As Deep Neural Networks (DNNs) are evolving in complexity to meet the demands of novel applications, a single device becomes insufficient for training, leading to the emergence of distributed DNN training. However, this evolution exposes a gap in research surrounding security vulnerabilities on model poisoning attacks, especially in model parallel setups, an area that has been scarcely studied. To bridge this gap, we introduce Patronus, an approach that counters model poisoning attacks in distributed DNN training, accommodating both data and model parallelism. With the employment of Loss-aware Credit Evaluation, Patronus scores each participating client. Based on the continuously updated credit, malicious clients are isolated and detected after multiple epochs by Shuffling-based Isolation Mechanism. Additionally, the training system is reinforced by Byzantine Fault-tolerant Aggregation to minimize malicious client impacts. Comprehensive experiments confirm Patronus's superior reliable and efficient performance over the existing methods under attack scenarios.

Recently, blockchain-based covert communication has gained momentum, for the decentralization, anonymity, and immutability feature of blockchain. Nevertheless, some challenges impair its security and efficiency. Most schemes have a weak generalization ability, and can merely be applied to a specific blockchain platform. Storage-based covert transmission schemes usually have limited space for data embedding, affecting their Information delivery efficiency. Besides, static data sifting rules raise the risk of information leakage. In this paper, we design DLCCB(Dynamic Labeling based Covert Communication on Blockchain). We first split the information to be delivered into several pieces and utilize the destination address of each transaction to embed them. Then a dynamic labeling method is proposed for updating sifting rules without extra negotiation between sender and receiver. Besides, we design two kinds of sifting algorithms, namely online and offline sifting algorithm. We perform our solution on Ropsten, a test net of Ethereum. The experiment result verifies the feasibility of our scheme.

Bitcoin and Ethereum have always been the two major heavyweight infrastructures in the blockchain space. However, Low throughput and high cost hinder their further development. Recently, some emerging public blockchains have become popular. They all have efficient transaction confirmation mechanism and cheap interaction costs. However, the advantages are actually a sacrifice of decentralization. As we all know, decentralization is an essential feature of blockchain. Therefore, it requires the conceiving of up-to-date metrics of decentralization measurement. However, there is little research on the degree of decentralization of these emerging public blockchains in the past. This paper studies nine popular public chains such as Binance Smart Chain, Cardano, and Avalanche. Since these public chains mostly use the consensus mechanism of POS variants, the distribution of governance token balances on the chain can reflect the decentralization of the blockchain. Hence, We evaluate the distribution of the token balance of those public blockchains to indicate their decentralization degree. Two kinds of indicators are adopted and redesigned: information entropy and Gini coefficients. Among the nine public blockchains we selected, Cardano, Tron and Polkadot have a higher degree of decentralization, while Elrond and Binance Smart Chain have a lower degree of decentralization. We think our work will be helpful for future research on the degree of blockchain decentralization.

Intensive video transcoding and data transmission are the most crucial tasks for large-scale Crowd-sourced Livecast Services (CLS). However, there exists no versatile model for joint optimization of computing resources (e.g., CPU) and transmission resources (e.g., bandwidth) in CLS systems, making maintaining the balance between saving resources and improving user viewing experience very challenging. In this paper, we first propose a novel universal model, called Augmented Graph Model (AGM), which converts the above joint optimization into a multi-hop routing problem. This model provides a new perspective for the analysis of resource allocation in CLS, as well as opens new avenues for problem-solving. Further, we design a decentralized Networked Multi-Agent Reinforcement Learning (MARL) approach and propose an actor-critic algorithm, allowing network nodes (agents) to distributively solve the multi-hop routing problem using AGM in a fully cooperative manner. By leveraging the computing resource of massive nodes efficiently, this approach has good scalability and can be employed in large-scale CLS. To the best of our knowledge, this work is the first attempt to apply networked MARL on CLS. Finally, we use the centralized (single-agent) RL algorithm as a benchmark to evaluate the numerical performance of our solution in a large-scale simulation. Additionally, experimental results based on a prototype system show that our solution is superior in saving resources and service performance to two alternative state-of-the-art solutions.

Nowadays, amateur broadcasters can massively generate video contents and stream them across the Internet. For this reason, crowdsourced livecast services (CLS) are attracting millions of users around the world. To provide a smooth and high-quality playback experience to viewers with diversified device configurations in dynamic network conditions, CLS providers have to find a way to deploy cost-effective transcoding operations by distributing the computation-intensive workload among Cloud, Edge, and Crowd. In addition, it is necessary to control transcoded streams from million broadcasters to worldwide viewers. To address these challenges, we propose a novel stochastic approach that jointly optimizes the usage of transmission resources (e.g., bandwidth), and transcoding resources (e.g., CPU) in CLS systems that leverage the cooperation of Cloud, Edge, and Crowd technologies. In particular, we first design an augmented queue structure that can jointly capture the dynamic features of data transmission and online transcoding, based on the virtual queue technology. Then, we formulate a joint resource allocation problem, using stochastic optimization arguments, and devise an Accelerated Gradient Optimization (AGO) algorithm to solve the optimization problem in a scalable way. Moreover, we provide four main theoretical results that characterize the algorithm’s steady-state queue-length, optimality, and fast-convergence. By conducting both numerical simulations and system-level evaluations based on our prototype, we demonstrate that our solution provides lower system costs and higher QoE performance against state-of-the-art solutions.

By exploiting the massive data generated from the numerous interconnected machines and control systems, industrial Internet-of-Things (IIoT) provides unprecedented opportunities for facilitating the intelligence and smartness of manufacturing. Timely processing the large-scaled IIoT data by the conventional computation framework, such as Cloud computing, however, is nontrivial due to its costly resource usage, intolerable delay, and unbearable backbone pressures. By leveraging the idle resources of smart objects at the edge, mobile device cloud (MDC) becomes promising for the IIoT data analysis, thanks to the flexible resource provision and nearby task offloading. However, MDC workers are mostly human-carried devices with large scale, high dynamic resource provision, and untruthful behaviors, which pose significant challenges on MDC task allocation. In this article, we propose a blockchain-based decentralized and truthful framework for MDC (BC-MDC). BC-MDC enables the decentralization and prevents dishonesty by incorporating a plasma-based blockchain into the MDC. We design four smart contracts for distributedly managing the worker registration, task posting/allocation, rewarding, and penalizing. Furthermore, MDC task allocation is formulated as a stochastic optimization problem that jointly minimizes the long-term processing cost and risk of task failing. We also design a truthful reward/penalty algorithm that stimulates workers to provide resources and enforce them to keep the promise as well. Collaborated by the extensive simulation tests, we show how our proposed scheme achieves low cost on usage and high truthfulness and outperforms state-of-the-art solutions.