Different from ship detection from synthetic aperture radar (SDSAR) and ship detection from spaceborne optical images (SDSOI), ship detection from visual image (SDVI) has better detection accuracy and real-time performance, which can be widely used in port management, cross-border ship detection, autonomous ship, safe navigation, and other real-time applications. In this paper, we proposed a new SDVI algorithm, named enhanced YOLO v3 tiny network for real-time ship detection. The algorithm can be used in video surveillance to realize the accurate classification and positioning of six types of ships (including ore carrier, bulk cargo carrier, general cargo ship, container ship, fishing boat, and passenger ship) in real-time. Based on the original YOLO v3 tiny network, we have made the following fine tunings. 1) The preset anchors trained on Seaship annotation data have the similar “dumpy” shape as the normal ships, helping the network to achieve faster and better training; 2) Convolution layer instead of max-pooling layer and expanding the channels of prediction network improve the small target detection ability of the algorithm. 3) Due to the problem that large-scale ships are easily disturbed by the onshore building, complex waves and light on the water surface, we introduced attention module named CBAM into the backbone network, which make the model more focused on the target. The detection accuracy of the proposed algorism is obviously better than that of the original YOLO v3 tiny work. Although it is slightly inferior to the Yolo v3 network, it has faster speed than Yolo v3. However, the proposed algorithm is a better trade-off between real-time performance and detection accuracy, and is more suitable for actual scenes. Compared with the SOAT algorithm in Z. Shao et al. (2020), our algorithm has a 9.6% improvement in mAP and a faster speed.

With the fast development of the Internet of Things (IoT) technologies, more IoT devices are currently connected with the Internet, resulting in more exchange of information. However, data privacy and security threats have become emerging challenges of the IoT. In this paper, we are concerned about the security of image transmission in green IoT. Image encryption algorithms for green IoT are faced with two challenges: 1) To save the cost, devices in green Internet of Things (IoT) always have very low computing power, so they cannot support high-precision computing and 2) The algorithm deployed on the device should be efficient to guarantee the device to run for a long time. To solve the problem of precision limited, we propose a parallel chaotic system named PSBP. ¹ The PSBP is composed of Piecewise Linear Chaotic Map (PWLCM), Skew Tent Map (STM) and Bernoulli map in parallel model with the limited precision of 16-bit, which can generate good-performance key matrix for encryption. Then, we introduce a cost-efficient image encryption algorithm based on PSBP (named IEPSBP) which addresses the second challenge. Instead of bits or bytes, we use one row or one column as the basic unit to realize permutation and diffusion. The security analysis and performance experiments indicate that IEPSBP is secure and cost-efficient for green IoT.

Enterprises and organizations are faced with potential threats from insider employees that may lead to serious consequences. Previous studies on insider threat detection (ITD) mainly focus on detecting abnormal users or abnormal time periods (e.g., a week or a day). However, a user may have hundreds of thousands of activities in the log, and even within a day there may exist thousands of activities for a user, requiring a high investigation budget to verify abnormal users or activities given the detection results. On the other hand, existing works are mainly post-hoc methods rather than real-time detection, which can not report insider threats in time before they cause loss. In this paper, we conduct the first study towards real-time ITD at activity level, and present a fine-grained and efficient framework LAN. Specifically, LAN simultaneously learns the temporal dependencies within an activity sequence and the relationships between activities across sequences with graph structure learning. Moreover, to mitigate the data imbalance problem in ITD, we propose a novel hybrid prediction loss, which integrates self-supervision signals from normal activities and supervision signals from abnormal activities into a unified loss for anomaly detection. We evaluate the performance of LAN on two widely used datasets, i.e., CERT r4.2 and CERT r5.2. Extensive and comparative experiments demonstrate the superiority of LAN, outperforming 9 state-of-the-art baselines by at least 8.43% and 6.35% in AUC for real-time ITD on CERT r4.2 and r5.2, respectively. Moreover, LAN can be also applied to post-hoc ITD, surpassing 8 competitive baselines by at least 7.70% and 4.03% in AUC on two datasets. Finally, the ablation study, parameter analysis, and compatibility analysis evaluate the impact of each module and hyper-parameter in LAN. The source code can be obtained from https://github.com/Li1Neo/LAN.

In these years, image encryption systems based on chaotic maps have received considerable attention from researchers. For the security of encryption algorithms, it is important to ensure that chaotic systems can produce high quality pseudo-random sequences. However, when a chaotic system that theoretically has good random performance is deployed in a limited precision platform, its random performance will deteriorate. We prove that even if the precision reaches 256-bit, the piecewise linear chaotic map still fails to achieve the desired random performance. Moreover, in the case of low precision, the cascade structure commonly used in mixed chaotic maps will aggravate the problem of random degeneration. To generate good pseudo-random numbers in low-precision platforms, we propose a positive integer random sequence generator, called 32-bit PL_PWLCM&LM, which comprises two 32-bit PL_PWLCMs and one 32-bit logistic map in parallel. In our proposed image encryption system, we adopt the permutation algorithm with four pixels as a permutation unit and the diffusion algorithm based on rows and columns. The security and performance analyses prove that the proposed scheme is a secure, robust, and fast image encryption algorithm. Source codes are shared on GitHub: https://github.com/cuclihao/Pic_Enc_V3.

In the construction process of smart cities, more and more video surveillance systems have been deployed for traffic, office buildings, shopping malls, and families. Thus, the security of video surveillance systems has attracted more attention. At present, many researchers focus on how to select the region of interest (RoI) accurately and then realize privacy protection in videos by selective encryption. However, relatively few researchers focus on building a security framework by analyzing the security of a video surveillance system from the system and data life cycle. By analyzing the surveillance video protection and the attack surface of a video surveillance system in a smart city, we constructed a secure surveillance framework in this manuscript. In the secure framework, a secure video surveillance model is proposed, and a secure authentication protocol that can resist man-in-the-middle attacks (MITM) and replay attacks is implemented. For the management of the video encryption key, we introduced the Chinese remainder theorem (CRT) on the basis of group key management to provide an efficient and secure key update. In addition, we built a decryption suite based on transparent encryption to ensure the security of the decryption environment. The security analysis proved that our system can guarantee the forward and backward security of the key update. In the experiment environment, the average decryption speed of our system can reach 91.47 Mb/s, which can meet the real-time requirement of practical applications.

Internet of Multimedia Things (IoMT) brings convenient and intelligent services while also bringing huge challenges to multimedia data security and privacy. Access control is used to protect the confidentiality and integrity of restricted resources. Attribute-Based Access Control (ABAC) implements fine-grained control of resources in an open heterogeneous IoMT environment. However, due to numerous users and policies in ABAC, access control policy evaluation is inefficient, which affects the quality of multimedia application services in the Internet of Things (IoT). This paper proposed an efficient policy retrieval method to improve the performance of access control policy evaluation in multimedia networks. First, retrieve policies that satisfy the request at the attribute level by computing based on the binary identifier. Then, at the attribute value level, the depth index was introduced to reconstruct the policy decision tree, thereby improving policy retrieval efficiency. This study carried out simulation experiments in terms of the different number of policies and different policy complexity situation. The results showed that the proposed method was three to five times more efficient in access control policy evaluation and had stronger scalability.