Prediction of Network Attacks Using Connection Behavior

Author(s):  
N. Aakaash ◽  
K. Akshaya Bala ◽  
Veerabrahmam Pranathi ◽  
Meenakshi S. Arya
Keyword(s):  
Author(s):  
Pradip M. Jawandhiya ◽  
Mangesh Ghonge ◽  
M. S. Ali ◽  
J. S. Deshpande

Electronics ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 844
Author(s):  
Tsung-Yi Tang ◽  
Li-Yuan Hou ◽  
Tyng-Yeu Liang

With the rise in fog computing, users are no longer restricted to only accessing resources located in central and distant clouds and can request services from neighboring fog nodes distributed over networks. This can effectively reduce the network latency of service responses and the load of data centers. Furthermore, it can prevent the Internet’s bandwidth from being used up due to massive data flows from end users to clouds. However, fog-computing resources are distributed over multiple levels of networks and are managed by different owners. Consequently, the problem of service discovery becomes quite complicated. For resolving this problem, a decentralized service discovery method is required. Accordingly, this research proposes a service discovery framework based on the distributed ledger technology of IOTA. The proposed framework enables clients to directly search for service nodes through any node in the IOTA Mainnet to achieve the goals of public access and high availability and avoid network attacks to distributed hash tables that are popularly used for service discovery. Moreover, clients can obtain more comprehensive information by visiting known nodes and select a fog node able to provide services with the shortest latency. Our experimental results have shown that the proposed framework is cost-effective for distributed service discovery due to the advantages of IOTA. On the other hand, it can indeed enable clients to obtain higher service quality by automatic node selection.


2006 ◽  
Vol 39 (21) ◽  
pp. 310-315
Author(s):  
Maciej Wołowiec ◽  
Jakub Botwicz ◽  
Piotr Sapiecha

2021 ◽  
Author(s):  
Sun Wenbo ◽  
Xing Shuangyun ◽  
Yue Xishun ◽  
Chang Chunling

2021 ◽  
pp. 1-30
Author(s):  
Qingtian Zou ◽  
Anoop Singhal ◽  
Xiaoyan Sun ◽  
Peng Liu

Network attacks have become a major security concern for organizations worldwide. A category of network attacks that exploit the logic (security) flaws of a few widely-deployed authentication protocols has been commonly observed in recent years. Such logic-flaw-exploiting network attacks often do not have distinguishing signatures, and can thus easily evade the typical signature-based network intrusion detection systems. Recently, researchers have applied neural networks to detect network attacks with network logs. However, public network data sets have major drawbacks such as limited data sample variations and unbalanced data with respect to malicious and benign samples. In this paper, we present a new end-to-end approach based on protocol fuzzing to automatically generate high-quality network data, on which deep learning models can be trained for network attack detection. Our findings show that protocol fuzzing can generate data samples that cover real-world data, and deep learning models trained with fuzzed data can successfully detect the logic-flaw-exploiting network attacks.


Sign in / Sign up

Export Citation Format

Share Document