Attribute-Based Encryption (ABE) is an advanced public-key encryption paradigm that enforces fine-grained access control over encrypted data. For instance, the data owner can generate the ciphertext associated with ((”Cardiology” OR ”Critical Care Medicine”) AND ”Consultant Physician”), which can only be decrypted by other data users whose attributes satisfy this access policy. However, a major efficiency drawback of ABE is that ciphertext size, encryption time, and decryption time grow with the complexity of the access policy and the number of attributes. To address this issue, we propose an adaptively secure, offline/online and outsourcing ABE scheme under the Generic Group Model. The majority of encryption operation is performed during the offline phase, while ABE ciphertext is quickly assembled during the online phase. Decryption outsourcing enables the edge node to convert the original ABE ciphertext into an ElGamal-style ciphertext using a transformation key without revealing the plaintext message to the edge node. Our approach is efficient and suitable for mobile devices. Performance evaluation demonstrates the system can balance computation and power consumption over an extended period, effectively addressing challenges in data sharing.

The collaboration between aerial and ground computing is effective for supporting computation-intensive and latency-critical applications, especially in the infrastructure-less scenarios. However, the main challenge lies in task allocation, as well as optimizing the trajectories to complete tasks fast. This paper investigates a collaborative computing network where heterogeneous unmanned aerial vehicles (UAVs) and a ground base station work together to provide computation services for smart mobile devices on the ground. An optimization framework to minimize the system processing delay is established by jointly designing computing UAV deployment, computation task allocation, and relay UAVs’ trajectories. However, the formulated problem is a non-convex mixed integer non-linear programming problem. We reformulate it into a tractable one and further divide it into three sub-problems, i.e., computing UAV deployment, computation task allocation, and UAVs’ trajectories scheduling. We further propose a K-Medoids-based alternate iterative algorithm, which uses the K-Medoids clustering algorithm to determine UAV deployment and optimize task allocation and relaying UAV trajectories iteratively with successive convex approximation (SCA). Simulation results show that the proposed approach reduces system processing delay compared to other benchmarks.

Recent advances in multimodal large language models (MLLMs) have shown remarkable capabilitiesin integrating vision and language for complex reasoning. While most existing benchmarks evaluate models under offline settings with a fixed set of pre-recorded inputs, we introduce OST-Bench, a benchmark designed to evaluate Online Spatio-Temporal understanding from the perspective of an agent actively exploring a scene. The “Online” aspect emphasizes the need to process and reason over incrementally acquired observations, while the “Spatio-Temporal” component requires integrating current visual inputs with historical memory to support dynamic spatial reasoning. OST-Bench better reflects the challenges of real-world embodied perception. Built on an efficient data collection pipeline, OST-Bench consists of 1.4k scenes and 10k question-answer pairs collected from ScanNet, Matterport3D, and ARKitScenes. We evaluate several leading MLLMs on OST-Bench and observe that they fall short on tasks requiring complex spatio-temporal reasoning. Under the online setting, their accuracy declines as the exploration horizon extends and the memory grows. Through further experimental analysis, we identify common error patterns across models and find that both complex clue-based spatial reasoning demands and long-term memory retrieval requirements significantly drop model performance along two separate axes, highlighting the core challenges that must be addressed to improve online embodied reasoning. To foster further research and development in the field, our codes, dataset, and benchmark are available at https://github.com/InternRobotics/OST-Bench.

DDoS (Distributed Denial of Service) attacks are increasingly becoming a major threat in the field of cybersecurity. They overwhelm target servers by sending large-scale requests from multiple locations, causing the servers to become unresponsive. The distributed nature of DDoS attacks also makes detection and defense even more challenging. As the damage caused by such attacks grows, the development of efficient detection and mitigation mechanisms has become an urgent priority. While traditional machine learning methods are useful, they still require manual feature extraction, which not only involves significant human intervention, but also is time-consuming. In contrast, deep learning offers an automated approach to feature extraction and can learn more abstract patterns, which leads to improved detection performance. Therefore, this paper reviews and analyzes existing deep learning methods for DDoS attack detection. We provide a comprehensive analysis of the various types of DDoS attacks and explore different deep learning models employed for attack detection. Additionally, we explore techniques such as federated learning that can be integrated with deep learning, and analyze their related literature in DDoS attack detection. Finally, we specify future research directions on DDoS attack detection using deep learning.

ABSTRACT In this paper, we investigate the computation offloading and resource allocation strategy of the coexistence and synergy between fog computing and cloud computing in heterogeneous networks. Consider that the reported schemes have prohibitive complexity when achieving the optimal computation offloading strategy in cloud‐fog cooperative heterogeneous networks, an improved genetic algorithm (IGA) is proposed in this paper, which can maintain a low computation complexity while obtaining the optimal solution. In the IGA algorithm, we propose to use a penalty function to express the constraint conditions of the optimisation problem and use a non‐uniform mutation operator to accelerate the convergence speed. Besides, an improved method of parameter self‐adaptation and a perturbation method of mutation probability based on population fitness standard deviation are proposed to optimise the genetic algorithm. The numerical results show that the proposed genetic algorithm can obtain a lower average cost of the system while keeping a smaller computational cost.

In the realm of computer vision and robotics, embodied agents are expected to explore their environment and carry out human instructions. This necessitates the ability to fully understand 3D scenes given their first-person observations and contextualize them into language for interaction. However, traditional research focuses more on scene-level input and output setups from a global view. To address the gap, we introduce EmbodiedScan, a multi-modal, ego-centric 3D perception dataset and benchmark for holistic 3D scene understanding. It encompasses over 5k scans encapsulating 1M ego-centric RGB-D views, 1M language prompts, 160k 3D-oriented boxes spanning over 760 categories, some of which partially align with LVIS, and dense semantic occupancy with 80 common categories. Building upon this database, we introduce a baseline framework named Embodied Perceptron. It is capable of processing an arbitrary number of multi-modal inputs and demonstrates remarkable 3D perception capabilities, both within the two series of benchmarks we set up, i.e., fundamental 3D perception tasks and language-grounded tasks, and in the wild.

With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress. However, limited by existing datasets, previous works mainly focus on understanding object properties or inter-object spatial relationships in a 3D scene. To tackle this problem, this paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan. It is constructed based on a top-down logic, from region to object level, from a single target to inter-target relationships, covering holistic aspects of spatial and attribute understanding. The overall pipeline incorporates powerful VLMs via carefully designed prompts to initialize the annotations efficiently and further involve humans' correction in the loop to ensure the annotations are natural, correct, and comprehensive. Built upon existing 3D scanning data, the resulting multi-modal 3D dataset encompasses 1.4M meta-annotated captions on 109k objects and 7.7k regions as well as over 3.04M diverse samples for 3D visual grounding and question-answering benchmarks. We evaluate representative baselines on our benchmarks, analyze their capabilities in different aspects, and showcase the key problems to be addressed in the future. Furthermore, we use this high-quality dataset to train state-of-the-art 3D visual grounding and LLMs and obtain remarkable performance improvement both on existing benchmarks and in-the-wild evaluation.

Being data-driven is one of the most iconic properties of deep learning algorithms. The birth of ImageNet [24] drives a remarkable trend of ‘learning from large-scale data’ in computer vision. Pretraining on ImageNet to obtain rich universal representations has been manifested to benefit various 2D visual tasks, and becomes a standard in 2D vision. However, due to the laborious collection of real-world 3D data, there is yet no generic dataset serving as a counterpart of ImageNet in 3D vision, thus how such a dataset can impact the 3D community is unraveled. To remedy this defect, we introduce MVImgNet, a large-scale dataset of multi-view images, which is highly convenient to gain by shooting videos of real-world objects in human daily life. It contains 6.5 million frames from 219,188 videos crossing objects from 238 classes, with rich annotations of object masks, camera parameters, and point clouds. The multi-view attribute endows our dataset with 3D-aware signals, making it a soft bridge between 2D and 3D vision. We conduct pilot studies for probing the potential of MVImgNet on a variety of 3D and 2D visual tasks, including radiance field reconstruction, multi-view stereo, and view-consistent image understanding, where MVImgNet demonstrates promising performance, remaining lots of possibilities for future explorations. Besides, via dense reconstruction on MVImgNet, a 3D object point cloud dataset is derived, called MVPNet, covering 87,200 samples from 150 categories, with the class label on each point cloud. Experiments show that MVP-Net can benefit the real-world 3D object classification while posing new challenges to point cloud understanding. MVImgNet and MVPNet will be public, hoping to inspire the broader vision community.

Excellent performance has been achieved on instance segmentation but the quality on the boundary area remains unsatisfactory, which leads to a rising attention on boundary refinement. For practical use, an ideal post-processing refinement scheme are required to be accurate, generic and efficient. However, most of existing approaches propose pixel-wise refinement, which either introduce a massive computation cost or design specifically for different backbone models. Contour-based models are efficient and generic to be incorporated with any existing segmentation methods, but they often generate over-smoothed contour and tend to fail on corner areas. In this paper, we propose an efficient contour-based boundary refinement approach, named SharpContour, to tackle the segmentation of boundary area. We design a novel contour evolution process together with an Instance-aware Point Classifier. Our method deforms the contour iteratively by updating offsets in a discrete manner. Differing from existing contour evolution methods, SharpContour estimates each offset more independently so that it predicts much sharper and accurate contours. Notably, our method is generic to seamlessly work with diverse existing models with a small computational cost. Experiments show that SharpContour achieves competitive gains whilst preserving high efficiency.

Environmental monitoring is one of the fundamental applications of the Internet of Things (IoT), and caching in energy harvesting-aided IoT is a promising solution to handle the energy charging of the IoT nodes in the vast monitoring area. However, the growth of the requirements for monitoring area and accuracy brings huge infrastructure costs to the network operators (OP), especially for the multiple OPs scenario. In this article, we utilize wireless virtualization to enable the IoT node sharing between multiple OPs in cache-enabled energy harvesting-aided IoT, so as to improve the utility of the OPs. A Stackelberg game is formulated to jointly handle the IoT node sharing and energy transmission incentives between OPs and energy transmitters. Then, the knapsack problem, convex and linear programming are utilized to approximate the game through problem transformation and derivations. On the basis of that, an alternative direction algorithm is proposed to solve the equilibrium efficiently. The simulation results verify the advantages of the proposed algorithm in utility improvement and fairness maintenance between multiple OPs.