English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

One of the most significant challenges in the field of software code auditingis the presence of vulnerabilities in software source code. Every year, moreand more software flaws are discovered, either internally in proprietary codeor publicly disclosed. These flaws are highly likely to be exploited and canlead to system compromise, data leakage, or denial of service. To create alarge-scale machine learning system for function level vulnerabilityidentification, we utilized a sizable dataset of C and C++ open-source codecontaining millions of functions with potential buffer overflow exploits. Wehave developed an efficient and scalable vulnerability detection method basedon neural network models that learn features extracted from the source codes.The source code is first converted into an intermediate representation toremove unnecessary components and shorten dependencies. We maintain thesemantic and syntactic information using state of the art word embeddingalgorithms such as GloVe and fastText. The embedded vectors are subsequentlyfed into neural networks such as LSTM, BiLSTM, LSTM Autoencoder, word2vec,BERT, and GPT2 to classify the possible vulnerabilities. We maintain thesemantic and syntactic information using state of the art word embeddingalgorithms such as GloVe and fastText. The embedded vectors are subsequentlyfed into neural networks such as LSTM, BiLSTM, LSTM Autoencoder, word2vec,BERT, and GPT2 to classify the possible vulnerabilities. Furthermore, we haveproposed a neural network model that can overcome issues associated withtraditional neural networks. We have used evaluation metrics such as F1 score,precision, recall, accuracy, and total execution time to measure theperformance. We have conducted a comparative analysis between results derivedfrom features containing a minimal text representation and semantic andsyntactic information.

Feature Engineering-Based Detection of Buffer Overflow Vulnerability in Source Code Using Neural Networks