Detecting software vulnerabilities is a vital component of cybersecurity, concentrating on identifying and remedying weaknesses or flaws in software that malicious actors could exploit. Improving Android security includes using robust software vulnerability detection processes to identify and mitigate possible threats. Leveraging advanced methods like dynamic and static analysis and machine learning (ML) approaches with fractals theories these models early scan Android apps for vulnerabilities. Effectual software vulnerability detection is critical to mitigate safety risks, security systems, and data from cyber-attacks. Android malware detection employing deep learning (DL) supports the control of neural networks (NNs) for identifying and mitigating malicious apps targeting the Android and Complex Systems platforms. DL approaches, namely recurrent neural networks (RNNs) and convolutional neural networks (CNNs) can be trained on massive datasets encompassing benign and malicious samples. This study develops a Hyperparameter Tuned Deep Learning Approach for Robust Software Vulnerability Detection (HPTDLA-RSVD) technique. The primary aim of the HPTDLA-RSVD technique is to ensure Android malware security using an optimal DL model. In the HPTDLA-RSVD technique, the min-max normalization method is applied to scale the input data into a uniform format. In addition, the HPTDLA-RSVD methodology employs ant lion fractal optimizer (ALO)-based feature selection (FS) named ALO-FS methodology for choosing better feature sets. Besides, the HPTDLA-RSVD technique uses a deep belief network (DBN) model for vulnerability detection and classification. Moreover, the slime mould algorithm (SMA) has been executed to boost the hyperparameter tuning process of the DBN approach. The experimental value of the HPTDLA-RSVD approach can be examined by deploying a benchmark database. The simulation outcomes implied that the HPTDLA-RSVD approach performs better than existing approaches with respect to distinct measures.
原文链接
分享
引用
