Abstract Recently, image encryption is becoming increasingly important, many chaotic models have been prevalently used to design kinds of cryptographic schemes in chaos cryptography. Among those models, coupled map lattice (CML), as a classics spatiotemporal chaotic model with good performance, is popularly used for those chaos-based cryptographic schemes. However, there exist no scientific studies in the three dimensional (3D) CML model from the view of theoretical and application perspectives besides our previous research. To further improve the complicated chaotic dynamic behavior and extend the application scenarios of CML into a3D CML one, therefore it is introduced into our paper for constructing chaos-based image encryption scheme with higher security. First of all, properties of 3D CML are comprehensively analyzed to fully verify that it possesses more complicated chaotic behavior than one dimensional and two dimensional CML. Subsequently, the chaotic sequences are produced by means of intercepting 32 bit from each node of the 3D CML model, both NIST and TestU01 testing certificate those chaotic sequences have high randomness, which are pretty suitable for designing the chaos-based cryptographic scheme. Based on those above-mentioned analyses, a new color image encryption scheme is proposed via diffusion and confusion. In our scheme, diffusion is performed based on those above-mentioned chaotic sequences via the 3D CML model, while confusion is carried out according to the Baker map. Specially, before diffusion and confusion operations, red, green and blue channel of a plain color image are combined into one pixel including 24 bit (0 or 1) for improving the efficiency of our scheme. To sum up, all corresponding simulations show our scheme has excellent encryption performance, and it would be popularly applied in the real-life cryptographic domains. Our research contributes to enriching the theoretical research on chaotic cryptography and provides new chaotic image encryption schemes.

With the explosive growth of digital data, recommendation systems (RSs) play a crucial role in alleviating the problem of information overload. Implicit feedback data has become the primary data source for training recommendation models because of its richness and ease of collection. Leveraging such data for personalized recommendation services requires a large amount of user historical interactions, which poses serious privacy risks. Differential privacy (DP) has been integrated into implicit recommendation algorithms to protect user privacy. However, due to the inherent characteristics of implicit feedback, the current studies still have certain deficiencies in terms of data utility and privacy level. To this end, this article proposes a novel differentially private implicit recommendation algorithm. It integrates the Bayesian personalized ranking (BPR) matrix factorization (MF) with the Gaussian mechanism in Rényi DP (RDP) and designs an optimization strategy based on the binary index tree (BIT) to alleviate the cumulative errors. The proposed method not only can effectively capture the user preferences from sparse implicit feedback data by maximizing the posterior probability of rankings but also can more precisely manage the privacy budget allocation according to the query matrix. The theoretical analyses prove that the proposed method can satisfy the privacy guarantee and give the upper bound of privacy loss. The experimental results show that our method outperforms several existing advanced methods. It achieves a maximum performance improvement of 6.5% and 6.9% on Hit Rate (HR@10) and Normalized Discounted Cumulative Gain (NDCG@10) at a low privacy budget, which indicates that it can provide good recommendation quality while ensuring a strict privacy level.

With the advent of the intelligent era, increasing attention has been given to facial aesthetics. While the academic community has achieved notable progress in facial aesthetic research, current efforts predominantly concentrate on two isolated subtasks: aesthetic evaluation and enhancement. Crucially, the intrinsic correlation between these tasks and their integration within a unified framework remain underexplored. To bridge this gap, this paper proposes a facial aesthetic enhancement and prediction network based on differential average aesthetic perceptions (Diff-AEPNet) that synergistically combines facial aesthetic enhancement with prediction. The proposed framework implements a four-stage architecture: (1) a transformer module learns latent code beautification trajectories to guide preenhancement feature modification; (2) a dual-stream encoder extracts and contrasts pre/postbeautification features to refine evaluation accuracy; (3) a lightweight network generates attention-guided image mask for image fusion; and (4) a deghosting block eliminates fusion artifacts through residual learning. The experimental results demonstrate that the model achieves a favorable beautification effect in the enhancement task and exhibits better generalization performance across datasets in the evaluation task than existing aesthetic evaluation models do.

Abstract Face recognition has been widely used in many fields and has become an important identification method. The templates in face recognition systems are associated with the facial biometric features of users, and once leaked, it will pose a persistent threat to the users. Therefore, it is particularly important to protect the security of templates. In this work, a novel face template protection scheme is proposed by combining chaotic map, error correction code and locality sensitive hashing. The scheme utilizes two sets of parameters: global keys and user keys, and the generated data consists of two parts: storage key and biometric template. When generating a template, the extracted feature vector is permuted by using chaotic sequences to disrupt the correlation between different dimensions. Then, the user keys are processed by error correction code to generate the storage key, which can be used to recover the user keys during authentication. Finally, the permuted vector is processed by the proposed random number based locality sensitive hashing to generate biometric template. Experimental results and theoretical analysis show that the scheme has good accuracy and security, and can effectively resist various attacks on the face template.

In recommendation systems, the interactions between users and items are influenced by two factors: the user's conformity towards popular items and the user's real interest. Training individual user embeddings and item embeddings to capture these two factors can effectively improve the accuracy of recommendations. However, recommendation systems often exchange item embeddings with third-party servers, which may expose sensitive information to malicious attackers. Specifically, attackers can infer sensitive user information based on published item embeddings and partial public user information. In this paper, we first design a model inversion attack to analyze the influence of conformity item embeddings and interest item embeddings on privacy. This analysis reveals that different item embeddings have varying resistances against inversion attack. Based on the resistance levels of the two item embeddings, we propose a novel adaptive differential privacy protection method that enhances resistance against model inversion attacks while ensuring recommendation accuracy. We conduct experiments on three real datasets, and the results demonstrate the outstanding performance of our method in terms of both recommendation accuracy and resistance to inversion attack.

Implicit feedback data has become the primary choice for building recommendation models due to its abundance and ease for collection in the real world. The strong generalization capability and high computational efficiency of matrix factorization make it one of the principal models for constructing recommender systems. Recommenders have to collect vast amounts of user data for model training, which poses a significant threat to user privacy. Most of the current privacy enhancing recommendation systems mainly focus on explicit feedback data, and there are limited studies dedicated to the privacy protection of implicit recommender. To bridge the existing research gap, this paper designs a distributed differentially private matrix factorization for implicit feedback data in scenarios where the recommender is not trusted. Our mechanism not only eliminates the assumption of a trusted recommender, but also achieves the same accuracy as CDP-based privacy-preserving MF model. We prove that our mechanism satisfies$(\epsilon,\delta)$-CDP. The experimental results on three public datasets confirm that the proposed mechanism can achieve high recommendation quality.

Applying the chaos theory for secure digital communications is promising and it is well acknowledged that in such applications the underlying chaotic systems should be carefully chosen. However, the requirements imposed on the chaotic systems are usually heuristic, without theoretic guarantee for the resultant communication scheme. Among all the primitives for secure communications, it is well accepted that (pseudo) random numbers are most essential. Taking the well-studied 2-D coupled map lattice (2D CML) as an example, this article performs a theoretical study toward pseudorandom number generation with the 2D CML. In so doing, an analytical expression of the Lyapunov exponent (LE) spectrum of the 2D CML is first derived. Using the LEs, one can configure system parameters to ensure the 2D CML only exhibits complex dynamic behavior, and then collect pseudorandom numbers from the system orbits. Moreover, based on the observation that least significant bit distributes more evenly in the (pseudo) random distribution, an extraction algorithm$\mathbf {E}$is developed with the property that when applied to the orbits of the 2D CML, it can squeeze uniform bits. In implementation, if fixed-point arithmetic is used in binary format with a precision of$z$bits after the radix point,$\mathbf {E}$can ensure that the deviation of the squeezed bits is bounded by$2^{-z}$. Further simulation results demonstrate that the new method not only guides the 2D CML model to exhibit complex dynamic behavior but also generates uniformly distributed independent bits with good efficiency. In particular, the squeezed pseudorandom bits can pass both NIST 800-22 and TestU01 test suites in various settings. This study thereby provides a theoretical basis for effectively applying the 2D CML to secure communications.

Most previous studies on matrix factorization (MF)-based collaborative filtering (CF) have focused solely on user rating information for predicting recommendations. However, to further enhance the performance of recommender systems (RSs), it is important to also consider review information and rating reliability in the model. This article proposes a new probabilistic MF (PMF)-based CF method that integrates multiple information sources to provide reliable predictions. First, we introduce a sentiment-based PMF to handle user reviews and fit the normalized sentiment information obtained from our previously proposed sentiment analysis method. We also consider the helpfulness of reviews to highlight their reliability and effectiveness in this model. Subsequently, our proposed noise detection method is adopted to determine the reliability of user ratings, and then the rating matrix is transformed into a binary reliability matrix. A rating reliability-based PMF through Bernoulli distribution is then proposed to factorize it. To effectively integrate three types of information (ratings, reviews, and rating reliability) into a PMF procedure, we design a weight matrix using the proposed weighting strategy to generate a set of comprehensive prediction ratings with corresponding reliability probabilities. Experiments on four Amazon datasets demonstrate that our model outperforms comparison methods in terms of comprehensive evaluation.

The digital image, as the critical component of information transmission and storage, has been widely used in the fields of big data, cloud and frog computing, Internet of things, and so on. Due to large amounts of private information in the digital image, the image protection is fairly essential, and the designing of the encryption image scheme has become a hot issue in recent years. In this paper, to resolve the shortcoming that the probability density distribution (PDD) of the chaotic sequences generated in the original two-dimensional coupled map lattice (2D CML) model is uneven, we firstly proposed an improved 2D CML model according to adding the offsets for each node after every iteration of the original model, which possesses much better chaotic performance than the original one, and also its chaotic sequences become uniform. Based on the improved 2D CML model, we designed a compressive image encryption scheme. Under the condition of different keys, the uniform chaotic sequences generated by the improved 2D CML model are utilized for compressing, confusing, and diffusing, respectively. Meanwhile, the message authentication code (MAC) is employed for guaranteeing that the encryption image be integration. Finally, theoretical analysis and simulation tests both demonstrate that the proposed image encryption scheme owns outstanding statistical, well encryption performance, and high security. It has great potential for ensuring the digital image security in application.

In this paper, we discuss the couple-group consensus problem for heterogeneous multi-agent systems with communication and input time delays. From the perspective of the competitive relationship between agents, a novel group consensus protocol is designed which is distinctive to most of the existing works based on the cooperative networks. Specifically, we relax the restrictive assumptions existed in the related works and theoretically propose the sufficient algebraic criteria for the realization of couple-group consensus of the systems under the influence of multiple time delays. The results show that the achievement of the couple-group consensus depends on the agents' input time delays, coupling weights and the systems' control parameters, whereas it is independent of the communication time delays between the agents. Finally, the validity of our findings is verified by several simulations.

Abstract The cloud storage service has been widely used in daily life because of its convenience. However, the service frequently suffers confidentiality problems. To address this problem, some efforts have been made on keyword search over encrypted data schemes. For instance, the chaotic‐based keyword search scheme over encrypted data has been proposed recently. However, the scheme just only support single‐ keyword search each time, which severely limits its utilization in cloud storage. This article proposes a novel chaotic‐based time‐aware multi‐keyword search scheme with designated server. Inner product similarity is adopted in our scheme to realize multiple keyword search and remove the constraint of single‐keyword search each time. Timed‐release encryption is integrated into the proposed scheme at the same time, which enables the data sender to specify the time when the cloud servers can search the encrypted data. Analysis indicates that our scheme not only can counter off‐line guessing attacks to the ciphertext and trapdoor, but also supports ranked search with a reasonable computational cost. Copyright © 2015 John Wiley & Sons, Ltd.