-
Article
Multi-period early-warning precipitation identification method for the easily waterlogged districts in Jiangxi province, China
Urban easily waterlogged districts need more systematic monitoring as the key disaster-forming and managing spatial scale, hard to identify the early-warning precipitation (EP). We proposed new algorithms to extr...
-
Chapter and Conference Paper
A Three-Stage Framework for Event-Event Relation Extraction with Large Language Model
Expanding the parameter count of a large language model (LLM) alone is insufficient to achieve satisfactory outcomes in natural language processing tasks, specifically event extraction (EE), event temporal rel...
-
Chapter and Conference Paper
PNPT: Prototypical Network with Prompt Template for Few-Shot Relation Extraction
Few-shot relation extraction involves predicting the relations between entity pairs in a sentence with a limited number of labeled instances for each specific relation. Prototypical network, which is based on ...
-
Chapter and Conference Paper
Minimizing Distortion in Steganography via Adaptive Language Model Tuning
Linguistic steganography, a technique that hides secret information within normal text, possesses tremendous potential in various applications such as protecting user privacy. However, previous research in lin...
-
Chapter and Conference Paper
CATS: Connection-Aware and Interaction-Based Text Steganalysis in Social Networks
The generative linguistic steganography in social networks have potential huge abuse and regulatory risks, with serious implications for information security, especially in the era of large language models. Ma...
-
Chapter and Conference Paper
Hi-Stega: A Hierarchical Linguistic Steganography Framework Combining Retrieval and Generation
Due to the widespread use of social media, linguistic steganography which embeds secret message into normal text to protect the security and privacy of secret message, has been widely studied and applied. Howe...
-
Article
Frame-level steganalysis of QIM steganography in compressed speech based on multi-dimensional perspective of codeword correlations
In this paper, a frame-level steganalysis of Quantization Index Modulation (QIM) steganography in compressed speech streams is proposed for the first time. The proposed method builds a neural network classific...
-
Article
Open AccessDifferentially private knowledge transfer for federated learning
Extracting useful knowledge from big data is important for machine learning. When data is privacy-sensitive and cannot be directly collected, federated learning is a promising option that extracts knowledge fr...
-
Article
Open AccessRemoving AI’s sentiment manipulation of personalized news delivery
Artificial intelligence (AI) is empowering personalized online news delivery to accommodate people’s information needs and combat information overload. However, AI models learned from user data are inheriting ...
-
Article
Research on covert communication channel based on modulation of common compressed speech codec
As is well known, multimedia has been widely used in VoIP and mobile communications. Research on how to establish covert communication channel over the above popular public applications has been flourishing in...
-
Article
Open AccessA federated graph neural network framework for privacy-preserving personalization
Graph neural network (GNN) is effective in modeling high-order interactions and has been widely used in various personalized applications such as recommendation. However, mainstream personalization methods rel...
-
Article
Open AccessCommunication-efficient federated learning via knowledge distillation
Federated learning is a privacy-preserving machine learning technique to train intelligent models from decentralized data, which enables exploiting private data by communicating local model updates in each ite...
-
Chapter and Conference Paper
Association Extraction and Recognition of Multiple Emotion Expressed in Social Texts
Detecting the sentiment people present in social media such as tweets is important for politics, commerce, education and so on. The task of multiple emotion recognition in texts is to predict a set of emotion ...
-
Chapter and Conference Paper
Aspect-Level Sentiment Classification Based on Graph Attention Network with BERT
With accelerated evolution of the internet, people can express their sentiments towards organizations, politics, products, events, etc. Analyzing these sentiments becomes very beneficial for businesses, govern...
-
Article
Open AccessA Multi-grained Log Auditing Scheme for Cloud Data Confidentiality
With increasing number of cloud data leakage accidents exposed, outsourced data control becomes a more and more serious concern of their owner. To relieve the concern of these cloud users, reliable logging sch...
-
Chapter and Conference Paper
Improving Text-Image Matching with Adversarial Learning and Circle Loss for Multi-modal Steganography
This paper proposes a multi-modal steganography method based on an improved text-image matching algorithm. At present, most of the steganography methods are based on single modality of carriers and embed confi...
-
Chapter and Conference Paper
Research on Information Hiding Based on Intelligent Creation of Tang Poem
Text is the most important and frequent way for people to exchange information and daily communication in today’s society; thus, text information hiding has great research value and practical significance. Thi...
-
Chapter and Conference Paper
A Vehicle Intrusion Detection System Based on Time Interval and Data Fields
With the development of the Internet of Things and automobile technology, intelligent networked vehicles are becoming more and more mature. Automobile manufacturers have installed various entertainment and saf...
-
Chapter and Conference Paper
TStego-THU: Large-Scale Text Steganalysis Dataset
In recent years, with the development of natural language processing (NLP) technology, linguistic steganography has developed rapidly. However, to the best of our knowledge, currently there is no public datase...
-
Chapter and Conference Paper
Multi-modal Steganography Based on Semantic Relevancy
Traditional steganography embeds confidential information by modifying the carrier at the symbol level, e.g., the pixels of an image or the words of a text. Since modification traces will inevitably be left on th...
