Privacy-preserving image multi-classification deep learning model in robot system of industrial IoT

Chen, Yange; Ping, Yuan; Wang, Baocang; He, Suyu

doi:10.1007/s00521-020-05426-0

Cited by 31 publications

(15 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen from Figure 10 that in the predicted two clustering categories, 300 detection data were predicted, respectively, and the detection error of category one was 9, and the accuracy rate reached 97%, and the detection error of category 2 is 8, and the accuracy rate reaches 97.33%. It can be seen from Figure 10 that the detection accuracy of the four clusters of the AKN algorithm is higher than that of the KN algorithm, which is about 6% higher than the traditional KN algorithm [30][31][32]. is shows that the detection accuracy of the AKN algorithm is higher, and it can more effectively defend against Dos attacks [33][34][35][36].…”

Section: Data Mining Model Based On Akn Algorithmmentioning

confidence: 99%

Application of Computer Data Mining Technology Based on AKN Algorithm in Denial of Service Attack Defense Detection

Huang¹

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Denial of service attacks have become one of the most difficult network security problems because they are easy to implement, difficult to prevent, and difficult to track, and they have brought great harm to the network society. Denial of service (Dos) is a phenomenon in which a large number of useless data packets or obstructive content are maliciously transmitted to the target server, which makes the target server unable to provide users with normal services. Denial of service attack (Dos attack) is a very typical network attack method, and the main harm of Dos attack is to exhaust service resources, making the computer or network unable to provide normal services. And AKN (adaptive Kohonen network) is an adaptive neural network proposed in recent years, and an algorithm summarized by using the characteristics of the neural network is called the AKN algorithm. This algorithm can realize fast, low-consumption, and high-precision denial of service detection in complex networks. In the era of big data, network security is becoming more and more important, and in order to maintain the security of network data, this article studies the common forms and principles of Dos attacks, as well as the current corresponding defense detection methods. It also investigates several commonly used algorithms of computer data mining technology, such as clustering algorithms, classification algorithms, neural network algorithms, regression algorithms, website data mining, and association algorithms, and proposes a computer data mining model based on the AKN algorithm. In addition, the computer data mining technology based on the AKN algorithm is used to conduct defensive detection experiments under Dos attacks and compares with classic algorithms. Experimental results show that experiments based on the AKN algorithm have better defensive detection effects than classic algorithms, with a detection accuracy rate of more than 97% and a detection efficiency improvement of more than 20%.

show abstract

Section: Data Mining Model Based On Akn Algorithmmentioning

confidence: 99%

Application of Computer Data Mining Technology Based on AKN Algorithm in Denial of Service Attack Defense Detection

Huang¹

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…This section briefly reviews the previous privacy-preserving recognition methods for image and video datasets [21][22][23][24][25].…”

Section: Introductionmentioning

confidence: 99%

“…They analyzed perturbation's effect satisfying -LDP on data utility regarding distance and count-based machine learning algorithms. Chen et al [25] presented a secure multi-classification scheme to address the privacy-leakage in robot system using DL. The authors adopted two pairs of activation and cost functions using HE, namely softmax plus log-likelihood function and sigmoid plus cross-entropy function, along with secure calculation protocols.…”

Section: Introductionmentioning

confidence: 99%

P2SLR: A Privacy-Preserving Sign Language Recognition as-a-Cloud Service Using Deep Learning For Encrypted Gestures

Tanwar¹,

Sharma²,

Raman³

et al. 2022

Preprint

View full text Add to dashboard Cite

<div>Cloud-based services have revolutionized data storage and processing tasks. However, these services raise security concerns as service providers may misuse the user’s stored data. Privacy loss is particularly problematic for hearing and speech impaired individuals that may need to use cloud infrastructure for sign language recognition (SLR). Addressing these challenges, this paper presents a privacy-preserving sign language recognition (P2SLR) as a cloud-service that operates over cloud infrastructure without revealing the individual’s visual information to the cloud service provider (CSP). The proposed P2SLR system is realized through two innovations: (a) block-based probabilistic image encryption scheme that combines fractional-order chaotic system (FOCS) and singular value decomposition (SVD) to obfuscate the visual information in video frames, and (b) a cloud-residing deep convolutional neural network (DCNN) based recognition architecture with a modified classifier to recognize gestures from encrypted video. The proposed scheme is validated for American, Argentinian, and German sign languages. The proposed scheme achieved recognition accuracy in the range 90:76 - 98:09%, comparable to existing state-of-the-art SLR techniques in the plain domain (PD). The proposed image encryption scheme is secure under standard cryptographic image attacks, protecting the individual’s identity. P2SLR is the first move towards developing a secure SLR system over the cloud.</div>

show abstract

“…However, the approximation process more or less makes the results loss in accuracy and requires complex computational cost. Other schemes start directly from the accuracy of the underlying network by designing a comparison protocol using the special structure of the Rectified Linear Units (Relu) function 22 . Combined with homomorphic encryption to achieve calculation, such an approach obviates the unnecessary accuracy loss, but the comparison protocols in most schemes are not efficient enough due to complex modulo‐exponential operations.…”

Section: Introductionmentioning

confidence: 99%

“…Bellafqira et al 8 constructed a privacy‐preserving multilayer perceptron model based on Paillier cryptosystem, although the activation function computing on the two‐server model is achieved by comparison protocol to ensure the underlying network accuracy, the fact that one of the servers in the model is allowed to know the user's private key will cause privacy threat to raw data. Chen et al 22 utilized the Paillier homomorphic cryptosystem to implement the activation function computing with a comparison protocol, which achieves underlying network accuracy without loss, but the complicated modulo exponential operations will cause high latency. Li et al 9 proposed an optimized outsourced privacy‐preserving convolutional neural network prediction scheme, which first applies asynchronous computation and single instruction multiple data (SIMD) techniques to generate offline triplets, then adopts garbled circuit for nonlinear Relu function to assure the underlying network structure accuracy, and finally it uses average pooling to achieve similar accuracy as maximum pooling.…”

Section: Introductionmentioning

confidence: 99%

Privacy‐preserving convolutional neural network prediction with low latency and lightweight users

Chen

Duan

et al. 2021

Int J Intell Syst

Self Cite

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have excellent and extensive applications in image recognition. With the continuous exploitation of data value and the proliferation of machine learning‐as‐a‐service, convolutional neural network prediction schemes on privacy preservation have been introduced one after another, which makes much more attention focused on the privacy leakage and services offered to be efficient and light. Therefore, how to improve the convolutional neural prediction scheme on the premise of privacy preservation turns out to be an imperative research issue. In this paper, we propose a privacy‐preserving convolutional neural network prediction scheme (PCP‐LL) that supports low latency and lightweight users. The scheme starts from the perspective of lossless accuracy from underlying networks. First, we construct a secure activation function computing protocol (SActF) utilizing a commodity‐based secure comparison protocol, which reduces the complexity and latency during the activation function computing under ciphertexts compared with common schemes. Second, to further support lightweight users, we introduce a secure output layer protocol (SOut) that enables users to obtain the prediction results without extra decryption after simple operations. Then, the scheme adopts the distributed two trapdoors public‐key cryptosystem (DT‐PKC) to achieve both data and model security, which well avoids security issues especially such as wiretapping by semi‐honest participants commonly in secret sharing schemes. Finally, through relevant evaluations, the scheme not only achieves privacy preservation and low latency, but also supports lightweight users.

show abstract

Privacy-preserving image multi-classification deep learning model in robot system of industrial IoT

Cited by 31 publications

References 37 publications

Application of Computer Data Mining Technology Based on AKN Algorithm in Denial of Service Attack Defense Detection

Application of Computer Data Mining Technology Based on AKN Algorithm in Denial of Service Attack Defense Detection

P2SLR: A Privacy-Preserving Sign Language Recognition as-a-Cloud Service Using Deep Learning For Encrypted Gestures

Privacy‐preserving convolutional neural network prediction with low latency and lightweight users

Contact Info

Product

Resources

About