Search

In today's business environment, reducing costs is crucial due to the variety of Internet of Things (IoT) devices and security infrastructure. However, applying security measures to complex business scenarios can lead to performance degradation, making it a challenging task. To overcome this problem, we propose a novel algorithm based on deep reinforcement learning (DRL) for optimizing cost in multi-party computation software-defined security middle platforms (MPC-SDSmp) in real-time. To accomplish this, we first integrate fragmented security requirements and infrastructure into the MPC-SDSmp cloud model with privacy protection capabilities to reduce deployment costs. By leveraging the power of DRL and cloud computing technology, we enhance the real-time matching and dynamic adaptation capabilities of the security middle platform (Smp). This enables us to generate a real-time scheduling strategy for Smp resources that meet low-cost goals to reduce operating costs. Our experimental results demonstrate that the proposed method not only reduces the costs by 13.6% but also ensures load balancing, improves the quality-of-service (QoS) satisfaction by 18.7%, and reduces the average response time by 34.2%. Moreover, our solution is highly robust and better suited for real-time environments compared to the existing methods. [ABSTRACT FROM AUTHOR]

Although cloud computing is one of the promising technologies for online business services, how to schedule real-time cloud jobs with high quality of service (QoS) is still challenging current techniques. With the advancing of machine learning, deep reinforcement learning (DRL) has demonstrated its outstanding capability in dispatching time-sensitive tasks. However, the reinforced rewards in DRL are typically unavailable until the completion of the scheduling for all the jobs. Considering the fact that the trajectory of jobs in cloud is always long, current DRL-based solutions will meet challenges in finding the trajectories with high rewards, and thus would have issues such that the finally trained scheduling policy is suboptimal. To improve the problem, in this article, we propose a more advanced approach called a deep adversarial imitation reinforcement learning (AIRL) framework for scheduling time-sensitive cloud jobs. Specifically, we focus on scheduling user requests in a way to maximize job successful rate along with a significant reduction on job response time. We present the detailed design of our method, and our experimental results demonstrate that AIRL can generally outperform the existing cloud job scheduling approaches, including the DRL-based method, in the presence of different real-time workload and computing resource configurations. [ABSTRACT FROM AUTHOR]

Big data and cloud computing could bring security problems. In order to ensure data security and user privacy, people would choose to store data in the cloud with ciphertext. How to search data efficiently and comprehensively without decryption has become the focus of this paper. In this paper, we propose an efficient privacy protection scheme. In this scheme, Elliptic Curve Cryptography (ECC) is adopted to encrypt the data. It can reduce the computing cost of encryption and decryption uploading the encrypted files and indexes to the cloud server. Then it can authorize users to generate trap door using hash conflict function, and send it to Cloud Service Provider (CSP) for searching for matched ciphertext. The CSP uses the Apriori algorithm to extend keywords and search index to match the ciphertext. In this paper, we will use the Apriori algorithm to extend the keywords' semantics, match the index list based on these keywords, and return the requested file-set which is more consistent with the user's search. Experiments show that compared with traditional methods, files can be encrypted, decrypted, and recovered more quickly when we use this method. It can also ensure the privacy of data and reduce the communication overhead. [ABSTRACT FROM AUTHOR]

In power cloud environment, the existing Ciphertext-Policy Attribute-Based Encryption (CP-ABE) access control schemes, do not consider the generation of access structure and the existence of malicious users. To tackle these problems, a power cloud access control (PCAC) scheme is proposed, which improves the traditional CP-ABE access control model. Considering the heavy time consumption of CP-ABE, PCAC encrypts the symmetric key, instead of the raw data. PCAC combines the access tree and linear secret-sharing scheme (LSSS) to achieve the automatic generation and efficient operation of access structure. Additionally, an action audit phase, based on zero-knowledge verification was designed to defend against malicious users. The experiments proved that PCAC meets the requirement of fine-grained access control, in a power cloud. Compared with existing CP-ABE schemes, the PCAC scheme reduced about half of the time consumption, in the action audit phase and costs about one-third the time, in the data obtainment stage. [ABSTRACT FROM AUTHOR]

With the rise in biometric-based identity authentication, facial recognition software has already stimulated interesting research. However, facial recognition has also been subjected to criticism due to security concerns. The main attack methods include photo, video, and three-dimensional model attacks. In this paper, we propose a multifeature fusion scheme that combines dynamic and static joint analysis to detect fake face attacks. Since the texture differences between the real and the fake faces can be easily detected, LBP (local binary patter) texture operators and optical flow algorithms are often merged. Basic LBP methods are also modified by considering the nearest neighbour binary computing method instead of the fixed centre pixel method; the traditional optical flow algorithm is also modified by applying the multifusion feature superposition method, which reduces the noise of the image. In the pyramid model, image processing is performed in each layer by using block calculations that form multiple block images. The features of the image are obtained via two fused algorithms (MOLF), which are then trained and tested separately by an SVM classifier. Experimental results show that this method can improve detection accuracy while also reducing computational complexity. In this paper, we use the CASIA, PRINT-ATTACK, and REPLAY-ATTACK database to compare the various LBP algorithms that incorporate optical flow and fusion algorithms. [ABSTRACT FROM AUTHOR]