At CRYPTO 2019, Gohr applied deep learning to differential cryptanalysis of SPECK32/64, achieving identification accuracy surpassing that of traditional differential distinguishers. This achievement offers new perspectives for data security and privacy protection in the Internet of Things (IoT). However, existing research still faces challenges such as limited model accuracy and excessive computational resource consumption. To address these issues, we propose a novel enhanced model of differential neural distinguishers that balances high accuracy with low computational overhead. Initially, an innovative data feature extraction strategy is designed by introducing the skip connection mechanism to effectively integrate both linear and non-linear features extracted from the raw data. This allows the model to better approximate the internal mechanisms of cryptographic algorithms. Subsequently, based on the positional relationships of non-linear components within round functions and the diffusion properties of linear components, an original input data format selection strategy is proposed. We employ the multi-pair data augmentation strategy, significantly improving the model’s identification accuracy and generalization capabilities. Additionally, we pioneer the integration of an Efficient Channel Attention (ECA) module, to curtail the number of residual blocks required, thereby effectively reducing computational load. Furthermore, leveraging the algebraic expressions of cryptographic ciphers and the propagation characteristics of differential features, we develop a fast neutral bit search algorithm that enhances the efficiency of the key recovery process. Taking SIMON32/64 as an example, we successfully demonstrate a key recovery attack for 16 rounds with an accuracy rate of 80%.

Lightweight block ciphers are proposed for Internet of Things (IoT) edge devices to ensure secure data transmission with limited resources. However, past research has been designed on ideal channel models, disregarding the possibility of ciphertext errors caused by channel interference during actual transmission. This omission poses difficulties in ensuring the reliability of the ciphertext, especially in the Internet of Medical Things (IoMT) where resources are limited and data accuracy requirements are high. Designing a highly secure and reliable lightweight block cipher for such situations is one of the most challenging tasks. Hence, we propose a lightweight block cipher ECLBC with error detection and correction mechanisms. For security, ECLBC not only achieves a certain security level in fewer rounds but also achieves a mode transition within AND-Rotation-XOR (AND-RX) lightweight block ciphers. This transition involves a shift from the Feistel to the Substitution-Permutation Network (SPN) and from half-round key XOR to full-round key XOR. For reliability, ECLBC supports detecting and correcting erroneous ciphertext due to channel interference. Given the resource-constrained nature of IoMT devices, we implement the detection and correction mechanism of ECLBC based on the linear block code. Finally, various classical cryptography methods are employed to analyze the performance and security of the ECLBC.

In the era of big data, one of the most critical challenges is ensuring secure access, retrieval, and sharing of linked spatiotemporal data. To address this challenge, this paper introduces a groundbreaking blockchain-enabled evolutionary indirect feedback graph algorithm for the secure management of interconnected spatiotemporal datasets. The algorithm utilizes a generative neural network model for data imputation, predicting and generating plausible values to improve dataset completeness and integrity. The core architecture utilizes blockchain technology to optimize data retrieval efficiency and uphold robust access control mechanisms. The algorithm incorporates indirect feedback mechanisms, allowing users to provide implicit feedback through their interactions, enhancing the relevance and efficiency of data retrieval. In addition. sophisticated graph-based techniques are used to model intricate relationships between data entities, facilitating seamless data retrieval and sharing in interwoven datasets. The algorithm’s data security approach includes comprehensive access control mechanisms, encryption, and authentication mechanisms, safeguarding data confidentiality and integrity. Extensive evaluations show significant enhancements in retrieval performance and access control precision, making the proposed model a promising solution for the secure management of expansive interconnected spatiotemporal data.

Matrix multiplication computation (MMC) is one of the most important basic operations with a variety of applications in the scientific and engineering community, including linear regression, k-nearest neighbor classification and biometric identification. However, performing these tasks with large-scale datasets can result in significant computation beyond the capabilities of resource-constrained clients. As outsourcing intensive tasks to cloud server has become a promising method, many matrix-transformation-based privacy-protected schemes have been presented for certain outsourcing tasks, such as Lei et al's scheme for the outsourcing MMC task and Zhao et al's scheme for matrix determinant computation. Nevertheless, Lei et al's scheme suffers from inherent security flaws that reveal the statistical information of zero elements in the original data. Additionally, Zhao et al's scheme can only be applied to specific outsourced tasks and is not suitable for more universal situations, such as MMC, where the client needs to compute the inverse matrix of the secret key. Therefore, designing an invertible matrix is a difficult task that affects privacy security, efficiency, and universality of the matrix-transformation-based privacy-protected outsourcing computing scheme. To address this challenge, we propose a subtly designed invertible matrix (SDIM) and a privacy-protected outsourcing MMC scheme based on the SDIM to remedy the inherent security flaws of Lei et al's scheme. We also propose an optimized matrix-chain multiplication method to maintain high efficiency of the SDIM-based privacy-protected scheme. This optimization also allows the SDIM to be universally applied not only to MMC tasks but also to other related outsourced tasks such as linear regression. Theoretical analyses and experiments show that our methods are more secure in terms of data privacy, with comparable efficiency to the state-of-the-art scheme based on matrix transformation. This SDIM-based scheme has achieved a well-balanced trade-off between security, efficiency and universality.

Automatic source code summarization system aims to generate a valuable natural language description for a program, which can facilitate software development and maintenance, code categorization, and retrieval. However, previous sequence-based research did not consider the long-distance dependence and highly structured characteristics of source code simultaneously. In this article, we present a Transformer-based Graph-Augmented Source Code Summarization (GA-SCS), which can effectively incorporate inherent structural and textual features of source code to generate an effective code description. Specifically, we develop a graph-based structure feature extraction scheme leveraging abstract syntax tree and graph attention networks to mine global syntactic information. And then, to take full advantage of the lexical and syntactic information of code snippets, we extend the original attention to a syntax-informed self-attention mechanism in our encoder. In the training process, we also adopt a reinforcement learning strategy to enhance the readability and informativity of generated code summaries. We utilize the Java dataset and Python dataset to evaluate the performance of different models. Experimental results demonstrate that our GA-SCS model outperforms all competitive methods on BLEU, METEOR, ROUGE, and human evaluations.

Encrypted traffic classification is a key technology for network monitoring and management, and its recent research results are mostly based on deep learning. Due to the difficulty in obtaining sufficient labeled data, few-shot traffic classification has received considerable attention. However, most of the existing results have two defects. First, they are mostly based on the assumption of a labeled base dataset for pre-training. Second, they neglect the problem of unknown traffic discovery under open-set conditions. In this paper, aiming at the problem of few-shot open-set encrypted traffic classification, a corresponding framework FSOSTC is constructed under the condition of unsupervised pre-training. Two data augmentation methods for packet feature map are proposed to assist the pre-training through self-supervised learning, which is combined with parameter fine-tuning, unknown discovery and class extension strategies. Experiments on public datasets verify the effectiveness of FSOSTC. For the few-shot open-set malicious traffic classification task, the CSA reaches 95.41% and the AUROC reaches 0.8664.

With the increasing concern on the preservation of personal privacy, privacy‐preserving data mining has become a hot topic in recent years. Spectral clustering is one of the most widely used clustering algorithm for exploratory data analysis and usually has to deal with sensitive data sets. How to conduct privacy‐preserving spectral clustering is an urgent problem to be solved. In this study, the authors focus on introducing the notion of differential privacy, which is considered as the de facto standard of privacy‐preserving data analysis, into spectral clustering. Specifically, by combining the well‐studied constrained spectral clustering with the Wishart mechanism in a novel way, the authors propose a differentially private constrained spectral clustering (DP‐CSC) algorithm. The DP‐CSC algorithm is proved to capture asymptotic property and achieves ‐differential privacy. To illustrate the effectiveness and efficiency of DP‐CSC, the authors conduct experiments on five real‐word data sets. The results indicate that the DP‐CSC algorithm can provide acceptable clustering accuracy with short running time while preserving individual privacy.

Cloud computing provides a flexible and convenient way for data sharing, which brings various benefits for both the society and individuals. But there exists a natural resistance for users to directly outsource the shared data to the cloud server since the data often contain valuable information. Thus, it is necessary to place cryptographically enhanced access control on the shared data. Identity-based encryption is a promising cryptographical primitive to build a practical data sharing system. However, access control is not static. That is, when some user's authorization is expired, there should be a mechanism that can remove him/her from the system. Consequently, the revoked user cannot access both the previously and subsequently shared data. To this end, we propose a notion called revocable-storage identity-based encryption (RS-IBE), which can provide the forward/backward security of ciphertext by introducing the functionalities of user revocation and ciphertext update simultaneously. Furthermore, we present a concrete construction of RS-IBE, and prove its security in the defined security model. The performance comparisons indicate that the proposed RS-IBE scheme has advantages in terms of functionality and efficiency, and thus is feasible for a practical and cost-effective datasharing system. Finally, we provide implementation results of the proposed scheme to demonstrate its practicability.

The amount of Internet data is significantly increasing due to the development of network technology, inducing the appearance of big data. Experiments have shown that deep mining and analysis on large datasets would introduce great benefits. Although cloud computing supports data analysis in an outsourced and cost-effective way, it brings serious privacy issues when sending the original data to cloud servers. Meanwhile, the returned analysis result suffers from malicious inference attacks and also discloses user privacy. In this paper, to conquer the above privacy issues, we propose a general framework for Preserving Multiparty Data Privacy (PMDP for short) in cloud computing. The PMDP framework can protect numeric data computing and publishing with the assistance of untrusted cloud servers and achieve delegation of storage simultaneously. Our framework is built upon several cryptography primitives (e.g., secure multiparty computation) and differential privacy mechanism, which guarantees its security against semihonest participants without collusion. We further instantiate PMDP with specific algorithms and demonstrate its security, efficiency, and advantages by presenting security analysis and performance discussion. Moreover, we propose a security enhanced framework sPMDP to resist malicious inside participants and outside adversaries. We illustrate that both PMDP and sPMDP are reliable and scale well and thus are desirable for practical applications.

As a new variant of digital signature, attribute-based signature (ABS) is appealing for many scenarios, where both authentication and anonymity are desired. However, in such a paradigm, a user's secret key is not linkable to an authenticated identity, and the same set of attributes might be shared among multiple users. Consequently, a malicious user would leak his secret key for some purposes without the risk of being identified among these equal users. On the other hand, for a cryptosystem with a large number of users, there should be an efficient revocation mechanism to further inform that a user's credential is abolished. We note that none of the existing ABS schemes simultaneously supports traceability and revocability, which are crucial towards the practicability of ABS. In this work, we first give a formal security model for traceable and revocable ABS. Next, we provide a concrete construction that admits flexible threshold signing predicates. Finally, we prove the anonymity and traceability of the proposed scheme in the standard model. To the best of our knowledge, our construction is the first ABS scheme that enjoys the functionalities of traceability and revocability simultaneously, and thus is more feasible for practical applications.

In an attribute-based signature (ABS) scheme, each signer is issued a private key according to his/her attributes, and can sign a message with respect to some signing predicate satisfied by his/her attributes. A recipient of the signature can verify that the signature is indeed endorsed by someone that possesses some attributes satisfying the signing predicate, without learning any information about the attributes that are utilized to produce the signature. Since the introduction of ABS, it has been well investigated in recent years. However, there are few works proposed to solve the problem of key exposure in the setting of ABS. In fact, this problem becomes more acute with the increasing tendency that unprotected and mobile devices are more and more popular. To solve the above problem, this work proposes a forward-secure ABS scheme supporting threshold predicates. The proposed scheme is proved secure under the η-Diffie–Hellman Exponent assumption without random oracles, and is also efficient in terms of communication and computation. Furthermore, it is implemented to show its practical applicability.

It is known that the set of rotation symmetric Boolean functions has many functions with various useful properties for cryptography. This study shows how to construct some families of rotation symmetric functions which are balanced or plateaued. The authors also consider vectorial Boolean functions [that is, maps from GF (2) n to GF (2) m ] which are k ‐rotation symmetric and they give two infinite families of such functions which are permutations with the maximum possible algebraic degree. The families of functions that they give provide a source, which can be searched for functions with other useful cryptographic properties.

ABSTRACT Signcryption can provide confidentiality and authenticity for many cryptographic applications. In this study, we propose a new efficient attribute‐based signcryption scheme. This scheme achieves confidentiality against chosen ciphertext attacks and unforgeability against chosen messages attacks in the selective attribute model. In addition, our scheme enjoys traceability by use of non‐interactive witness indistinguishable proofs; that is, the authority can break the anonymity of users when necessary. Compared with previous works, our scheme has advantages in terms of functionality and efficiency simultaneously. Copyright © 2013 John Wiley & Sons, Ltd.

In this paper, we consider constructions of rotation symmetric bent functions, which are of the forms: fc(x) = Σi=1m-1ci(Σj=0n-1xjxi+j) + cm(Σj=0m-1xjxm+j) and ft(x) = Σi=0n-1(xixt+ixm+i+ xixt+i) + Σi=0m-1xixm+i, where n = 2m, ciϵ {0,1} (the subscript u of xuin the previous expressions is taken as u modulo n). For each case, a necessary and sufficient condition is obtained. To the best of our knowledge, this class of cubic rotation symmetric bent functions is the first example of an infinite class of nonquadratic rotation symmetric bent functions.

In this paper, we consider the conjecture that σ2t+1l-1,2tare the only nonlinear balanced elementary symmetric Boolean functions wheretandlare positive integers. We prove ifn=2t+1l-1,lodd and 2t+1\nmidd, σn,dis balanced if and only ifd=2k, 1 ≤k≤t. Our results verify most cases of the conjecture forn≡ 3 (mod 4) .