Fang Fang

Method of secure, scalable, and fine-grained data access control with efficient revocation in untrusted cloud

2015 · 中国邮电高校学报：英文版

云计算是计算基础结构的资源在网络上作为服务在被提供的一个发展中的计算范例。有希望当日期主人存储敏感数据为与 untrusted 云服务器一起分享时，实际上，这个范例也为数据安全和加密存储带新挑战。当它来到有细密纹理的数据和可伸缩的存取控制时，为关键分发和数据管理的巨大的计算被要求。在这篇文章，我们由利用并且特别地联合密文政策的技术达到了这个目标基于属性的加密(CP-ABE ) ，线性秘密分享计划(LSSS ) ，和柜台(CTR ) 模式加密。建议计划由在属性水平上而非在用户水平上进行撤回是高度有效的。数据机密和没有串通的目标攻击(甚至云服务器(CS ) 与用户一起共谋勾结) ，以及有细密纹理和可伸缩性之一，也在我们的存取结构被完成。

Which Invariance Should We Transfer? A Causal Minimax Learning Approach

2021 · arXiv (Cornell University)

A major barrier to deploying current machine learning models lies in their non-reliability to dataset shifts. To resolve this problem, most existing studies attempted to transfer stable information to unseen environments. Particularly, independent causal mechanisms-based …

Neural Prediction Errors as a Unified Cue for Abstract Visual Reasoning

2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Humans exhibit remarkable abilities in recognizing relationships and performing complex reasoning. In contrast, deep neural networks have long been critiqued for their limitations in abstract visual reasoning (AVR), a key challenge in achieving artificial general …

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization

2025 · arXiv (Cornell University)

Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple instructions to extract data, both of which well-alignment …

Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network

2020

Sentence-level extractive text summarization is substantially a node classification task of network mining, adhering to the informative components and concise representations. There are lots of redundant phrases between extracted sentences, but it is difficult to …