Visible to the public Biblio

Filters: Author is Guan, Shaopeng  [Clear All Filters]
Conference Paper
Zhang, Conghui, Li, Yi, Sun, Wenwen, Guan, Shaopeng.  2020.  Blockchain Based Big Data Security Protection Scheme. 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC). :574–578.
As the key platform to deal with big data, Hadoop cannot fully protect data security of users by relying on a single Kerberos authentication mechanism. In addition, the single Namenode has disadvantages such as single point failure, performance bottleneck and poor scalability. To solve these problems, a big data security protection scheme is proposed. In this scheme, blockchain technology is adopted to deploy distributed Namenode server cluster to take joint efforts to safeguard the metadata and to allocate access tasks of users. We also improved the heartbeat model to collect user behavior so as to make a faster response to Datanode failure. The smart contract conducts reasonable allocation of user role through the judgment of user tag and risk value. It also establishes a tracking chain of risk value to monitor user behavior in real time. Experiments show that this scheme can better protect data security in Hadoop. It has the advantage of metadata decentralization and the data is hard to be tampered.
Sun, Wenwen, Li, Yi, Guan, Shaopeng.  2019.  An Improved Method of DDoS Attack Detection for Controller of SDN. 2019 IEEE 2nd International Conference on Computer and Communication Engineering Technology (CCET). :249–253.
For controllers of Software Defined Network (SDN), Distributed Denial of Service (DDoS) attacks are still the simplest and most effective way to attack. Aiming at this problem, a real-time DDoS detection attack method for SDN controller is proposed. The method first uses the entropy to detect whether the flow is abnormal. After the abnormal warning is issued, the flow entry of the OpenFlow switch is obtained, and the DDoS attack feature in the SDN environment is analyzed to extract important features related to the attack. The BiLSTM-RNN neural network algorithm is used to train the data set, and the BiLSTM model is generated to classify the real-time traffic to realize the DDoS attack detection. Experiments show that, compared with other methods, this method can efficiently implement DDoS attack traffic detection and reduce controller overhead in SDN environment.