The rapid expansion of mobile edge computing (MEC), driven by the escalating data volume and the demand for minimal network latency, underscores the need for efficient data processing. To address the growing complexity of neural networks and applications, segmentation into smaller components (e.g., neural network layers, subnetworks, and subtasks) for parallel computation across diverse nodes is common. However, effective data transmission between these segments necessitates optimized task scheduling among edge servers. Many platforms leverage container-based operating system-level virtualization to enhance edge computing efficiency, leveraging container image layers to cut storage and transmission costs. However, previous research predominantly emphasizes task scheduling, overlooking runtime environment preparation on edge servers and potential collaboration among edge nodes. This article introduces an innovative approach that adeptly manages task data and image layer dependencies collaboratively. It formulates an NP-hard problem: minimizing total computation completion time by jointly determining downlink transmission rate allocation, task-offloading strategies, and layer-loading schemes, allowing for thoughtful decoupling and iterative refinement. The Gray Wolf Optimizer and cellular automata are introduced for dynamic task scheduling, complemented by a low-complexity algorithm inspired by the Nawas-Enscore-Ham method. For layer downloading, this article explores a partial-layer loading policy, considering storage constraints, and establishes a full-layer loading strategy with the Peer-to-Peer mechanism, significantly reducing computational complexity. Rigorous experimental results underscore the remarkable efficacy of these approaches in curtailing total computation completion time, positioning them as benchmarks for comparison against alternative solutions.

Although numerous state-of-the-art deep neural networks have recently been proposed for malware classification, effectively detecting malware on a large-scale sample set and identifying zero-day or new malware variants still pose significant challenges. To address this issue, a deep hashing-based malware classification model is designed for malware identification, including two parts: 1) ResNet50-based deep hashing for malware retrieval and 2) voting-based malware classification. Specifically, multiple deep hashing models are developed by extracting the high-layer outputs (feature maps) from the ResNet50 trained with malware gray-scale images in the first part. In this case, to maximize the Hamming distance or dissimilarity among hash values computed with malware samples under different families, a ResNet50-based deep polarized network (RNDPN) is designed to return $Top\;K$ similar samples. In the second part, we propose a majority-voting and a Hamming-distance-based voting for malware identification according to the retrieved results. The experiment results show that RNDPN outperforms the other six deep hashing models with 97.54% mean average precision (mAP) for malware retrieval when only 40 similar examples are retrieved, where the best results for all deep hashing models are observed with 48-bits hashing code length. Furthermore, the Hamming distance-based voting method implemented with RNDPN demonstrates unparalleled performance in malware classification compared to other models. Notably, it achieves exceptional results in two key aspects: 1) malware classification accuracy with an impressive accuracy rate of 96.5% and 2) the identification of new or zero-day malware with a commendable accuracy of 85.7%.

Deep-learning-based malware-detection models are threatened by adversarial attacks. This paper designs a robust and secure convolutional neural network (CNN) for malware classification. First, three CNNs with different pooling layers, including global average pooling (GAP), global max pooling (GMP), and spatial pyramid pooling (SPP), are proposed. Second, we designed an executable adversarial attack to construct adversarial malware by changing the meaningless and unimportant segments within the Portable Executable (PE) header file. Finally, to consolidate the GMP-based CNN, a header-aware loss algorithm based on the attention mechanism is proposed to defend the executive adversarial attack. The experiments showed that the GMP-based CNN achieved better performance in malware detection than other CNNs with around 98.61% accuracy. However, all CNNs were vulnerable to the executable adversarial attack and a fast gradient-based attack with a 46.34% and 34.65% accuracy decline on average, respectively. Meanwhile, the improved header-aware CNN achieved the best performance with an evasion ratio of less than 5.0%.