A comparative study of adversarial training methods for neural models of source code

Li, Zhen; Huang, Xiang; Li, Yang–Rui; Chen, Guenevere

doi:10.1016/j.future.2022.12.030

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the adversarial attacks against deep learning models of code should be mentioned. The comparative analysis of the adversarial attacks against deep learning models of code is given in [9].…”

Section: Comparison With Other Literature Reviewsmentioning

confidence: 99%

An Analytical Review of the Source Code Models for Exploit Analysis

Fedorchenko,

Novikova,

Fedorchenko

et al. 2023

Information

View full text Add to dashboard Cite

Currently, enhancing the efficiency of vulnerability detection and assessment remains relevant. We investigate a new approach for the detection of vulnerabilities that can be used in cyber attacks and assess their severity for further effective responses based on an analysis of exploit source codes and real-time detection of features of their implementation. The key element of this approach is an exploit source code model. In this paper, to specify the model, we systematically analyze existing source code models, approaches to source code analysis in general, and exploits in particular in order to examine their advantages, applications, and challenges. Finally, we provide an initial specification of the proposed source code model.

show abstract

Section: Comparison With Other Literature Reviewsmentioning

confidence: 99%

An Analytical Review of the Source Code Models for Exploit Analysis

Fedorchenko,

Novikova,

Fedorchenko

et al. 2023

Information

View full text Add to dashboard Cite

show abstract

“…Code generation is an essential generation task in the field of natural language processing (NLP) and software engineering [20,24,7,8,18,35,36,16], which deals with automatically generating a piece of executable code from NL utterances. In recent years, a series of Seq2Tree models have made remarkable achievements for code generation [2,38,1,39,27,29,28,33,11,14,43,21].…”

Section: Introductionmentioning

confidence: 99%

Antecedent Predictions Are More Important Than You Think: An Effective Method for Tree-Based Code Generation

Dong,

Li,

Jiang

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Code generation focuses on automatically converting natural language (NL) utterances into code snippets. Sequence-to-tree (Seq2Tree) approaches are proposed for code generation with the aim of ensuring grammatical correctness of the generated code. These approaches generate subsequent Abstract Syntax Tree (AST) nodes based on the preceding predictions of AST nodes. However, existing Seq2Tree approaches tend to treat both antecedent predictions and subsequent predictions equally, which poses a challenge for models to produce accurate subsequent predictions if the antecedent predictions are incorrect under the constraints of the AST. Given this challenge, it is necessary to pay more attention to antecedent predictions compared to subsequent predictions. To this end, this paper proposes a novel and effective method, named Antecedent Prioritized (AP) Loss, which prioritizes antecedent predictions by leveraging the position information of the generated AST nodes. We design an AST-to-Vector (AST2Vec) method that maps AST node positions to two-dimensional vectors, thereby modeling the position information of AST nodes. To evaluate the effectiveness of our proposed loss, we implement and train an Antecedent Prioritized Tree-based code generation model called APT. Experiments on four benchmark datasets demonstrate that with better antecedent predictions and accompanying subsequent predictions, APT achieves significant improvements, indicating the superiority and generality of our proposed method.

show abstract

Membrane separation of antibiotics predicted with the back propagation neural network

Zhou

et al. 2023

Journal of Environmental Science and Health, Part A

View full text Add to dashboard Cite

A comparative study of adversarial training methods for neural models of source code

Cited by 4 publications

References 18 publications

An Analytical Review of the Source Code Models for Exploit Analysis

An Analytical Review of the Source Code Models for Exploit Analysis

Antecedent Predictions Are More Important Than You Think: An Effective Method for Tree-Based Code Generation

Membrane separation of antibiotics predicted with the back propagation neural network

Contact Info

Product

Resources

About