Mrs. Guoqin Chang | AI Security | Excellence in Research Award
Mrs. Guoqin Chang | AI Security | Shaanxi Science and Technology Holding Institute | China
Mrs. Guoqin Chang holds a Ph.D. in Cyberspace Security from the School of Cybersecurity at Xidian University and currently leads the Artificial Intelligence Research Group at Shaanxi KeKong Technology Industry Research Institute, while also serving as Technical Advisor to the Shaanxi Printing Science and Technology Research Institute. Over her career, Chang Guoqin has built expertise in natural language processing (NLP), domain-specific large language model deployment, prompt engineering, fine-tuning and adaptation of models, AI model security, detection of text generated by large language models, adversarial text attacks/defenses, and multimodal information fusion. She is skilled in designing and evaluating robust NLP pipelines, adversarial-robust model architectures, secure model deployment, domain adaptation techniques, and text classification systems with security-aware defenses. Her professional experience spans research and development, project leadership, and peer-reviewing for major journals including Information Sciences and Computer Engineering and Design, and she has contributed to both academic publications and applied software/patents through her inventive activity. Through her publication record, patent filings, software copyrights, and R&D project involvement, Chang Guoqin has demonstrated a strong commitment to improving the security, robustness, and domain-adaptability of modern AI. In conclusion, Chang Guoqin brings together advanced academic training, deep technical skills in NLP security and model adaptation, and real-world engineering experience positioning her as a leading researcher/engineer in secure, domain-specific artificial intelligence and robust natural language processing solutions.
Selected Publications
-
Chang, G., Gao, H., Yao, Z., & Xiong, H. (2023). TextGuise: Adaptive adversarial example attacks on text classification model.
-
Chang, G., Gao, H., Pei, G., … & Guo, Q. (2024). The robustness of behavior-verification-based slider CAPTCHAs. Journal of Information Security and Applications.
-
Cheng, L., Zhang, Z., & Chang, G. (2019). Multimedia Social Network Authorization Scheme of Comparison-based Encryption.
-
Cheng, N., Chang, G., & Gao, H. (2020). WordChange: Adversarial Examples Generation Approach for Chinese Text Classification.
-
Chang, G., Gao, H., & Li, B. (2025). TextShelter: Text Adversarial Example Defense Based on Input Reconstruction.
-
Chang, G., & colleagues. (2019). A Survey of Research on CAPTCHA Designing and Breaking Techniques.
-
Cheng, N., Chang, G., Gao, H., … & Zhang, Y. (2020). WordChange: Adversarial Examples Generation Approach for Chinese Text Classification.