scholarly journals Mutual learning-based efficient synchronization of neural networks to exchange the neural key

2021 ◽  
Author(s):  
Arindam Sarkar
Keyword(s):  
Neural Networks ◽  
Weight Vector ◽  
Key Exchange ◽  
Security And Privacy ◽  
Complete Synchronization ◽  
Neural Synchronization ◽  
Mutual Learning ◽  
Public Channel ◽  
Improved Technique

AbstractSynchronization of two neural networks through mutual learning is used to exchange the key over a public channel. In the absence of a weight vector from another party, the key challenge with neural synchronization is how to assess the coordination of two communication parties. There is an issue of delay in the current techniques in the synchronization assessment that has an impact on the security and privacy of the neural synchronization. In this paper, to assess the complete coordination of a cluster of neural networks more efficiently and timely, an important strategy for assessing coordination is presented. To approximately determine the degree of synchronization, the frequency of the two networks having the same output in prior iterations is used. The hash is used to determine if both the networks are completely synchronized exactly when a certain threshold is crossed. The improved technique makes absolute coordination between two communication parties using the weight vectors’ has value. In contrast, with existing approaches, two communicating parties who follow the proposed approach will detect complete synchronization sooner. This reduces the effective geometric likelihood. The proposed method, therefore, increases the safety of the protocol for neural key exchange. This proposed technique has been passed through different parametric tests. Simulations of the process show effectiveness in terms of cited results in the paper.

scholarly journals An Improved Method to Evaluate the Synchronization in Neural Key Exchange Protocol

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Yi Liang Han ◽  
Yu Li ◽  
Zhe Li ◽  
Shuai Shuai Zhu
Keyword(s):  
Neural Networks ◽  
Hash Function ◽  
Weight Vector ◽  
Critical Issue ◽  
Key Exchange ◽  
Improved Method ◽  
Key Exchange Protocol ◽  
Mutual Learning ◽  
Successful Probability ◽  
Full Synchronization

The synchronization between two neural networks by mutual learning can be used to design the neural key exchange protocol. The critical issue is how to evaluate the synchronization without a weight vector. All existing methods have a delay in evaluating the synchronization, which affects the security of the neural key exchange. To evaluate the full synchronization of neural networks more timely and accurately, an improved method for evaluating the synchronization is proposed. First, the frequency that the two networks have the same output in previous steps is used for assessing the degree of them roughly. Second, the hash function is utilized to judge whether the two networks have achieved full synchronization precisely when the degree exceeds a given threshold. The improved method can find the full synchronization between two networks with no information other than the hash value of the weight vector. Compared with other methods, the full synchronization can be detected earlier by two communication partners which adopt the method proposed in this paper. As a result, the successful probability of geometric is reduced. Therefore, the proposed method can enhance the security of the neural exchange protocol.

scholarly journals Generative adversarial network guided mutual learning based synchronization of cluster of neural networks

2021 ◽  
Author(s):  
Arindam Sarkar
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Binary Tree ◽  
Key Exchange ◽  
Key Exchange Protocol ◽  
Session Key ◽  
Generative Adversarial Network ◽  
Neural Synchronization ◽  
Adversarial Network ◽  
Internal Architecture

AbstractNeural synchronization is a technique for establishing the cryptographic key exchange protocol over a public channel. Two neural networks receive common inputs and exchange their outputs. In some steps, it leads to full synchronization by setting the discrete weights according to the specific rule of learning. This synchronized weight is used as a common secret session key. But there are seldom research is done to investigate the synchronization of a cluster of neural networks. In this paper, a Generative Adversarial Network (GAN)-based synchronization of a cluster of neural networks with three hidden layers is proposed for the development of the public-key exchange protocol. This paper highlights a variety of interesting improvements to traditional GAN architecture. Here GAN is used for Pseudo-Random Number Generators (PRNG) for neural synchronization. Each neural network is considered as a node of a binary tree framework. When both i-th and j-th nodes of the binary tree are synchronized then one of these two nodes is elected as a leader. Now, this leader node will synchronize with the leader of the other branch. After completion of this process synchronized weight becomes the session key for the whole cluster. This proposed technique has several advantages like (1) There is no need to synchronize one neural network to every other in the cluster instead of that entire cluster can be able to share the same secret key by synchronizing between the elected leader nodes with only logarithmic synchronization steps. (2) This proposed technology provides GAN-based PRNG which is very sensitive to the initial seed value. (3) Three hidden layers leads to the complex internal architecture of the Tree Parity Machine (TPM). So, it will be difficult for the attacker to guess the internal architecture. (4) An increase in the weight range of the neural network increases the complexity of a successful attack exponentially but the effort to build the neural key decreases over the polynomial time. (5) The proposed technique also offers synchronization and authentication steps in parallel. It is difficult for the attacker to distinguish between synchronization and authentication steps. This proposed technique has been passed through different parametric tests. Simulations of the process show effectiveness in terms of cited results in the paper.

scholarly journals Natural Images Allow Universal Adversarial Attacks on Medical Image Classification Using Deep Neural Networks with Transfer Learning

2021 ◽  
Author(s):  
Akinori Minagi ◽  
Hokuto Hirano ◽  
Kazuhiro Takemoto
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Transfer Learning ◽  
Medical Image ◽  
Deep Neural Networks ◽  
Disease Diagnosis ◽  
Natural Images ◽  
Fine Tuning ◽  
Security And Privacy ◽  
Medical Image Classification

Abstract Transfer learning from natural images is well used in deep neural networks (DNNs) for medical image classification to achieve computer-aided clinical diagnosis. Although the adversarial vulnerability of DNNs hinders practical applications owing to the high stakes of diagnosis, adversarial attacks are expected to be limited because training data — which are often required for adversarial attacks — are generally unavailable in terms of security and privacy preservation. Nevertheless, we hypothesized that adversarial attacks are also possible using natural images because pre-trained models do not change significantly after fine-tuning. We focused on three representative DNN-based medical image classification tasks (i.e., skin cancer, referable diabetic retinopathy, and pneumonia classifications) and investigated whether medical DNN models with transfer learning are vulnerable to universal adversarial perturbations (UAPs), generated using natural images. UAPs from natural images are useful for both non-targeted and targeted attacks. The performance of UAPs from natural images was significantly higher than that of random controls, although slightly lower than that of UAPs from training images. Vulnerability to UAPs from natural images was observed between different natural image datasets and between different model architectures. The use of transfer learning causes a security hole, which decreases the reliability and safety of computer-based disease diagnosis. Model training from random initialization (without transfer learning) reduced the performance of UAPs from natural images; however, it did not completely avoid vulnerability to UAPs. The vulnerability of UAPs from natural images will become a remarkable security threat.

Quasi-projective and complete synchronization of fractional-order complex-valued neural networks with time delays

2019 ◽  
Vol 118 ◽  
pp. 102-109 ◽  
Author(s):  
Hong-Li Li ◽  
Cheng Hu ◽  
Jinde Cao ◽  
Haijun Jiang ◽  
Ahmed Alsaedi
Keyword(s):  
Neural Networks ◽  
Fractional Order ◽  
Time Delays ◽  
Order Complex ◽  
Complete Synchronization ◽  
Complex Valued
Sign in / Sign up

Export Citation Format

Share Document