A5007408376- Advanced Malware Detection Techniques
- Security and Verification in Computing
- Network Security and Intrusion Detection
- Generative Adversarial Networks and Image Synthesis
- Music and Audio Processing
- Speech and Audio Processing
- Software System Performance and Reliability
- Distributed and Parallel Computing Systems
- Speech Recognition and Synthesis
- Emotion and Mood Recognition
- Scientific Computing and Data Management
- Advanced Database Systems and Queries
- Internet Traffic Analysis and Secure E-voting
- User Authentication and Security Systems
- Vehicle License Plate Recognition
- Advanced Neural Network Applications
- Chemical Reactions and Isotopes
- Distributed systems and fault tolerance
- Cloud Data Security Solutions
- Imbalanced Data Classification Techniques
- Physical Unclonable Functions (PUFs) and Hardware Security
- Image Processing and 3D Reconstruction
- Fault Detection and Control Systems
- Human Pose and Action Recognition
- ATP Synthase and ATPases Research
Institute of Information Engineering
2020-2024
University of Chinese Academy of Sciences
2016-2024
Chinese Academy of Sciences
2016-2024
Shenyang Institute of Computing Technology (China)
2016-2023
This paper proposes a method called autoencoder with probabilistic LightGBM (AED-LGB) for detecting credit card frauds. deep learning-based AED-LGB algorithm first extracts low-dimensional feature data from high-dimensional bank using the characteristics of an which has symmetrical network structure, enhancing ability representation learning. The fraud dataset comes real anonymized by and is highly imbalanced, normal far greater than data. For this situation, smote used to resample before...
Being as one of important means enhancing production efficiency and reducing cost, intelligent failure detection system is great significance. However, there are shortcomings in the existing expert such single information flow (lack interaction) between components, denial dynamic allocation workloads which defy guarantee real-time quality reliability. Based on survey CPS related research focus, proposes a framework machine system. This centers systematic issues heterogeneity, autonomy,...
AMD Secure Encrypted Virtualization (SEV) assumes the hypervisor (HV) is untrusted and introduces hardware memory encryption support for virtual machines (VMs). Previous studies have proposed various attacks against encrypted VMs by exploiting SEV security flaws such as unencrypted VMCB lack of integrity. Most these been solved subsequent releases with State (SEV-ES) Nested Paging (SEV-SNP). However, latest SEV-SNP cannot stop malicious HV tampering critical flags in nested page table (NPT)....
Microservice application architecture is one of the most widely used service architectures in industry. To prevent a compromised microservice from abusing other microservices, authorization policy applied to regulate access among them. However, configuring control manually challenging due complexity and dynamic nature applications. In this paper, we present Log2Policy, novel approach generate based on logs. Our consists three fundamental techniques: (1) log-based topological graph generation...
Analyzing programs with loops is a challenging task, suffering from potential issues such as indeterminate number of iterations and exponential growth control flow complexity. Loop summarization, static analysis method for concrete semantic interpretation, receives increasing focuses. It produces symbolic expressions semantically equivalent to the loop program. However, current summarization methods are only suitable single-branch or multi-branch simple cycles, without supporting complex...
Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, task "in-the-wild" speaker verification is still challenging, considering speech samples may contain lots identity-unrelated information, e.g., background noise, reverberation, emotion, etc. Previous works focus optimizing model improve accuracy, without taking into account elimination impact from information. To solve above problem, we...
Despite the remarkable progress made in synthesizing emotional speech from text, it is still challenging to provide emotion information existing segments. Previous methods mainly rely on parallel data, and few works have studied generalization ability for one model transfer across different languages. To cope with such problems, we propose an system named ET-GAN, learning language-independent another without training samples. Based cycle-consistent generative adversarial network, our method...
Objective To investigate the effects of aquaporin-8 (AQP-8) on expression multidrug resistance factors by overexpression AQP-8 in human colon cancer HT-29 cells vitro.Methods Human logarithm growth period were used.AQP-8 eukaryotic vector was constructed and transfected into cells.Western blotting used to detect transfection efficiency.Methyl thiazol tetrazolium (MTT) assay measure cell inhibition rate.Fluorescence real-time quantitative polymerase chain reaction (FQ-PCR) Western determine...
In recent years, high-fidelity three-dimensional (3D) oracle bone models (3D-OBMs) have received extensive attention from experts due to their unparalleled reducibility real bone. the research process of 3D-OBMs, first procedure is extract inscriptions (OBIs) model form individual characters (OBCs). However, manual extraction OBIs a time-consuming and labor-intensive task that relies heavily on knowledge. To address these problems, we propose texture-mapping-based OBI extractor (tm-OBIE),...
With the rapid development of Internet technology, caching technology has become a key various large and medium-sized websites. The quality cache design is directly related to speed website access number servers purchased., even affects user experience. increase concurrency, traditional small architecture can not meet needs business., particularly important. How that resist high concurrency amount data problem worthy in-depth research. This paper first introduces commonly used then puts...