Search

Federated Learning (FL) offers collaborative machine learning without data exposure, but challenges arise in the mobile edge network (MEC) environment due to limited resources and dynamic conditions. This paper presents a Digital Twin (DT)-assisted FL platform for MEC networks and introduces a novel multi-FL service framework to address resource dynamics and mobile users. We leverage DT models to optimize device scheduling and MEC resource allocation, aiming to maximize utility across FL services. Our work includes heuristic and constant approximation algorithms for offline multi-FL service scenarios and we also investigate an online setting of our solution with dynamic bandwidth and moving client conditions. To adapt to changing network conditions, we utilize historical bandwidth data in DTs and implement a deep reinforcement learning algorithm, Ra_DDPG, for automatic bandwidth allocation. Evaluation results demonstrate a significant 49.8% increase in system utility compared to a benchmark algorithm, showcasing the effectiveness of our approach.

Federated learning is a powerful technique that enables collaborative learning among different clients. Prototype-based federated learning is a specific approach that improves the performance of local models by integrating class prototypes. However, prototype-based federated learning faces several challenges, such as prototype redundancy and prototype failure, which can limit its accuracy. In addition, it is also susceptible to poisoning attacks and server malfunction, which can degrade the quality of prototypes. To address these issues, we propose FedRFQ, a prototype-based federated learning approach that aims to reduce redundancy, minimize failure, and improve quality. FedRFQ leverages the SoftPool mechanism with prototype-based federated learning, which effectively mitigates prototype redundancy and prototype failure on Non-IID data. Moreover, we introduce the BFT-detect algorithm, a BFT detectable aggregation algorithm, to ensure the security of FedRFQ against poisoning attacks and server malfunction. Finally, we conducted experiments on three different datasets, namely MNIST, FEMNIST, and CIFAR-10. The results demonstrate that FedRFQ outperforms existing baselines in terms of accuracy when handling Non-IID data.

Deep learning is a thriving field currently stuffed with many practical applications and active research topics. It allows computers to learn from experience and to understand the world in terms of a hierarchy of concepts, with each being defined through its relations to simpler concepts. Relying on the strong capabilities of deep learning, we propose a convolutional generative adversarial network-based (Conv-GAN) framework titled MalFox, targeting adversarial malware example generation against third-party black-box malware detectors. Motivated by the rival game between malware authors and malware detectors, MalFox adopts a confrontational approach to produce perturbation paths, with each formed by up to three methods (namely Obfusmal, Stealmal, and Hollowmal) to generate adversarial malware examples. To demonstrate the effectiveness of MalFox, we collect a large dataset consisting of both malware and benignware programs, and investigate the performance of MalFox in terms of accuracy, detection rate, and evasive rate of the generated adversarial malware examples. Our evaluation indicates that the accuracy can be as high as 99.0% which significantly outperforms the other 12 well-known learning models. Furthermore, the detection rate is dramatically decreased by 56.8% on average, and the average evasive rate is noticeably improved by up to 56.2%.

With the increment of data sets and models sizes, distributed deep learning has been proposed to accelerate training and improve the accuracy of DNN models. The parameter server framework is a popular collaborative architecture for data-parallel training, which works well for homogeneous environments by properly aggregating the computation/communication capabilities of different workers. However, in heterogeneous environments, the resources of different workers vary a lot. Some stragglers may seriously limit the whole speed, which impacts the overall training process. In this paper, we propose an adaptive multi-stage distributed deep learning training framework, named ASHL, for heterogeneous environments. First, a profiling scheme is proposed to capture the capabilities of each worker to reasonably plan the training and communication tasks on each worker, and lay the foundation for the formal training. Second, a hybrid-mode training scheme (i.e., coarse-grained and fined-grained training) is proposed to balance the model accuracy and training speed. The coarse-grained training scheme (named AHL) adopts an asynchronous communication strategy, which involves less frequent communications. Its main goal is to make the model quickly converge to a certain level. The fine-grained training stage (named SHL) uses a semi-asynchronous communication strategy and adopts a high communication frequency. Its main goal is to improve the model convergence effect. Finally, a compression-based communication scheme is proposed to further increase the communication efficiency of the training process. Our experimental results show that ASHL reduces the overall training time by more than 35% to converge to the same degree and has better generalization ability compared with state-of-the-art schemes like ADSP.

Non-volatile processors are proposed for ambient energy harvesting systems to enable accumulative computing across power failures. They employ nonvolatile memory for processor status backup before power outage and resume the system after power recovers. A straightforward backup policy is to back up all volatile data in processors, but it induces high backup cost. In this paper, we focus on branch predictor, an important component in processor, and propose efficient backup schemes to reduce backup cost while maintaining its prediction ability. We first analyze the modules in both traditional and artificial intelligence (AI) assisted designs of branch predictor, and accordingly propose three backup mechanisms pertaining to saturation-driven, locality-driven and maturity-driven backup. On the basis of these mechanisms, adaptive backup branch predictors are designed. Evaluation shows that, with traditional Tournament architecture, the proposed design achieves 15.9% and 54.1% energy reduction when compared with no-backup and all-backup strategy. For AI assisted branch predictor, the proposed design achieves 27.5% and 82.2% energy saving.

Nowadays, volumetric videos have emerged as an attractive multimedia application providing highly immersive watching experiences since viewers could adjust their viewports at 6 degrees-of-freedom. However, the point cloud frames composing the video are prohibitively large, and effective compression techniques should be developed. There are two classes of compression methods. One suggests exploiting the conventional video codecs (2D-based methods) and the other proposes to compress the points in 3D space directly (3D-based methods). Though the 3D-based methods feature fast coding speeds, their compression ratios are low since the failure of leveraging inter-frame redundancy. To resolve this problem, we design a patch-wise compression framework working in the 3D space. Specifically, we search rigid moves of patches via the iterative closest point algorithm and construct a common geometric structure, which is followed by color compensation. We implement our decoder on a GPU platform so that real-time decoding and rendering are realized. We compare our method with GROOT, the state-of-the-art 3D-based compression method, and it reduces the bitrate by up to 5.98$\times$×. Moreover, by trimming invisible content, our scheme achieves comparable bandwidth demand of V-PCC, the representative 2D-based method, in FoV-adaptive streaming.

Decentralized Storage Networks (DSNs) can gather storage resources from mutually untrusted providers and form worldwide decentralized file systems. Compared to traditional storage networks, DSNs are built on top of blockchains, which can incentivize service providers and ensure strong security. However, existing DSNs face two major challenges. First, deduplication can only be achieved at the directory-level. Missing file-level deduplication leads to unavoidable extra storage and bandwidth cost. Second, current DSNs realize file indexing by storing extra metadata while blockchain ledgers are not fully exploited. To overcome these problems, we propose FileDAG, a DSN built on DAG-based blockchain to support file-level deduplication in storing multi-versioned files. When updating files, we adopt an increment generation method to calculate and store only the increments instead of the entire updated files. Besides, we introduce a two-layer DAG-based blockchain ledger, by which FileDAG can provide flexible and storage-saving file indexing by directly using the blockchain database without incurring extra storage overhead. We implement FileDAG and evaluate its performance with extensive experiments. The results demonstrate that FileDAG outperforms the state-of-the-art industrial DSNs considering storage cost and latency.

Graphs are widely employed in complex system modeling, VLSI design, and social analysis. Mining cohesive subgraphs is a fundamental problem in graph analysis, while implementing cohesive subgraphs requires analysts to not only ensure cohesiveness but also consider the computational intractability. Among a variety of diverse cohesive structures, $k$k-truss exhibits a perfect trade-off between structure tightness and computational efficiency. In a $k$k-truss, each edge is present in at least $k-2$k-2 triangles. This study aims to contribute to this growing area of truss maintenance in fully dynamic graphs by avoiding expensive re-computation. Specifically, we consider the challenging scenario of batch processing of edge and vertex insertion/deletion and propose efficient algorithms that can maintain the trusses by only searching a very small range of affected edges. Also, our algorithms allow parallel implementations to further improve the efficiency of maintenance. Extensive experiments on both real-world static and temporal graphs illustrate the efficiency and scalability of our algorithms.