Malicious JavaScript Detection Based on Bidirectional LSTM Model

Song, Xuyan; Chen, Chen; Cui, Baojiang; Fu, Junsong

doi:10.3390/app10103440

Cited by 26 publications

(18 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xuyan Song et al [11] have presented new deep learning-based approaches for detecting malicious JavaScript. A programmer dependency graph (PDG) was developed and semantic slices were generated, which were easy to translate into vectors, so that semantic information could be extracted from JavaScript programs.…”

Section: Literature Reviewmentioning

confidence: 99%

Surgical Striking SQL Injection Attacks Using LSTM

N¹,

Ravishankar²,

B.³

et al. 2022

INDJCSE

View full text Add to dashboard Cite

When a software program or website employs SQL databases such as Oracle, SQL Server, or MySQL, a SQL injection attack is possible. Phishers utilize SQL injection attacks to infiltrate confidential corporate and personal information, increasing the risk of compromise. If a SQL injection exploit is successful, it can be used to read and alter database data (e.g., insert, update, or delete), perform database administration operations, retrieve the data of a database management system file, also issue commands to the operating system in some cases. In comparison to basic recurrent architectures, LSTM networks have been demonstrated to learn long-term dependencies more quickly and reduce gradient disappearance and explosion. Preventing SQL injection with the usage of LSTMs is the subject of the proposed research. The LSTM model has been suggested as a training method for tracing or filtering requests from an unauthentic user. The dataset trained is looking at records that include the sender and recipient information, as well as the success or failure of the transmission. If this transaction has repeatedly failed due to an on-going assault on the system, then this is a red flag. Then, this system will flag the transaction and block the user from accessing any of the system's resources. This model has been trained to increase security by creating a system that allows the user to authenticate a transaction.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Surgical Striking SQL Injection Attacks Using LSTM

N¹,

Ravishankar²,

B.³

et al. 2022

INDJCSE

View full text Add to dashboard Cite

show abstract

“…Song et al [34] proposed a bidirectional LSTM model to detect malicious JavaScript. In order to obtain semantic information from the code, the authors first constructed a program dependency graph (PDG) for generating semantic slices.…”

Section: Related Workmentioning

confidence: 99%

A Bidirectional LSTM Language Model for Code Evaluation and Repair

2021

View full text Add to dashboard Cite

Programming is a vital skill in computer science and engineering-related disciplines. However, developing source code is an error-prone task. Logical errors in code are particularly hard to identify for both students and professionals, and a single error is unexpected to end-users. At present, conventional compilers have difficulty identifying many of the errors (especially logical errors) that can occur in code. To mitigate this problem, we propose a language model for evaluating source codes using a bidirectional long short-term memory (BiLSTM) neural network. We trained the BiLSTM model with a large number of source codes with tuning various hyperparameters. We then used the model to evaluate incorrect code and assessed the model’s performance in three principal areas: source code error detection, suggestions for incorrect code repair, and erroneous code classification. Experimental results showed that the proposed BiLSTM model achieved 50.88% correctness in identifying errors and providing suggestions. Moreover, the model achieved an F-score of approximately 97%, outperforming other state-of-the-art models (recurrent neural networks (RNNs) and long short-term memory (LSTM)).

show abstract

“…Song et al 18 devised a deep learning‐based strategy for malicious JavaScript detection. Here, the extraction of semantic information was done from JavaScript programs.…”

Section: Motivationsmentioning

confidence: 99%

“…However, these dynamics may induce risks. In addition, the classical hateful script detection depends on expert knowledge, but for the specialist, it is erroneous 18 The dynamic feature and reliable JavaScript syntax maximize the complexity of analysis.…”

Section: Motivationsmentioning

confidence: 99%

See 1 more Smart Citation

Taylor–HHO algorithm: A hybrid optimization algorithm with deep long short‐term for malicious JavaScript detection

Alex

Rajkumar

2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

The security of information has become a major issue due to the development of network information-based technologies. The malicious script, like, JavaScript, is a major threat to computer networks in terms of network security. Here, the JavaScript allows the programmers not only to build advanced client-side interfaces for web-based applications but also utilized for carrying out attacks that may steal the user's confidential data.In addition, the attackers can easily induce malicious JavaScript into webpages for implanting attacks, like, phishing, spreading viruses, and Trojan horses. This paper devises a novel method, namely, Taylor-Harris Hawks Optimization driven deep long short-term memory (Taylor-HHO-based Deep LSTM) for malicious JavaScript discovery. Initially, the JavaScript is subjected as input to feature extraction in which certain features, such as time of execution, function calls, condition statement, break statement, loop statements, Boolean, number of lines, and number of O(N 2 ) loops, are extracted. The obtained features are fed to transformation, wherein log transformation is applied for data transformation. The obtained transformed features are fused using information gain and Deep LSTM. Furthermore, the proposed Taylor-HHO-based Deep LSTM is employed for discovering malevolent JavaScript. The proposed Taylor-HHO-based Deep LSTM provided enhanced performance with the highest accuracy of 0.955, minimal FPR of 0.059, and highest TPR of 0.967.

show abstract

Malicious JavaScript Detection Based on Bidirectional LSTM Model

Cited by 26 publications

References 34 publications

Surgical Striking SQL Injection Attacks Using LSTM

Surgical Striking SQL Injection Attacks Using LSTM

A Bidirectional LSTM Language Model for Code Evaluation and Repair

Taylor–HHO algorithm: A hybrid optimization algorithm with deep long short‐term for malicious JavaScript detection

Contact Info

Product

Resources

About