Underwater acoustic sensor networks (UASNs) are extensively utilized in various sectors, including aquaculture, naval operations, and oceanic disaster alert systems. The protection of UASNs, with a specific focus on internal threats, has become an increasing priority. Attacks originating from within the network, involving compromised legitimate nodes, can be more harmful and covert compared to external threats, such as communication interception, data decryption, and identity impersonation. Trust models, which serve as mechanisms for detecting internal threats through interaction data, have proven effective in enhancing UASN security. However, traditional trust models often face scalability issues, particularly in environments characterized by mobile underwater devices, diverse network conditions, and evolving attack strategies. To address these challenges, this work presents a novel trust management scheme based on attention-weighted federated deep reinforcement learning (AFRTM). The AFRTM overcomes the limitations of existing approaches by first improving the evidence quantification methods-encompassing both environmental and behavioral evidence-to better adapt to the uncertainty of underwater scenarios. Subsequently, the acquired trust evidence is input into the respective deep reinforcement learning (DRL)-driven local trust framework to achieve trust estimation and model development. Finally, the model's parameters are periodically aggregated and updated using an attention-weighted federated learning method, ensuring adaptability to changing conditions. The experimental findings demonstrate that the suggested approach delivers commendable outcomes in enhancing trust estimation precision and energy efficiency, and further providing a robust solution to the security challenges faced by UASNs.

Routing-driven timely data collection in Underwater Acoustic Sensor Networks (UASNs) is crucial for marine environmental monitoring, disaster warning, and underwater resource exploration, etc. However, harsh underwater conditions, including high delays, limited bandwidth, and dynamic topologies, make efficient routing decisions challenging in UASNs. In this paper, we propose a smart interrupted routing scheme for UASNs to address dynamic underwater challenges. We first model underwater noise influences from real underwater routing features, e.g., turbulence and storms. We then propose a Software-Defined Networking (SDN)-based Interrupted Software-defined UASNs Reinforcement Learning (ISURL) framework, which ensures adaptive routing through dynamical failure handling (e.g., energy depletion of sensor nodes or link instability) and real-time interrupted recovery. Based on ISURL, we propose the MA-MAPPO algorithm, integrating multi-head attention mask mechanism with MAPPO to filter out infeasible actions and streamline training. Furthermore, to support interrupted data routing in UASNs, we introduce MA-MAPPO_i, MA-MAPPO with interrupted policy, to enable smart interrupted routing decisions in UASNs. The evaluations demonstrate that our proposed routing scheme achieves exact underwater data routing decisions with faster convergence speed and lower routing delays than existing approaches.

Recent advances in network technologies and Multi Agent Reinforcement Learning (MARL) have accelerated the development of Autonomous Underwater Vehicle (AUV) cluster networks, enabling intelligent applications such as target tracking and cooperative target encirclement. However, existing MARL models are typically designed for single-task scenarios, limiting their scalability in real-world multi-task environments. To ad dress this, we propose a lightweight MARL framework capable of handling multiple AUV tasks with reduced reliance on underwater sampling. Specifically, a unified state space representation is constructed to support task generalization, while a hybrid online offline MARL training paradigm is introduced by leveraging the logical reasoning and sample generation capabilities of Large Language Models (LLMs). This reduces the demand for real-time data collection. Furthermore, a supervised pretraining strategy is incorporated to improve convergence and learning stability. Based on these components, we develop the Large Language Model-driven Hybrid online-offline MARL algorithm towards Multi-Task scenarios (LLM-HMT), which supports intelligent deployment of multi-task AUV cluster systems with minimal state representation, reduced sample requirements, and limited training iterations. Extensive experiments demonstrate that LLM HMT outperforms mainstream MARL baselines in convergence speed, task success rate, and resource efficiency, highlighting its potential for practical underwater applications.

Deep learning compilers are essential for deploying deep learning applications across heterogeneous hardware platforms. To improve execution efficiency, they employ sophisticated optimizations, which inevitably introduce bugs due to their considerably large code size and complex logic. Therefore, effectively detecting optimization bugs is essential to guarantee the correctness and trustworthiness of deep learning compilers.In this paper, we present ORThrus, an automatic approach to effectively detect optimization bugs in deep learning compilers. Conceptually, our approach develops a non-optimizing reference compiler to an optimizing compiler, then to detect optimization bugs by comparing the discrepancies in the two compilers’ outputs. Obtaining a non-optimizing reference compiler is challenging, because existing deep learning compilers provide limited control over optimizations. We thus propose a novel approach dubbed optimization resistance transformation that structurally transforms an input deep learning model from an optimizable form to an unoptimizable form that the deep learning compiler can no longer perform the potential optimizations. We build a prototype for our approach and evaluate it in an extensive testing campaign on two widely-used deep learning compilers TVM and ONNXRuntime. ORThrus detects 21 bugs, of which 9 are non-crash optimization bugs and 1 is missed by the state-of-the-art tool NNSmith even with its cross reference feature enabled. Meanwhile, ORThrus introduces negligible execution overhead.

In this study, the task assignment problem for heterogeneous underwater vehicle collaborative system, which involves autonomous underwater vehicles (AUVs) and underwater gliders (UGs), is studied for high-efficiency data collection. UGs and AUVs show different motion modes. The advantages of different motion modes can be mutually complemented to achieve the preference-matched task assignment results, which show greatly promising prospect to enhance the data collection efficiency. Most of existing underwater task assignment algorithms focus on the single-type vehicles, which can not be applied to the heterogeneous system. To address this issue, a hierarchical learning algorithm is proposed. Firstly, based on the evaluated emergency degree of tasks, the preliminary-task-assignment hierarchy is proposed to assign the emergency tasks to AUVs and assign the non-emergency tasks to UGs, thereby achieving the preference-matched task assignment. Therefore, the collaborative efficiency of heterogeneous system can be enhanced. Then, in the UG-task-assignment hierarchy, the adaptive serial cluster mechanism is proposed to extract the high utility task-connectivity regions for UGs, thereby fully leveraging the UG advantages in region data collection. Furthermore, in the AUV-task-assignment hierarchy, the extended self-organizing mapping neural network is constructed to eliminate the disorganization of neuronal loops. As a result, the crossed paths of AUVs can be excluded to reduce the energy consumption. Finally, the superior performance is verified by numerical results.

This paper investigates a joint discrete-channel and continuous-power allocation problem for multi-user underwater acoustic communication networks. The unknown underwater acoustic Channel State Information (CSI) and the distributed optimization requirement make the proposed hybrid discrete-continuous optimization problem full of challenges. Firstly, an adversarial multi-player bandit game model is formulated, which enables each user to independently optimize its own strategy, thereby achieving the distributed decision. In the strategic game, the Multi-armed Bandit (MAB) learning theory is exploited to achieve the best response strategy of independent user without prior CSI. Secondly, an evolutive finite discrete strategy pool learning structure is proposed to achieve an efficient search for the hybrid discrete-continuous space. The constant evolvement of strategy pool endows the proposed MAB-based algorithm with the ability to search the whole continuous power space, thereby avoiding missing the superior strategy caused by the discretization of continuous space. Thirdly, a selection probability setting rule is proposed, which promotes the exploration-exploitation balance for the dynamic strategy pool, thereby improving the learning efficiency. Finally, simulation results demonstrate the superiority of the proposed algorithm.

This article deals with a joint multiple resources (relay, channel, and power) allocation problem for underwater acoustic (UWA) cooperative communication in time-varying Internet of Underwater Things scenarios. The strong coupling of multiple resources and the unknown time-varying characteristic of UWA communication scenes make the joint optimization problem full of challenges. To address this issue, the adversarial multiarmed bandit online learning model without any prior channel information and statistic assumptions is employed. Furthermore, a double closed-loop learning structure with multiple intelligent experts assistance is proposed. Multiple experts embedded in inner loop can intelligently learn the derived inferential information to provide more efficient advice for the player in outer loop, thereby enriching learning information and enhancing learning ability. In addition, the expert diversity learning mechanism is proposed to fully reflect the characteristics of seeking advantages and avoiding disadvantages in the double closed-loop learning structure. As a result, the learning speed and performance of the proposed algorithms are significantly improved. The superiorities of the proposed algorithms are demonstrated through numerical results.

This article deals with the task assignment problem for multiple autonomous underwater vehicles to efficiently collect underwater data from sensors. We formulate a unified framework to consistently address the heterogeneous task assignment problem (nonemergency and emergency cases) without strictly distinguishing the mixed cases. First, a unified problem, which bridges the gap between different constraints and optimization objectives of different cases, is constructed. Then, the proposed reinforced self-organizing mapping algorithm is reinforced in three aspects: the regional learning rate, the self-configuring neuron (SCN) strategy, and the workload balance mechanism. Specifically, the proposed regional learning rate comprehensively considers the individual worth of tasks and the topology to generate the regional learning rate of dynamic task regions, which consists of dynamic remaining tasks and the reconstructed topology. Based on this idea, the constructed unified problem can be solved consistently. Furthermore, the proposed SCN strategy optimizes the neuron population both in quality and quantity, and guides the update of neurons with enriched historical information to improve the mapping ability. This strategy greatly improves learning efficiency and applicability in a wide range of scenarios. Meanwhile, the proposed workload balance mechanism takes into consideration of both the work capability and consumed energy to extend the continuous working capability. The numerical results validate the effectiveness and adaptability of the proposed unified task assignment framework.

Acoustic ranging is required to obtain the location of underwater mobile vehicles in the Internet of Underwater Things (IoUT). As seawater is an inhomogeneous medium, the sound velocity in the ocean is not constant, thereby causing sound waves to deviate from a straight line of propagation and bend. Thus, the travel time of the sound wave from the transmitter to receiver cannot be directly converted to a range value using a linear relationship as is done in the case of wireless radio ranging in the air. Therefore, the concept of effective sound velocity was introduced to account for the differences between the sound velocities at a transmitter and receiver. This enables conversion of the travel time to slant distance via a linear relationship. However, the existing methodologies for computing effective sound velocities are computationally intensive, which hinders the use of acoustic ranging in small underwater mobile vehicles operating in the deep sea. This study aimed to resolve this problem by developing an effective, computationally less demanding algorithm that could improve the precision of acoustic ranging on such platforms. The proposed algorithm converts global integrals into local integrals that correspond to depth variation ranges, thereby reducing the amount of integral calculation. The performance of the proposed algorithm is evaluated using extensive simulations and real deep-sea experimental data sets obtained at a depth of 3000 m. The results verify the efficacy of the algorithm in realizing real-time underwater acoustic ranging in deep sea. The proposed algorithm can improve the accuracy of real-time effective sound velocity measurement by small underwater mobile vehicles, and subsequently realize low-complexity underwater acoustic ranging in the deep-sea IoUT networks.

The exploitation/utilization of marine resources and the rapid development of urbanization along coastal cities result in serious marine pollution, especially underwater diffusion pollution. It is a non-trivial task to detect the source of diffusion pollution, such that the disadvantageous effect of the pollution can be reduced. With the vision of 6G framework, we employ Autonomous Underwater Vehicle (AUV) flock and introduce the concept of AUV-based network. In particular, we utilize the Software-Defined Networking (SDN) technique to update the controllability of the AUV-based network, leading to the paradigm of SDN-enabled multi-AUVs network Intelligent Transportation Systems (SDNA-ITS). For SDNA-ITS, we utilize artificial potential field theories to model the control model. To optimize the system output, we introduce the graph-based Soft Actor-Critic (SAC) algorithm, i.e., a category of Multi-Agent Reinforcement Learning (MARL) mechanism where each AUV can be regarded as a node in a graph. In particular, we improve the optimization model based on Centralized Training Decentralized Execution (CTDE) architecture with the assistance of the SDN controller, by which each AUV can efficiently adjust its speed towards the diffusion source. Further, to achieve exact path planning for detecting the diffusion source, a dynamic detection scheme is proposed to output the united control policy to schedule the SDNA-ITS dynamically. Simulation results demonstrate that our approaches are available to detect the underwater diffusion source when the actual scenario is taken into account and perform better than some recent research products.

The rapid development of intelligent underwater devices promotes marine exploitation activities, including marine resource exploitation, marine target tracking, etc. This work will present how to utilize the Autonomous Underwater Vehicle (AUV) swarm or multi-AUVs system to track the underwater diffusion pollution, especially the equipotential line of particular concentration. Different from most of the current research, in this work, we take the AUV swam as a network system and utilize the Software-Defined Networking (SDN) technique to optimize the network architecture, constructing an SDN-enabled AUV network Intelligent Transportation Systems (ITS). With the centralized management ability of the SDN technique, we propose the software-defined Centralized Training Decentralized Execution (CTDE) architecture based on the graph-based Soft Actor-Critic (SAC) algorithm to optimize the system control and management. To improve the computing and training efficiency, we embed the self-attention mechanism into the critic network construction, leading to a self-attention-based SAC algorithm. Evaluation results demonstrate that our proposed approach is able to exactly track the equipotential lines of a particular concentration in many categories (with different types of equipotential lines (including the shape, noise, and diffusion value)) of underwater diffusion fields. Meanwhile, our proposed approaches outperform some classical schemes in system awards, tracking errors, etc.

Pairwise ranging between nodes plays a crucial role in Internet-of-Underwater-Things (IoUT) networks, and it typically impacts the overall performance of such networks. As the sound speed depends on several parameters, time-of-flight-based techniques cannot work well under varying sound speeds in actual underwater conditions. Pairwise ranging algorithms that consider stratification should be studied to improve ranging accuracy. However, there is a tradeoff between underwater acoustic ranging accuracy and number of calculations. This makes it challenging to implement underwater acoustic ranging algorithms in IoUT networks. In this article, we propose an underwater acoustic horizontal ranging algorithm that rapidly and accurately estimates the horizontal range from a sender to a receiver under an arbitrary sound-speed profile in the deep sea. Simulation results show that the proposed algorithm accurately calculates the horizontal range with a low computational complexity. We validate the performance of the proposed algorithm using the data collected during an ultrashort baseline precision test in the South China Sea.

Motivated by the problem that the position error of strap-down inertial navigation system (SINS) accumulates over time while a deep-diving human occupied vehicle (HOV) executes unpowered diving, this paper describes an online SINS error amendment method using range-only positioning. The proposed method can avoid the use of expensive ultra-short baseline (USBL) system that needs to be precisely calibrated and long baseline (LBL) system, which is hard to be calibrated and expensive in ship time to deploy. The proposed method utilizes only a set of acoustic ranges from submersible support vessel as measurement information and the SINS error model as process model, based on which the error divergence is eliminated using extended Kalman filter(EKF). Results of simulation show that SINS/Range-only can effectively amend the longitude and latitude error in SINS based on the proposed method.