Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement
为解决AI诗歌系统削弱用户创作主动性的缺点，通过用户驱动、古文引导和AI辅助的三元模型，提升古典诗词创作中的可控性、可解释性和用户参与度。
0 citationsRead paper
Selected work
Representative Papers
A fragile zero-watermarking method based on dual quaternion matrix decomposition
Medical images face two critical security risks during transmission and sharing: ambiguous copyright ownership and vulnerability to unauthorized content tampering. To address these challenges, this paper proposes a fragile zero-watermarking method based on dual quaternion matrix decomposition. The approach models structural image features by exploiting the intrinsic algebraic relationship between the standard and dual parts of dual quaternions, and employs low-rank matrix decomposition to extract stable features that are simultaneously robust against benign distortions and sensitive to malicious alterations. The resulting zero-watermarking scheme is embedding-free and lossless, requiring no modification to the original image. It enables fine-grained copyright authentication and pixel-level tamper localization. Experimental results demonstrate high sensitivity—accurately detecting minute tampering—strong robustness against common signal processing operations (e.g., JPEG compression, filtering), and computational efficiency. The method thus offers practical utility for securing medical imaging data.
0 citationsRead paper
Attack and defense techniques in large language models: A survey and new perspectives
This survey addresses critical security vulnerabilities in large language models (LLMs), including adversarial prompting, model extraction, and application-layer attacks—alongside their corresponding defenses. It identifies key limitations in existing defensive approaches: insufficient adaptability to evolving threats, suboptimal robustness–utility trade-offs, and poor resource efficiency. To address these gaps, the work proposes a novel, end-to-end LLM security taxonomy—the first of its kind—spanning the full attack-defense lifecycle. Three foundational research directions are introduced: (1) scalable adaptive defense mechanisms, (2) interpretable security frameworks, and (3) standardized, reproducible evaluation protocols. Methodologically, the study integrates systematic literature review, rigorous threat modeling, and cross-disciplinary insights from NLP, cybersecurity, and AI governance. The resulting synthesis delivers both theoretical rigor and actionable guidance, offering industry practitioners a practical defense roadmap and advancing secure, trustworthy, and responsible LLM deployment paradigms.
0 citationsRead paper
Hua-Chen New Theory of Economic Optimization
This paper addresses fundamental challenges in economic optimization theory—including system stability assessment, uniqueness verification of equilibria, and structural dynamic optimization—by proposing a novel stochastic modeling paradigm grounded in Markov chains. Methodologically, it integrates stochastic process analysis with structural matrix theory to introduce the “economic structural matrix invariant” (Chen’s invariant), enabling a quantifiable, programmable, and AI-implementable economic optimization framework. Unlike conventional mathematical economics and mainstream equilibrium approaches, the framework abandons deterministic assumptions, supporting stability testing, corporate bankruptcy prediction, product-category ranking, macroeconomic trend forecasting and policy intervention, and structural optimization decisions. Empirical validation confirms both theoretical rigor and engineering feasibility, offering a new computational tool for intelligent economic governance.
0 citationsRead paper
Fuzzy Cluster-Aware Contrastive Clustering for Time Series
Clustering massive unlabeled time-series data in IoT remains challenging, as existing methods struggle to jointly model temporal structures and optimize representation learning with clustering. To address this, we propose the Fuzzy Cluster-aware Contrastive Clustering (FCC) framework. FCC introduces a novel three-view temporal augmentation strategy and a cluster-aware dynamic hard negative sampling mechanism; it is the first to embed the soft cluster structure of fuzzy C-means into the contrastive learning objective in real time, enabling clustering-guided adaptive representation learning. The method tightly integrates fuzzy clustering, contrastive learning, multi-view augmentation, and deep representation learning. Evaluated on 40 standard benchmark datasets, FCC consistently outperforms eight state-of-the-art baselines, achieving average improvements of 5.2% in clustering accuracy and 6.8% in normalized mutual information.
0 citationsRead paper
Recent publications
Latest Papers
Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement
为解决AI诗歌系统削弱用户创作主动性的缺点，通过用户驱动、古文引导和AI辅助的三元模型，提升古典诗词创作中的可控性、可解释性和用户参与度。
0 citationsRead paper
A fragile zero-watermarking method based on dual quaternion matrix decomposition
Medical images face two critical security risks during transmission and sharing: ambiguous copyright ownership and vulnerability to unauthorized content tampering. To address these challenges, this paper proposes a fragile zero-watermarking method based on dual quaternion matrix decomposition. The approach models structural image features by exploiting the intrinsic algebraic relationship between the standard and dual parts of dual quaternions, and employs low-rank matrix decomposition to extract stable features that are simultaneously robust against benign distortions and sensitive to malicious alterations. The resulting zero-watermarking scheme is embedding-free and lossless, requiring no modification to the original image. It enables fine-grained copyright authentication and pixel-level tamper localization. Experimental results demonstrate high sensitivity—accurately detecting minute tampering—strong robustness against common signal processing operations (e.g., JPEG compression, filtering), and computational efficiency. The method thus offers practical utility for securing medical imaging data.
0 citationsRead paper
Attack and defense techniques in large language models: A survey and new perspectives
This survey addresses critical security vulnerabilities in large language models (LLMs), including adversarial prompting, model extraction, and application-layer attacks—alongside their corresponding defenses. It identifies key limitations in existing defensive approaches: insufficient adaptability to evolving threats, suboptimal robustness–utility trade-offs, and poor resource efficiency. To address these gaps, the work proposes a novel, end-to-end LLM security taxonomy—the first of its kind—spanning the full attack-defense lifecycle. Three foundational research directions are introduced: (1) scalable adaptive defense mechanisms, (2) interpretable security frameworks, and (3) standardized, reproducible evaluation protocols. Methodologically, the study integrates systematic literature review, rigorous threat modeling, and cross-disciplinary insights from NLP, cybersecurity, and AI governance. The resulting synthesis delivers both theoretical rigor and actionable guidance, offering industry practitioners a practical defense roadmap and advancing secure, trustworthy, and responsible LLM deployment paradigms.
0 citationsRead paper
Hua-Chen New Theory of Economic Optimization
This paper addresses fundamental challenges in economic optimization theory—including system stability assessment, uniqueness verification of equilibria, and structural dynamic optimization—by proposing a novel stochastic modeling paradigm grounded in Markov chains. Methodologically, it integrates stochastic process analysis with structural matrix theory to introduce the “economic structural matrix invariant” (Chen’s invariant), enabling a quantifiable, programmable, and AI-implementable economic optimization framework. Unlike conventional mathematical economics and mainstream equilibrium approaches, the framework abandons deterministic assumptions, supporting stability testing, corporate bankruptcy prediction, product-category ranking, macroeconomic trend forecasting and policy intervention, and structural optimization decisions. Empirical validation confirms both theoretical rigor and engineering feasibility, offering a new computational tool for intelligent economic governance.
0 citationsRead paper
Fuzzy Cluster-Aware Contrastive Clustering for Time Series
Clustering massive unlabeled time-series data in IoT remains challenging, as existing methods struggle to jointly model temporal structures and optimize representation learning with clustering. To address this, we propose the Fuzzy Cluster-aware Contrastive Clustering (FCC) framework. FCC introduces a novel three-view temporal augmentation strategy and a cluster-aware dynamic hard negative sampling mechanism; it is the first to embed the soft cluster structure of fuzzy C-means into the contrastive learning objective in real time, enabling clustering-guided adaptive representation learning. The method tightly integrates fuzzy clustering, contrastive learning, multi-view augmentation, and deep representation learning. Evaluated on 40 standard benchmark datasets, FCC consistently outperforms eight state-of-the-art baselines, achieving average improvements of 5.2% in clustering accuracy and 6.8% in normalized mutual information.
0 citationsRead paper