湾区联校科研 · 学术发表
大湾区AI安全与发展常设委员会 联同高校科研伙伴的预印本与学术成果,聚焦 AI 安全、数据治理与可信智能。
预印本(Preprints)
1
Building the "International TCM Data Port": A Cross-Border Citizen Science Paradigm for the "Data Element ×" Strategy
Liu Kaijie · Alex Li · Hu Hao · Ho Kin Chung
2026 · SSRN
2
Scaling Laws Hit a Wall: Mitigating Semantic Sorting Collapse in Medical LLMs via the HoloAuditor Topological Guardrail
Liu Kaijie · Alex Li · Hu Hao · Ho Kin Chung
2026 · SSRN
3
When Embodied AI Meets Topology: A Topological Circuit Breaker for OpenClaw and Industrial Agents
Liu Kaijie · Alex Li · Hu Hao · Ho Kin Chung · Michael K. Ng
2026 · SSRN
4
HoloTSH: A Neuro-Symbolic Tensor Logic for TCM Modernization via Mathematical Isomorphism and Theoretical Guarantees
Liu Kaijie · Alex Li (Tak Ho) · Hu Hao · Ho Kin Chung
2026-02 · TechRxiv (IEEE)
5
具身智能「生存动机」的内在风险与拓扑物理断路器(HoloBlocker)治理架构前瞻
—
2026-04 · ChinaXiv
6
Opening Pandora's Box: The Existential Threat of Survival-Driven AI and the Urgent Need for Topological Circuit Breakers
—
Preprint · SSRN
7
「神农 AI」生态体系:构建青少年体质数据的「数字长城」 — The "ShenNong AI" Ecosystem
—
ResearchGate
8
K12 AI 驱动科研网络:耦合数据生产与人才创新的新范式
—
2026-06-11 · 中国科学院科技论文预发布平台 (ChinaXiv)
9
HoloAegis: Frozen Representation, Topological Inference — Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails
—
arXiv
10
Split-Learning and Split-Inference Privacy Defenses Fail Under Strong Attackers: A Metric-Agnostic Dual-Track Empirical Audit of Representation Leakage
—
2026-09 · ResearchGate
期刊论文(在审 · Under Review)
以下 8 篇论文已投递至国际期刊,正处独立同行评审中。获接收前不以期刊论文自称,结果以期刊公布为准。
J1
Neural Networks(Elsevier)
2026 · 期刊评审中(under review)
J2
IEEE Transactions on Information Forensics and Security(TIFS)
2026 · 期刊评审中(under review)
J3
Computer Methods and Programs in Biomedicine(CMPB)
2026 · 期刊评审中(under review)
J4
Journal of Systems Architecture(JSA)
2026 · 期刊评审中(under review)
J5
Safety Science(Elsevier)
2026 · 期刊评审中(under review)
J6
IEEE Journal of Biomedical and Health Informatics(JBHI)
2026 · 期刊评审中(under review)
J7
Expert Systems with Applications(ESWA)
2026 · 期刊评审中(under review)
J8
Transactions of the Association for Computational Linguistics(TACL)
2026 · 期刊评审中(under review)
资料集(Dataset)
D1
HoloAuditor: Topological Guardrail for Clinical LLMs — Audit Ledger, Evaluation Scripts, and Corpus Matching Pairs
2026-10-20 · IEEE DataPort(CC BY 4.0)
文章转载(GDIRI 微信公众号)
以下文章转载自广东省数字产业研究院(GDIRI)微信公众号,经作者同意转载,文末附委员会编者按。点击标题阅读全文。
© 2026 大湾区AI安全与发展常设委员会 · 学术成果版权归原作者所有 · 返回首页