Collusion Attack Detection in Networked Systems

Bhuiyan, Zakirul Alam; Wu, Jie

doi:10.1109/dasc-picom-datacom-cyberscitec.2016.67

Cited by 23 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adversary can use the compromised node to carry out malicious activities to exploit the system, such as collecting confidential information, executing sophisticated attacks, injecting false data, etc. [121]. It can also lead to various kinds of network security attacks and hence can pose a serious threat to the vehicular networks.…”

Section: Denial Of Servicementioning

confidence: 99%

A Comprehensive Survey on the Applications of Blockchain for Securing Vehicular Networks

Alladi¹,

Chamola²,

Sahu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Vehicular networks promise features such as traffic management, route scheduling, data exchange, entertainment, and much more. With any large-scale technological integration comes the challenge of providing security. Blockchain technology has been a popular choice of many studies for making the vehicular network more secure. Its characteristics meet some of the essential security requirements such as decentralization, transparency, tamper-proof nature, and public audit. This study catalogues some of the notable efforts in this direction over the last few years. We analyze around 75 blockchain-based security schemes for vehicular networks from an application, security, and blockchain perspective. The application perspective focuses on various applications which use secure blockchainbased vehicular networks such as transportation, parking, data sharing/ trading, and resource sharing. The security perspective focuses on security requirements and attacks. The blockchain perspective focuses on blockchain platforms, blockchain types, and consensus mechanisms used in blockchain implementation. We also compile the popular simulation tools used for simulating blockchain and for simulating vehicular networks. Additionally, to give the readers a broader perspective of the research area, we discuss the role of various state-of-the-art emerging technologies in blockchain-based vehicular networks. Lastly, we summarize the survey by listing out some common challenges and the future research directions in this field.

show abstract

Section: Denial Of Servicementioning

confidence: 99%

A Comprehensive Survey on the Applications of Blockchain for Securing Vehicular Networks

Alladi¹,

Chamola²,

Sahu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The traditional control system to be openly accessed through IIoT network, which poses severe threats to its security [3], [4]. In 2014, more than 30% intelligent electric meters of the top-three power supply providers in Spain exhibited serious security holes [5].…”

Section: Introductionmentioning

confidence: 99%

A Regularized Cross-Layer Ladder Network for Intrusion Detection in Industrial Internet of Things

Long

Liang

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

As part of BigData trends, the ubiquitous use of the Internet-of-Things (IoT) in the industrial environment has generated a significant amount of network traffic. In this type of IoT industrial network where there is a large equipment heterogeneity, security is a fundamental issue, thus it is very important to detect likely intrusion behaviors. Furthermore, since the proportion of labeled data records is small in IoT environment, it is challenging to detect various attacks and intrusions accurately. This investigation builds a semi-supervised ladder network model for intrusion detection in IIoT. This model considers the manifold distribution of high-dimensional data and incorporated a manifold regularization constraint in the decoder of the ladder network. Meanwhile, the feature propagation between layers is strengthened by adding more cross-layer connections in this model. On this basis, a random attention-based data fusion approach to generate global features for intrusion detection. The experiments on CIC-IDS2018 show that the proposed approach can recognize the intrusion with less false alarm rate, whilst model training is time-efficient.

show abstract

“…The adversary can attempt to compromise the transfer learning with negative transfer [12], [13], for example by executing a malicious computation, and changing the computation results for transfer learning. Thus, a covert adversary can launch a malicious learning with dishonest majority [14] by maliciously tuning transfer learning, resulting in transfer learning behaving badly on specific attacker-chosen inputs. Existing secure machine learning schemes are not generally designed to the setting of dishonest majority.…”

Section: Introductionmentioning

confidence: 99%

VerifyTL: Secure and Verifiable Collaborative Transfer Learning

Ma¹,

Ma²,

Miao³

et al. 2020

Preprint

View full text Add to dashboard Cite

Getting access to labelled datasets in certain sensitive application domains can be challenging. Hence, one often resorts to transfer learning to transfer knowledge learned from a source domain with sufficient labelled data to a target domain with limited labelled data. However, most existing transfer learning techniques only focus on one-way transfer which brings no benefit to the source domain. In addition, there is the risk of a covert adversary corrupting a number of domains, which can consequently result in inaccurate prediction or privacy leakage. In this paper we construct a secure and Verifiable collaborative Transfer Learning scheme, VerifyTL, to support two-way transfer learning over potentially untrusted datasets by improving knowledge transfer from a target domain to a source domain. Further, we equip VerifyTL with a cross transfer unit and a weave transfer unit employing SPDZ computation to provide privacy guarantee and verification in the two-domain setting and the multi-domain setting, respectively. Thus, VerifyTL is secure against covert adversary that can compromise up to n − 1 out of n data domains. We analyze the security of VerifyTL and evaluate its performance over two real-world datasets. Experimental results show that VerifyTL achieves significant performance gains over existing secure learning schemes.

show abstract

Collusion Attack Detection in Networked Systems

Cited by 23 publications

References 17 publications

A Comprehensive Survey on the Applications of Blockchain for Securing Vehicular Networks

A Comprehensive Survey on the Applications of Blockchain for Securing Vehicular Networks

A Regularized Cross-Layer Ladder Network for Intrusion Detection in Industrial Internet of Things

VerifyTL: Secure and Verifiable Collaborative Transfer Learning

Contact Info

Product

Resources

About