A5039018909- Rough Sets and Fuzzy Logic
- Security in Wireless Sensor Networks
- Face and Expression Recognition
- Wireless Signal Modulation Classification
- Imbalanced Data Classification Techniques
- Chaos-based Image/Signal Encryption
- Cryptographic Implementations and Security
- Face recognition and analysis
- Adversarial Robustness in Machine Learning
- Anomaly Detection Techniques and Applications
- Integrated Circuits and Semiconductor Failure Analysis
- Data Mining Algorithms and Applications
- Energy Efficient Wireless Sensor Networks
- IoT and Edge/Fog Computing
Guilin University of Electronic Technology
2021-2023
Source location privacy, one of the core contents Wireless Sensor Network (WSN) security, has a significant impact on extensive application WSNs. In this paper, novel privacy protection routing scheme called Energy Balanced Branch Tree (EBBT) is proposed by using multibranch and fake sources. This three phases. first place, data source are randomly sent to certain intermediate node. Then, minimum hop (MHR) from node base station formed. branch paths with sources generated dynamically some...
Currently, deep learning has provided an important means to solve problems in various fields. Intelligent computing will bring a new solution the security analysis of lightweight block cipher as its becomes more and intelligent automatic. In this study, novel multiple differential distinguishers round-reduced SIMECK32/64 based on are proposed. Two kinds SIMECK32/64’s 6–11 rounds designed by using neural network simulate case input differences output cryptanalysis. The general models two...
The vulnerability of deep neural networks to adversarial perturbations has been demonstrated in a large body research. Compared image-dependent perturbations, universal perturbations(UAPs) is more challenging for indiscriminately attacking the model inputs. However, there are few studies on generating data-free targeted UAPs and attack success rate latest method remains unsatisfactory. Not only that, fewer have implemented their approach Transformers its efficacy uncertain. Therefore, novel...
High-utility itemset mining is to mine high profit itemsets from transaction databases. But if there are some with negative utility values in the database, high-utility may be pruned incorrectly and subset of low-utility itemsets. In this paper, an improved algorithm items (IHUMN) proposed. A novel utility-list buffer structure unit profits proposed efficiently store retrieve utility-list, reduce memory consumption during process. Moreover, Transitive Extension Negative formula constructed...