Dynamic Economic-Denial-of-Sustainability (EDoS) Detection in SDN-based Cloud

Dinh, Phuc Trinh; Park, Min‐Ho

doi:10.1109/fmec49853.2020.9144972

Cited by 14 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers in [5] proposed an approach to mitigate EDoS attacks in the SDN-based cloud computing environment. An unsupervised deep learning technique called long short-term memory (LSTM) was used as a multivariate time series anomaly detection model.…”

Section: Solutions At Application Levelmentioning

confidence: 99%

“…In the post-COVID-19 world, it is clear that more people and businesses are adopting cloud services, software, and infrastructure, as they can be accessed anytime, and from anywhere. To handle security risks, several research works and developments, such as in [5][6][7][8], have been proposed. Nonetheless, there are still more opportunities for new techniques to make the cloud more secure.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Secure Cloud Infrastructure: A Survey on Issues, Current Solutions, and Open Challenges

et al. 2021

View full text Add to dashboard Cite

Cloud computing is currently becoming a well-known buzzword in which business titans, such as Microsoft, Amazon, and Google, among others, are at the forefront in developing and providing sophisticated cloud computing systems to their users in a cost-effective manner. Security is the biggest concern for cloud computing and is a major obstacle to users adopting cloud computing systems. Maintaining the security of cloud computing is important, especially for the infrastructure. Several research works have been conducted in the cloud infrastructure security area; however, some gaps have not been completely addressed, while new challenges continue to arise. This paper presents a comprehensive survey of the security issues at different cloud infrastructure levels (e.g., application, network, host, and data). It investigates the most prominent issues that may affect the cloud computing business model with regard to infrastructure. It further discusses the current solutions proposed in the literature to mitigate the different security issues at each level. To assist in solving the issues, the challenges that are still unsolved are summarized. Based on the exploration of the current challenges, some cloud features such as flexibility, elasticity and the multi-tenancy are found to pose new challenges at each infrastructure level. More specifically, the multi-tenancy is found to have the most impact at all infrastructure levels, as it can lead to several security problems such as unavailability, abuse, data loss and privacy breach. This survey concludes by giving some recommendations for future research.

show abstract

Section: Solutions At Application Levelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Secure Cloud Infrastructure: A Survey on Issues, Current Solutions, and Open Challenges

et al. 2021

View full text Add to dashboard Cite

show abstract

“…LSTM is another recurrent model that can address the RNN memory problem. In previous studies [12,20,21], LSTM showed major improvements over what RNNs could accomplish. LSTM is designed to avoid long dependency problems and can remember long historical information and gain high accuracy in EDoS detection with a sequence flow-based method.…”

Section: Related Workmentioning

confidence: 99%

“…In this section, the workflow of the scheme is discussed, including: data capture, data preprocessing and model architecture as shown in Figure 6. Referring to a previous study [21], the sequence length is 250 packets per flow. To overcome the loss of information and memory vanishing of LSTM, a longer sequence length of the window slot, that is 500 packets per flow sequence, is proposed.…”

Section: Preprocessing and Model Work Flowmentioning

confidence: 99%

“…The attention model not only feeds the inputs and computes in parallel, just as a neural network, but can also retain the information in the sequence by the attention techniques to predict the output. The results in the table show that the proposed attention model was much faster in training and testing times than the bidirectional LSTM, LSTM [21] and RNN [37] models. For each iteration epoch in the training time, the attention model was twice as fast as the RNN model and three times faster than the LSTM model, and its accuracy was as high as that of these other models.…”

Section: Evaluation With Recurrent Modelsmentioning

confidence: 99%

See 1 more Smart Citation

MAN-EDoS: A Multihead Attention Network for the Detection of Economic Denial of Sustainability Attacks

Park

2021

Electronics

Self Cite

View full text Add to dashboard Cite

Cloud computing is one of the most modernized technology for the modern world. Along with the developments in the cloud infrastructure comes the risk of attacks that exploit the cloud services to exhaust the usage-based resources. A new type of general denial attack, called “economic denial of sustainability” (EDoS), exploits the pay-per-use service to scale-up resource usage normally and gradually over time, finally bankrupting a service provider. The stealthiness of EDoS has made it challenging to detect by most traditional mechanisms for the detection of denial-of-service attacks. Although some recent research has shown that multivariate time recurrent models, such as recurrent neural networks (RNN) and long short-term memory (LSTM), are effective for EDoS detection, they have some limitations, such as a long processing time and information loss. Therefore, an efficient EDoS detection scheme is proposed, which utilizes an attention technique. The proposed attention technique mimics cognitive attention, which enhances the critical features of the input data and fades out the rest. This reduces the feature selection processing time by calculating the query, key and value scores for the network packets. During the EDoS attack, the values of network features change over time. The proposed scheme inspects the changes of the attention scores between packets and between features, which can help the classification modules distinguish the attack flows from network flows. On another hand, our proposal scheme speeds up the processing time for the detection system in the cloud. This advantage benefits the detection process, but the risk of the EDoS is serious as long as the detection time is delayed. Comprehensive experiments showed that the proposed scheme can enhance the detection accuracy by 98%, and the computational speed is 60% faster compared to previous techniques on the available datasets, such as KDD, CICIDS, and a dataset that emerged from the testbed. Our proposed work is not only beneficial to the detection system in cloud computing, but can also be enlarged to be better with higher quality of training and technologies.

show abstract