This paper proposes a novel machine learning-based scheme for the automatic analysis of authentication and key agreement protocols. Considering the traditional formal protocol analysis schemes, their analysis accuracies depend heavily on the prior knowledge possessed by the analyst and the subjective understanding of the protocol. The rapid development of artificial intelligence in security field shows that the ideal way to get rid of the dependency is to use machine learning. Hence, we elaborately compare more than 2000 protocol analysis results and select 500 most representative ones of them to build a protocol dataset. Combining the protocol representation method of traditional schemes, these selected protocols are expressed as weight matrixes based on security components. Furthermore, a machine learning-based security analysis model is proposed to automatically find the attacks of the protocol. For now, three types of attacks against authentication and key agreement protocols can be identified based on our model. And experiment results show that it can reach almost 72% upper-bound performance. From the derivative of the accuracy curves, it can be inferred that the performance of our scheme will definitely get better as the dataset expands.

A machine learning-based scheme for the security analysis of authentication and key agreement protocols

In order to solve the existing security problem of the distributed network cloud disk, such as transmission, storage security problems, etc, a network cloud disk safety storage scheme based on Hadoop is proposed. Based on the different confidential level of user data, it gives selective encryption scheme, which gives full consideration to the following security issues, such as the security of the user data transmission in the network, user data no verification , the user data privacy might be leaked, etc. Combined with the rapid encryption of symmetric encryption algorithm and identity authentication of RSA , overtime checking and the performance of Hadoop , the distributed network cloud data security storage disk can supply secured, effective, stable effect. Finally the security of the scheme is proved by BANLOGIC.

The research of the data security for cloud disk based on the Hadoop framework

A fair exchange protocol enable two parties to exchange secrets with fairness, so that neither can gain any information advantage by quitting prematurely or otherwise misbehaving. Therefore a fair exchange is the most important for electronic transactions between untrusted parties. To design new fair exchange, after describing basic concepts, definitions and existing protocols and designing a non-interactive OT protocol using ELGamal`s public key system, I will design new protocol to support fair exchange. In my designed new protocol, untrusted parties exchange secrets obliviously and verify that their received secrets are true by using transformed Zero Knowledge Interactive Proof extended to duplex. At this time, concerned two parties can`t decrypt the other`s ciphertext. .After all of the steps, two parties can do it. It is the most important to provide perfect fairness and anonymity to untrusted parties in this protocol.

How To Exchange Secrets By OT.

The application of machine learning in the security analysis of authentication and key agreement protocol was first launched by Ma et al. in 2018. Although they received remarkable results with an accuracy of 72% for the first time, their analysis is limited to replay attack and key confirmation attack. In addition, their suggested framework is based on a multiclassification problem in which every protocol or dataset instance is either secure or prone to a security attack such as replay attack, key confirmation, or other attacks. In this paper, we show that multiclassification is not an appropriate framework for such analysis, since authentication protocols may suffer different attacks simultaneously. Furthermore, we consider more security properties and attacks to analyze protocols against. These properties include strong authentication and Unknown Key Share (UKS) attack, key freshness, key authentication, and password guessing attack. In addition, we propose a much more efficient dataset construction model using a tenth number of features, which improves the solving speed to a large extent. The results indicate that our proposed model outperforms the previous models by at least 10–20 percent in all of the machine learning solving algorithms such that upper-bound performance reaches an accuracy of over 80% in the analysis of all security properties and attacks. Despite the previous models, the classification accuracy of our proposed dataset construction model rises in a rational manner along with the increase of the dataset size.

/pdf/a-novel-machine-learning-based-approach-for-security-2vfu91vp6m.pdf

A Novel Machine Learning-Based Approach for Security Analysis of Authentication and Key Agreement Protocols

Nowadays, most people use cryptography to deal with sensitive information either during storing or during communication. Dealing with cryptography requires secret or privet keys. But some of users use unsuitable secret keys. They use either short, or weak keys. The short and weak keys are easy to be remembered. The risk of using weak or short keys is that the weak key can be guessed and the short key can be broken easily. In cryptography, it is known that the security produced are directly proportional to the quality and the length of the used secret keys. On security rules, secret key should not be saved or written in any file or written, because it weakens the associated security. This paper suggests a method to remember a long secret key easily by assigning a suitable name to each finger of the two hands, selecting start and end points, selecting predefined path, and finger sequence. The collection of symbols to the finger-names between the start and end points at the predefined path is the secret key.

هظفح ةلوهس عم يرس حاتفم ديلوت هركذتو Generating a suitable secret key with faciliting its saving and remembering

This paper analyzes the Otway-Rees protocol based on BAN logic after has introducing the BAN logic. It has verified that the BAN logic can be used formally and prove the correctness and security of the protocols, which indicates that BAN logic is an important tool for analyzing cryptographic protocols. The paper has established the ideal protocol model to Otway-Rees protocol based on the BAN logic, which uses the initial assumption of the protocol and the publicly known assumption of the BAN logic to analyze the security of Otway-Rees protocol.

Kening Liu

Papers

The Security Analysis on Otway-Rees Protocol Based on BAN Logic