Machine learning (ML) techniques have significantly enhanced decision support systems to render them more accurate, efficient, and faster. ML classifiers in securing networks, on the other hand, face a disproportionate risk from the sophisticated adversarial attacks compared to other areas, such as spam filtering, intrusion, and virus detection, and this introduces a continuous competition between malicious users and preventers. Attackers test ML models with inputs that have been specifically crafted to evade these models and obtain inaccurate forecasts. This paper presents a comprehensive review of attack and defensive techniques in ML-based NIDSs. It highlights the current serious challenges that the systems face in preserving robustness against adversarial attacks. Based on our analysis, with respect to their current superior performance and robustness, ML-based NIDS require urgent attention to develop more robust techniques to withstand such attacks. Finally, we discuss the current existing approaches in generating adversarial attacks and reveal the limitations of current defensive approaches. In this paper, the most recent advancements, such as hybrid defensive techniques that integrate multiple strategies to prevent adversarial attacks in NIDS, have highlighted the ongoing challenges.
1 November 2022 in Indonesian Journal of Electrical Engineering and Computer Science
Number theory research unit (NTRU) become the most important of securi-ty in recent, with its modification of their variant, this paper search of the literature and A number of studies have examined the in public key variant development and security. In general, prior work is limited to a subset of public key increasing complexity but the benefits of speed up encryption/ decryption have not been fully established. So this paper will be the basis for those who want to develop and find proposed solutions for new studies of the NTRU algorithm. This paper aims to develop a framework to investigate the NTRU development, had been discovered that despite its development over the years and even its acceptance in round three of post quantum cryptograph, then found that limit study in the new scope of quantum facility and the ability of hybrid of new study.
In the current digitalized world, the notion of cybersecurity has become crucial in everyday life, and the issue of privacy takes the leading role in the technological agenda of the global community. One such social engineering attack that is currently prevalent is phishing, which is a common technique used by cybercriminals to intercept sensitive data. Despite the presence of certain limitations which can restrict its usefulness, machine learning (ML) has evolved into an interesting approach to identify phishing attacks. Cloud ML is an effective solution that uses cloud computing solutions to create, train, and deploy models that provide a faster and more accurate result as well as support large datasets. This paper compares the ensemble method of Amazon SageMaker’s AutoML tool, AutoGluon, with the linear method of SageMaker’s linear learner algorithm for website phishing detection. Key factors examined include training techniques, training time, batch transform time, endpoint prediction time, and model accuracy. The results demonstrate that while AutoGluon outperforms linear learner in terms of accuracy and prediction speed, linear learner is faster in training and batch transform processes.
Neural architecture search (NAS) automates network design by exploring candidate architectures. Although existing methods achieve competitive results, choosing suitable search heuristics as search conditions change remains challenging. This paper proposes a State-Aware Reinforcement Learning Hyper-Heuristic for Neural Architecture Search (SARL-HHNAS), which explores the heuristic space to indirectly search the architecture space. A Double Deep Q-Network (Double DQN) controller selects among six low-level heuristics for architecture modification. These heuristics support local refinement, incumbent-guided modification, broader exploration, and the restoration of architecture diversity. Its 13-dimensional state describes search progress, stagnation, diversity, remaining budget, architecture complexity, and heuristic utility. A temperature-based acceptance mechanism determines whether a candidate replaces the current solution. A cost-aware objective combines validation accuracy with normalized parameter count and floating-point operations. Experiments compare SARL-HHNAS with six architecture-search and hyper-heuristic baselines using the NATS-Bench topology search space on CIFAR-10, CIFAR-100, and ImageNet16-120. The evaluation covers 630 runs under budgets of 100, 250, and 500 architecture evaluations. Search decisions use validation information, while test accuracy is queried only for the selected architecture. At 250 evaluations, mean test accuracies reach 94.37%, 73.51%, and 46.80%, respectively. Eight of 54 paired Search-AUC comparisons favor SARL-HHNAS over Random Search or REINFORCE after Holm correction within each dataset–budget condition. On CIFAR-100 at 100 evaluations, increasing the complexity penalty from zero to 0.10 reduces mean parameter count and floating-point operations by 61.6% and 63.3%, respectively. These findings support competitive architecture search under limited evaluation budgets and an adjustable accuracy–complexity trade-off.