The complicated multi-step attacks, such as Advanced Persistent Threats (APTs), have brought considerable threats to cybersecurity because they are naturally varied and complex. Therefore, studying the strategies of adversaries and making predictions are still significant challenges for attack preventions. To address these problems, we propose DeepAG, a framework utilizing system logs to detect threats and predict the attack paths. DeepAG leverages transformer models to novelly detect APT attack sequences by modeling system logs with semantic information. On the other hand, DeepAG utilizes Long Short-Term Memory (LSTM) network to propose bi-directional prediction for attack paths, which achieves higher performance than traditional BiLSTM. In addition, with previously detected attack sequences and predicted paths, DeepAG constructs the attack graphs that attackers may follow to compromise the network. Furthermore, DeepAG offers the mechanisms of Out-Of-Vocabulary (OOV) word processor and online update respectively to adapt new attack patterns that show up during detection and prediction stages. The experiments on open-source data sets show that more than 99% of over 15000 sequences can be detected accurately by DeepAG. Moreover, DeepAG can improve the baseline by 11.166% of accuracy in terms of prediction.

Wireless networks ensure the unmanned aerial vehicles (UAVs) communicate and cooperate with each other, which plays an indispensable role among UAVs. The two crucial challenges in UAV wireless networks are energy saving and security. The current lightweight communication approaches lead to insufficient robustness of the encrypted transmission that is insecure. To address this issue, we propose a secure transmission approach with energy efficiency toward UAVs networks. We design a lightweight symmetric encryption algorithm based on SM4 and the relevant key negotiation and update mechanism to protect the confidentiality of communication contents. Moreover, a modified aggregative BLS signature scheme, together with the Merkle Hash tree (MHT), is introduced to guarantee the integrity and authenticity of data packets in transmission. Furthermore, we propose an online/offline revocable identity-based group signature (OORIBGS) scheme and integrate it into our framework for UAV anonymity, traceability, as well as revocability with small key management cost and high efficiency. We give detailed security analysis and prove that our proposal has the properties of data confidentiality, integrity, and authenticity, as well as identity traceability and anonymity. Moreover, we apply our approach in the UAVs networks and evaluate the runtime and anti-attack performance. The experimental results show that the proposed method can be effectively used in UAVs secure communication.

Cloud-Fog-Assisted Internet-of-Things (IoT) is a convincing paradigm to provide users with on-demand and low-latency services through Fog nodes in the edge of multiple clouds (Multi-Cloud). Multi-Cloud is a scalable multi-domain service-oriented net-centric system and can respond to complicated user requirements leveraging Multi-Cloud Service Composition (MCSC). However, in MCSC, user security can be easily compromised by untrusted and curious cloud service providers that may collect and violate the privacy and other essential assets of cloud users. Although many trust-based MCSC solutions have been proposed to seek a trustworthy composite service with highest trust level, most of them are vulnerable to malicious users intending to break through the clouds and inflict serious data leakage or asset damage. Considering these security concerns on both malicious users and untrusted service providers, in this paper, we present a trust-based secure multi-cloud collaboration framework for Cloud-Fog-Assisted IoT systems. Specifically, to guarantee the security of users, we develop a role-based trust evaluation method to enhance the trustworthiness of MCSC. To preserve the security of services, we design an efficient user authentication scheme and a secure collaboration scheme to provide collaborative user authentication and access control mechanism for MCSC. We evaluate its performane with extensive experiments

Formation flight of unmanned aerial vehicles (UAVs) utilizes reconfiguration procedures to handle a variety of emergencies, such as collision avoidance, malfunctions, fuel savings, and member replacement. As UAVs have limited computing power and energy resources, it is necessary to optimize the control inputs to reduce the distance travelled by UAVs while reducing the computing costs during formation reconfiguration. In this paper, the problem of multi-UAV reconfiguration is decoupled into two stages: task assignment and control input optimization of UAVs. For a solution to the above problem, we propose an adaptive hybrid particle swarm optimization and differential evolution algorithm (AHPSODE) to optimize minimize the distance of the total movement and reduce the computing cost of formation reconfiguration. Based on the idea of receding horizon control (RHC) and the nonlinear model of multi-UAV formation reconfiguration, an RHC controller using AHPSODE is designed to optimize the control input of the UAV group to obtain the shortest movement distance, and this method can reduce the computation time. We use the CEC 2017 test suit to test the performance of our proposed AHPSODE algorithm, and simulate the AHPSODE-based RHC controller to manage formation reconfiguration. The results show that our proposed AHPSODE performed well in convergence and accuracy and the RHC controller is effective.

The rapid development of cloud computing and Internet of Things enables widely use of Internet of Vehicles (IoV) and drives a revolutionary change for intelligent transport system. The advent of 5G and fog computing architectures also facilitates applications of IoV and makes the enormous IoV data outsourcing and sharing in cloud and fog more convenient. However, the data outsourcing and sharing will incur many security concerns to IoV including data leakage and breach as the users cannot direct control their data. To guarantee IoV data security, a novel scheme is proposed for IoV data sharing with high efficiency. In our scheme, we utilize ciphertext-policy attribute-based encryption (CP-ABE) to achieve confidentiality and fine-grained access control for IoV data shared in cloud and fog. Nevertheless, as another intrinsic feature in IoV environment, the dynamicity in a group of connected vehicles brings some challenges to our scheme. To deal with this situation, we bring forward a concept of auditable user revocation for CP-ABE to adapt to the dynamic vehicle groups. Moreover, online/offline and verifiable outsourcing techniques are leveraged to improve the efficiency and guarantee the correctness of decryption. At the end, we demonstrate the security and efficiency for our scheme by giving detailed security analysis and performance evaluation with extensive experiments.

Wireless rechargeable sensor networks (WRSNs) have become a hot research issue owing to the breakthrough of wireless power transfer (WPT) technology. Previous theoretical schemes are mostly designed for 2-D networks, and few of them are tailored for 3-D scenarios, making them not suitable for wide adoptions in practical applications. In this paper, we address the issue of how to serve a 3-D WRSN with an unmanned aerial vehicle (UAV). Our main concern is to maximize the charged energy for sensors supplied by the UAV, which has energy constraints. We respectively develop a spatial discretization scheme to construct a finite feasible set of charging spots for the UAV in a 3-D environment and a temporal discretization scheme to determine the appropriate charging duration for each charging spot. Then, we reduce the problem into a submodular maximization problem with routing constraints and present a cost-efficient algorithm (CEA) with a provable approximation ratio to solve it. Finally, test-bed experiments are conducted to show the feasibility of our schemes in practical scenarios. Extensive simulations are taken to verify the superior performance of our algorithm in charged energy and robustness. The charged energy of our scheme outperforms other competing methods by at least $18.2\%$ .