professor Isao Echizen. Following that, I served as a PostDoc researcher at NII and KDDI. My primary research interest lies in security within Natural Language Processing and Computer Vision.

Email: quoc-nguyen(at)nict.go.jp

News

• [2023-10-06] A collaboration paper is accepted at APSEC 2023 

• [2023-06-09] I accepted an invitation as a reviewer for EMNLP 2023

• [2023-05-01] Our paper is accepted at Findings of ACL 2023

• [2023-02-12] I accepted an invitation as a reviewer for ACL 2023

Research Achievements

2023

Conference

1. 1. Hoang-Quoc Nguyen-Son, Seira Hidano, Kazuhide Fukushima, Shinsaku Kiyomoto and Isao Echizen, "VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations". Finding of The 61st Annual Meeting of the Association for Computational Linguistics (ACL), July 2023 , Long paper

   2. Tinghui Ouyang, Hoang-Quoc Nguyen-Son, Huy H. Nguyen, Isao Echizen and Yoshiki Seo, "Quality Assurance of A GPT-based Sentiment Analysis System: Adversarial Review Data Generation and Detection," 30th Asia-Pacific Software Engineering Conference (APSEC), December 2023 (accepted)

2022

Conference

1. 3. Hoang-Quoc Nguyen-Son, Huy Quang Ung, Seira Hidano, Kazuhide Fukushima and Shinsaku Kiyomoto, "CheckHARD: Checking Hard Labels for Adversarial Text Detection, Prediction Correction, and Perturbed Word Suggestion". Finding of Conference on Empirical Methods in Natural Language Processing (EMNLP), December 2022 (accepted, long paper, Sentiment Analysis, Stylistic Analysis, and Argument Mining Track)

   4. Duc-Thinh Le, Nhat-Anh Pham-Hoang, Vi-Minh Luong, Hoang-Quoc Nguyen-Son, Minh-Triet Tran. "Document Representation with Representative Sets and Document Similarity at Sentence Level Using Maximum Matching in Bipartite Graph". Proc. of the 8th International Conference on Future Data and Security Engineering (FDSE), pp.3-22, November 2022

2021

Conference

1. Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, Ishita Gupta, and Shinsaku Kiyomoto, "Machine Translated Text Detection Through Text Similarity with Round-Trip Translation". Proceedings of Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), June 2021, pp. 5792–5797 (Acceptance rate: 123/544=22.6%, Machine Translation Track)

1. 5. Hoang-Quoc Nguyen-Son, Seira Hidano, Kazuhide Fukushima, and Shinsaku Kiyomoto, "SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text", Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation (PACLIC), November 2021, pp. 11-20 (oral)

   6. Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, Vanessa Bracamonte, Shinsaku Kiyomoto and Rie Shigetomi Yamaguchi, "OPA2D: One-Pixel Attack, Detection, and Defense in Deep Neural Networks". Proceedings of International Joint Conference on Neural Networks (IJCNN), July 2021, pp. 1-10 (oral)

2020

Conferences

1. Tran Phuong Thao, Yukiko Sawaya, Hoang-Quoc Nguyen-Son, Akira Yamada, Ayumu Kubota, Sang Tran Van and Rie Shigetomi Yamaguchi, "Human Factors in Homograph Attack Recognition". Proceedings of 18th International Conference on Applied Cryptography and Network Security (ACNS), June 2020

2. Zicong Zhu, Tran Phuong Thao, Hoang-Quoc Nguyen-Son, Rie Shigetomi Yamaguchi, and Toshiyuki Nakata, "Enhancing A New Classification for IDN Homograph Attack Detection". In: Proceedings of the 18th IEEE International Conference on Dependable, Autonomic and Secure Computing (DASC), 2020.

3. Zicong Zhu, Tran Phuong Thao, Hoang-Quoc Nguyen-Son, Rie Shigetomi Yamaguchi, and Toshiyuki Nakata, "Enhanced Classification Method for Homograph Attack Detection". In: Proceedings of the 7th International Workshop on Information and Communication Security (WANC), 2020

4. Tran Phuong Thao, Hoang-Quoc Nguyen-Son, Rie Shigetomi Yamaguchi, and Toshiyuki Nakata, "Boosting Homograph Attack Classification Using Ensemble Learning and N-gram Model". In: Proceedings of the 1st International Workshop on Machine Learning for Trust, Security and Privacy in Computing and Communications (MLTrustCom), Trustcom workshop, 2020

Domestic conferences

1. Hoang-Quoc Nguyen-Son, Seira Hidano, Tran Phuong Thao, Ishita Gupta, Shinsaku Kiyomoto, "Towards efficient detection of machine-translated texts ". Symposium on Cryptography and Information Security (SCIS), January 2020.

2. Zhu Zicong, Tran Phuong Thao, Hoang-Quoc Nguyen-Son, Rie Shigetomi Yamaguchi, Toshiyuki Nakata, "An Improved Classification Method for IDN Homograph Attack". Symposium on Cryptography and Information Security (SCIS), January 2020.

Patent

• 1. Hoang-Quoc Nguyen-Son, Seira Hidano, and Shinsaku Kiyomoto, “Detecting an adversarial text and its victim system based on prediction similarities among candidate systems" No P2020-0084JP01, Japan

2019

Journal

1. Ngoc-Dung T. Tieu, Huy H. Nguyen, Hoang-Quoc Nguyen-Son, Junichi Yamagishi, and Isao Echizen, “Spatio-Temporal Generative Adversarial Network for Gait Anonymization,” Special Issue on Data Intelligence in Security and Privacy, Journal of Information Security and Applications (JISA), 307-319, Elsevier, 2019 

Conferences

1. Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, and Shinsaku Kiyomoto, “Detecting Machine-Translated Text using Back Translation,” Proceedings of 12th International Conference on Natural Language Generation (INLG), November 2019

2. Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, and Shinsaku Kiyomoto, “Identifying Adversarial Sentences by Analyzing Text Complexity,” Proceedings of Pacific Asia Conference on Language, Information and Computation (PACLIC), September 2019

3. Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, and Shinsaku Kiyomoto, “Detecting Machine-Translated Paragraphs by Matching Similar Words,” Proceedings of International Conference on Computational Linguistics and Intelligent Text Processing (CICLING), LNCS, April 2019

4. Tran Phuong Thao, Yukiko Sawaya, Hoang-Quoc Nguyen-Son, Akira Yamada, Kazumasa Omote and Ayumu Kubota, “Hunting Brand Domain Forgery: A Scalable Classification For Homograph Attack,” Proceedings of the 34th International Information Security and Privacy Conference (IFIP SEC), June 2019

Domestic conferences

1. Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, and Shinsaku Kiyomoto, "Coherence-based Spoken Machine Translation Recognition: Towards an Efficient Gateway to Detect Untrusted Information" ISEC 2019, Japan, March 2019

2. Gupta Ishita, Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, and Shinsaku Kiyomoto, "Integrating Back-Translation into BERT Model for Detecting Machine-Translated Text" CSS 2019, Nagasaki, Japan, October 2019

3. Tran Phuong Thao, Yukiko Sawaya, Hoang-Quoc Nguyen-Son, Akira Yamada, Kazumasa Omote and Ayumu Kubota, “A Classification Model For Visual Homograph Attack," Symposium on Cryptography and Information Security SCIS 2019, Japan, January 2019

Patents

• 2. Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, and Shinsaku Kiyomoto, “Toward a classification of data generated by human and data generated by machine" No P2019-0190JP01, Japan

  3. Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, and Shinsaku Kiyomoto, “An approach for detecting adversarial texts," No P2019-0111JP01, Japan

2018

Conferences

1. Hoang-Quoc Nguyen-Son, Ngoc-Dung T. Tieu, Huy H. Nguyen, Junichi Yamagishi, and Isao Echizen, “Identifying Computer-Generated Paragraphs using Coherence Features,” Proceedings of Pacific Asia Conference on Language, Information and Computation (PACLIC), 8 pages, December 2018 

2. Huy H. Nguyen, Ngoc-Dung T. Tieu, Hoang-Quoc Nguyen-Son, Vincent Nozick, Junichi Yamagishi, and Isao Echizen, “Modular Convolutional Neural Network for Discriminating between Computer-Generated Images and Photographic Images,” Proceedings of the International Conference on Availability, Reliability and Security (ARES), August 2018

3. Huy H. Nguyen, Ngoc-Dung T. Tieu, Hoang-Quoc Nguyen-Son, Junichi Yamagishi, and Isao Echizen, “Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector,” Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), July 2018 

4. Hoang-Quoc Nguyen-Son, Nam-Phong Tran, Ngoc-Vien Pham, Minh-Triet Tran, and Isao Echizen, "Vietnamese Paraphrase Identification Using Matching Duplicate Phrases and Similar Words," Proc. of the 5th International Conference on Future Data and Security Engineering (FDSE), pp.172-182, November 2018

Patents

1. Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, and Shinsaku Kiyomoto, “An approach for classifying machine and human translations," No P2018-0401JP01

2. Tran Phuong Thao, Yukiko Sawaya, Hoang-Quoc Nguyen-Son, Akira Yamada, and Ayumu Kubota, “An approach for detecting visual homograph domains," No P2018-0344JP01

2017

Conferences

• 1. Hoang-Quoc Nguyen-Son and Isao Echizen, “Detecting Computer-Generated Text Using Fluency and Noise Features,” Proceedings of Conference of the Pacific Association for Computational Linguistics (PACLING), pp. 288-300, August 2017

  2. Hoang-Quoc Nguyen-Son, Ngoc-Dung T. Tieu, Huy H. Nguyen, Junichi Yamagishi, and Isao Echizen, “Identifying Computer-Generated Text Using Statistical Analysis,” Proceedings of the Asia-Pacific Signal and Information Processing Association (APSIPA), pp. 1504-1511, December 2017

  3. Ngoc-Dung T. Tieu, Huy H. Nguyen, Hoang-Quoc Nguyen-Son, Junichi Yamagishi, and Isao Echizen, “An Approach for Gait Anonymization using Deep Learning,” Proceedings of the IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1-6, December 2017 (Best paper award)

Before 2017

Journal

1. Hoang-Quoc Nguyen-Son, Minh-Triet Tran, Hiroshi Yoshiura, Noboru Sonehara, and Isao Echizen, “Anonymizing Personal Text Messages Posted in Online Social Networks and Detecting Disclosures of Personal Information,” Special Issue on Enriched Multimedia, IEICE Transactions on Information and Systems, volume 98, pp. 78-88, January 2015 

Conferences

• 1. Hoang-Quoc Nguyen-Son, Yusuke Miyao, and Isao Echizen, “Paraphrase Detection Based on Identical Phrase and Similar Word Matching,” Proceedings of the Pacific Asia Conference on Language, Information and Computation (PACLIC), pp. 508-516, October 2015

  2. Huy H. Nguyen, Hoang-Quoc Nguyen-Son, Thuc Nguyen, and Isao Echizen, “Discriminating between Computer-Generated Facial Images and Natural Ones Using Smoothness Property and Local Entropy,” Proceedings of the International Workshop on Digital-Forensics and Watermarking (IWDW), pp. 39-50, October 2015

  3. Hoang-Quoc Nguyen-Son, Minh-Triet Tran, Hiroshi Yoshiura, Noboru Sonehara, and Isao Echizen, “A Rule-Based Approach for Detecting Location Leaks of Short Text Messages,” Workshop on Privacy by Transparency in Data-Centric Services (PTDCS), Proceedings of the International Conference on Business Information Systems (BIS), pp. 199-210, June 2015

  4. Hoang-Quoc Nguyen-Son, Minh-Triet Tran, Hiroshi Yoshiura, Noboru Sonehara, and Isao Echizen, “A System for Anonymizing Temporal Phrases of Message Posted in Online Social Networks and for Detecting Disclosure,” the 4th International Workshop on Resilience and IT-Risk in Social Infrastructures (RISI), Proceedings of the International Conference on Availability, Reliability and Security (ARES), pp. 455-460, September 2014

  5. Hoang-Quoc Nguyen-Son, Anh-Tu Hoang, Minh-Triet Tran, Hiroshi Yoshiura, Noboru Sonehara, and Isao Echizen, “Anonymizing Temporal Phrases in Natural Language Text to be Posted on Social Networking Services,” Proceedings of the International Workshop on Digital-Forensics and Watermarking (IWDW), pp. 437-451, October 2013

  6. Anh-Tu Hoang, Hoang-Quoc Nguyen-Son, Minh-Triet Tran, and Isao Echizen, “Detecting Traitors in Re-Publishing Updated Datasets,” Proceedings of the International Workshop on Digital-Forensics and Watermarking (IWDW), pp. 205-220, October 2013

  7. Hoang-Quoc Nguyen-Son, Minh-Triet Tran, Tien-Dung Tran, Hiroshi Yoshiura, Noboru Sonehara, and Isao Echizen, “Automatic Anonymous Fingerprinting of Text Posted on Social Networking Services”, Proceedings of the International Workshop on Digital-Forensics and Watermarking (IWDW), pp. 410-424, October 2012

  8. Hoang-Quoc Nguyen-Son, Quoc-Binh Nguyen, Minh-Triet Tran, Dinh-Thuc Nguyen, Hiroshi Yoshiura, and Isao Echizen, “Automatic Anonymization of Natural Languages Texts Posted on Social Networking Services and Automatic Detection of Disclosure,” the 7th International Workshop on Frontiers in Availability, Reliability and Security (FARES), Proceedings of the International Conference on Availability, Reliability and Security (ARES), pp. 358-364, August 2012

  9. Hoang-Quoc Nguyen-Son, Quoc-Binh Nguyen, Minh-Triet Tran, Dinh-Thuc Nguyen, Hiroshi Yoshiura, and Isao Echizen, “New Approach to Anonymity of User Information on Social Networking Services,” the 6th International Symposium on Digital Forensics and Information Security (DFIS-12), Proceedings of the FTRA International Conference on Future Information Technology (FUTURETECH), pp. 731-739, June 2012

  10. Hoang-Quoc Nguyen-Son, Tam Le, Hoang-Long Nguyen, and Minh-Triet Tran, “Digital Identity Management System with Identity Information Stored in Mobile Devices”, Proceedings of the Information and Communication Technology in Faculty of Information (ICTFIT), pp. 81-90, November 2010

Domestic conferences

1. Hoang-Quoc Nguyen-Son, Hiroshi Yoshiura Noboru Sonehara, and Isao Echizen, "A Recommendation System for Anonymous Fingerprinting of Text Posted on Social Networks," The Enriched Multimedia (EMM2013), IEICE Technical Report, vol. 113, no. 66, pp. 31-36, May 2013

2. Hoang-Quoc Nguyen-Son, Quoc-Binh Nguyen, Minh-Triet Tran, Dinh-Thuc Nguyen, Hiroshi Yoshiura and Isao Echizen, "Automatic Anonymous Fingerprinting of Text Posted on Social Networking Services," the 29th Symposium on Cryptography and Information Security (SCIS), Japan February 2012

Research Activities

Session Chair

• PACLIC 2021

• VANJ 2020 (Session: Deep Learning in NLP)

• PACLIC 2019

Speaker

• VANJ 2020 (Title: Machine-Generated Text Detection by Estimating the Similarity With Its Extra Generation)

Conference Review

• EMNLP 2023 (3 long papers and 2 short papers)

• ACL 2023 ( 1 long paper)

• ARR 2022 October (2 long papers) (main target for EACL 2023)

• EMNLP 2022 (2 long papers)

• ARR 2022 February (1 long paper)

• ARR 2022 January (1 long paper)

• ARR 2021 December (1 long paper) (main target for NAACL 2022)

• ARR 2021 November (5 long papers) (main target for ACL 2022)

• EMNLP 2021 (long and short papers)

• ACMMM 2018

Journal Review

• TEVC 2021

• LREV 2021

• TIP

• IEICE