Secure data aggregation methods and countermeasures against various attacks in wireless sensor networks: A comprehensive review

Deep neural networks are vulnerable to adversarial samples, posing potential threats to the applications deployed with deep learning models in practical conditions. A typical example is the fingerprint liveness detection module in fingerprint authentication systems. Inspired by great progress of deep learning, deep networks-based fingerprint liveness detection algorithms spring up and dominate the field. Thus, we investigate the feasibility of deceiving state-of-the-art deep networks-based fingerprint liveness detection schemes by leveraging this property in this paper. Extensive evaluations are made with three existing adversarial methods: FGSM, MI-FGSM, and Deepfool. We also proposed an adversarial attack method that enhances the robustness of adversarial fingerprint images to various transformations like rotations and flip. We demonstrate these outstanding schemes are likely to classify fake fingerprints as live fingerprints by adding tiny perturbations, even without internal details of their used model. The experimental results reveal a big loophole and threats for these schemes from a view of security, and enough attention is urgently needed to be paid on anti-adversarial not only in fingerprint liveness detection but also in all deep learning applications.

https://link.springer.com/content/pdf/10.1186/s13640-020-0490-z.pdf

Adversarial attacks on fingerprint liveness detection

With the wide deployment of cloud computing, many security challenges have arisen, such as data and storage integrity and virtualization security The crisis of trust caused by these security issues has become one of the important factors restricting the wide applications of cloud service Especially for security-sensitive users, it is challenging to quickly select a cloud service which has the high level of trust and can meet both the user preferences and specific functional demands This paper explores the multi-granularity selection standard of trust level, the users’ preference calculation model, and the cloud service selection algorithm First, the trust evaluation mechanisms among different entities in the human society are fitted, and the multi-granularity selection standard of trust levels based on Gaussian cloud transformation is constructed Then, the calculation model of user preferences based on the cloud analytic hierarchy process is developed Finally, the trusted cloud service selection algorithm based on two-step fuzzy comprehensive evaluation is proposed and experimentally validated

Normal Cloud Model-Based Algorithm for Multi-Attribute Trusted Cloud Service Selection

Privacy-preserving data aggregation is a kind of fundamental and essential algorithm for wireless sensor networks. However, the existing aggregation algorithms consume a large amount of energy to assure sensory data security. In this article, we propose an energy-efficient and privacy-preserving data aggregation algorithm (EPDA). We organize a sensor network into a tree and connect the leaf nodes of the tree to form many chains. EPDA requires only the data sensed by the tail nodes of the chains to be sliced to ensure privacy. Also, EPDA significantly decreases energy consumption and prolongs the lifetime of the network. We compare our scheme with the existing schemes through theoretical analysis and simulations. The analysis and simulation results show that EPDA outperforms the existing schemes.

Energy-Efficient and Privacy-Preserving Data Aggregation Algorithm for Wireless Sensor Networks

Confidentiality and data integrity are essential paradigms in data aggregation owing to the various cyberattacks in wireless sensor networks (WSNs). This study proposes a novel technique named Lamport certificateless signcryption-based shift-invariant connectionist artificial deep neural networks (LCS-SICADNN) by using artificial deep neural networks to develop the data aggregation security model. This model utilises the input layer with several sensor nodes, four hidden layers to overcome different attacks (data injection, compromised node, Sybil and black hole attacks) and the output layer to analyse the given input. The Lamport one-time certificateless signcryption technique involving three different processes (key generation, signcryption and unsigncryption) is adopted to achieve secure data transmission between the sender and receiver. Firstly, a one-way function is executed to generate the public and private keys for each sensor node in the WSN. Secondly, digital signature generation and encryption are both performed. The sender node, which handles the signature generation and data encryption, forwards the data to the aggregator node. Then, the receiver verifies the data by using the sender’s public key during data decryption. Thus, data aggregation security can be guaranteed. Finally, the authorised node aggregates the data with much higher data confidentiality and privacy. Performance analysis is conducted by simulating the proposed LCS-SICADNN and conventional models. Results of comparison indicate that the LCS-SICADNN can improve data aggregation security with higher throughput and lesser delay, packet drop and overhead compared with the conventional methods. 

/pdf/lamport-certificateless-signcryption-deep-neural-networks-2exlely5.pdf

Lamport Certificateless Signcryption Deep Neural Networks for Data Aggregation Security in WSN

With the development of wireless sensor networks, privacy-preserving has become a very important problem in numerous wireless sensor networks (WSN) applications. This paper presents a novel energy-efficient secure data aggregation scheme cluster-based private data aggregation (CSDA) based on cluster privacy-preserving. It has good flexibility and practical applicability using the slice-assemble technology. And, the number of fragments will dynamically change from the change of the network scale. Then, it can reduce communication overhead and energy consumption. Finally, the simulation results show that the proposed aggregation method demonstrates better performance in data aggregation precision, privacy-preserving and communication efficiency than other methods.

CSDA: a novel cluster-based secure data aggregation scheme for WSNs

With the explosive growth of the wireless multimedia data on the wireless Internet, a large number of illegal images have been widely disseminated in wireless networks, which seriously endangers the content security of wireless networks. However, how to identify and classify illegal images quickly, accurately, and in real time is a key challenge for wireless multimedia networks. To avoid illegal images circulating on the Internet, each image needs to be detected, extracted features, and compared with the image in the feature library to verify the legitimacy of the image. An improved image deep learning hash (IDLH) method to learn compact binary codes for image search is proposed in this paper. Specifically, there are three major processes of IDLH: the feature extraction, deep secondary search, and image classification. IDLH performs image retrieval by the deep neural networks (DNN) as well as image classification with the binary hash codes. Different from other deep learning-hash methods that often entail heavy computations by using a conventional classifier, exemplified by K nearest neighbor (K-NN) and support vector machines (SVM), our method learns classifiers using binary hash codes, which can be learned synchronously in training. Finally, comprehensive experiments are conducted to evaluate IDLH method by using CIFAR-10 and Caltech 256 image library datasets, and the results show that the retrieval performance of IDLH method can effectively identify illegal images.

/pdf/deep-learning-hash-for-wireless-multimedia-image-content-27rl1vvax6.pdf

Deep Learning Hash for Wireless Multimedia Image Content Security

The invention discloses a Jop-Shop scheduling method based on a QEA variable rotation angle distance. Quantum chromosome coding based on procedures is adopted for expressing a schedule, and by detecting the validity of the schedule, the searching efficiency of a solution space is increased; furthermore, a quantum evolution algorithm mode based on the QEA variable rotation angle is utilized for generating a filial generation, so that the diversity of solutions is effectively expanded, and the convergence to a local optimal solution is effectively prevented; in addition, the convergence speed is increased, and a global optimal solution is finally obtained with a minimal time cost (namely the optimal scheduling scheme is realized). According to the invention, the binary solution mode, the decimal solution mode, the procedure solution mode and the quantum evolution algorithm based on the quantum evolution algorithm are utilized, so that the efficiency of the method is better than the efficiency of other methods.

Jiezhong Zhu

Papers

CSDA: a novel cluster-based secure data aggregation scheme for WSNs

Deep Learning Hash for Wireless Multimedia Image Content Security

Jop-Shop scheduling method based on QEA variable rotation angle distance