Machine-learning supported vulnerability detection in source code

Sonnekalb, Tim

doi:10.1145/3338906.3341466

Cited by 6 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Step 2: mapping code fragments to vectors. This step maps each code fragment into an appropriate form of representation (e.g., a sequence of tokens [23]- [25] or an abstract syntax tree [26], [29], [31], [33]), depending on the specifics of DL-based detectors. The code representation is then embedded into a vector by, for example, the concatenation of the vectors corresponding to the tokens.…”

Section: Resultsmentioning

confidence: 99%

“…Program Slice + Sequence + BGRU. It can be instantiated as the detector SySeVR [24], which is an extended version of VulDeePecker [23], is publicly [32] to capture more syntactic and structural information of program source code, by replacing its sequence-based representation with AST-based representation [33] and using the code2vec tool [47], [48] to aggregate multiple AST paths into a vector.…”

Section: Selecting Dl-based Detectorsmentioning

confidence: 99%

“…Rulebased detectors use expert-defined rules to detect vulnerabilities [56], including open-source tools [12]- [14], commercial tools [15], [16], and academic efforts [17], [18]. Machine learning-based detectors [33] aim to use models learned from expert-defined feature representations of vulnerabilities [19]- [22] or use DL models without requiring expertdefined feature representations [23]- [35]. DL-based detectors have received much attention recently.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Towards Making Deep Learning-based Vulnerability Detectors Robust

Li,

Tang,

Zou

et al. 2021

Preprint

View full text Add to dashboard Cite

Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention. In particular, deep learning-based vulnerability detectors, or DL-based detectors, are attractive because they do not need human experts to define features or patterns of vulnerabilities. However, such detectors' robustness is unclear. In this paper, we initiate the study in this aspect by demonstrating that DL-based detectors are not robust against simple code transformations, dubbed attacks in this paper, as these transformations may be leveraged for malicious purposes. As a first step towards making DL-based detectors robust against such attacks, we propose an innovative framework, dubbed ZigZag, which is centered at (i) decoupling feature learning and classifier learning and (ii) using a ZigZag-style strategy to iteratively refine them until they converge to robust features and robust classifiers. Experimental results show that the ZigZag framework can substantially improve the robustness of DL-based detectors.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Selecting Dl-based Detectorsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Towards Making Deep Learning-based Vulnerability Detectors Robust

Li,

Tang,

Zou

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Outras mecanismos tomam como base a análise do tráfego da rede para detectar vulnerabilidades, o que diminui os custos operacionais e simplifica o processo de detecc ¸ão, pois não requer acesso ao dispositivo físico [Jia et al 2017, Yi et al 2019, Huang et al 2020. No geral, tais mecanismos empregam técnicas que reconhecem padrões dos dispositivos e da rede por meio de algoritmos de aprendizado de máquina [Sonnekalb 2019, Chernis and Verma 2018, Huang et al 2020], e técnicas que mapeiam a rede por meio de grafos [Jia et al 2018, Fang et al 2019. Outros trabalhos seguem fontes de dados de níveis diferentes, como o de firmware e software.…”

Section: Trabalhos Relacionadosunclassified

“…Existem também mecanismos que tomam como base a análise do tráfego da rede para detectar vulnerabilidades, o que diminui os custos operacionais e simplifica o processo de detecc ¸ão, pois não requer acesso ao dispositivo físico [Huang et al 2020]. No geral, tais mecanismos empregam técnicas que reconhecem padrões dos dispositivos e da rede por meio de algoritmos de aprendizado de máquina [Sonnekalb 2019] e técnicas que mapeiam a rede de comunicac ¸ão por meio de grafos [Fang et al 2019]. Entretanto, os trabalhos que analisam o comportamento da rede, ignoram a detecc ¸ão de vulnerabilidades críticas como a detecc ¸ão da ausência de criptografia na comunicac ¸ão [Wang et al 2011, Rezaei andLiu 2019].…”

Section: Introduc ¸ãOunclassified

Um Método para Detecção de Vulnerabilidades Através da Análise do Tráfego de Rede IoT

Brezolin¹,

Prates²,

Vergütz³

et al. 2022

Anais Do XL Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2022)

View full text Add to dashboard Cite

A Internet das Coisas (do inglês, Internet of Things IoT) compreende dispositivos sem fio com recursos computacionais limitados. Ela é alvo de ataques que exploram vulnerabilidades como a transferência de dados sem criptografia. A detecção convencional de vulnerabilidades ocorre a partir de bases de dados que listam as vulnerabilidades mais comuns (do inglês, common vulnerabilities and exposures – CVEs). Porém, essas bases são limitadas a vulnerabilidades conhecidas, o que na maioria das vezes não é o caso para o contexto da IoT. Este trabalho propõe MANDRAKE, um método para detecção de Vulnerabilidades através da análise do tráfego de Rede IoT e técnicas de aprendizado de máquina. A avaliação de desempenho foi conduzida em um cenário de casa inteligente com duas bases de dados, uma gerada experimentalmente e outra disponibilizada na literatura. Os resultados apontaram até 99% de precisão na detecção de vulnerabilidades na criptografia do tráfego.

show abstract

Tensor‐based gated graph neural network for automatic vulnerability detection in source code

Yang,

Ruan,

Zhang

2023

Software Testing Verif & Rel

View full text Add to dashboard Cite

The rapid expansion of smart devices leads to the increasing demand for vulnerability detection in the cyber security field. Writing secure source codes is crucial to protect applications and software. Recent vulnerability detection methods are mainly using machine learning and deep learning. However, there are still some challenges, how to learn accurate source code semantic embedding at the function level, how to effectively perform vulnerability detection using the learned semantic embedding of source code and how to solve the overfitting problem of learning‐based models. In this paper, we consider codes as various graphs with node features and propose a tensor‐based gated graph neural network called TensorGNN to produce code embedding for function‐level vulnerability detection. First, we propose a high‐dimensional tensor for combining different code graph representations. Second, inspired by the work of tensor technology, we propose the TensorGNN model to produce accurate code representations using the graph tensor. We evaluate our model on 7 C and C++ large open‐source code corpus (e.g. SARD&NVD, Debian, SATE IV, FFmpeg, libpng&LibTiff, Wireshark and Github datasets), which contains 13 types of vulnerabilities. Our TensorGNN model improves on existing state‐of‐the‐art works by 10%–30% on average in terms of vulnerability detection accuracy and F1, while our TensorGNN model needs less training time and model parameters. Specifically, compared with other existing works, our model reduces 25–47 times of the number of parameters and decreases 3–10 times of training time. Results of evaluations show that TensorGNN has better performance while using fewer training parameters and less training time.

show abstract

Machine-learning supported vulnerability detection in source code

Cited by 6 publications

References 8 publications

Towards Making Deep Learning-based Vulnerability Detectors Robust

Towards Making Deep Learning-based Vulnerability Detectors Robust

Um Método para Detecção de Vulnerabilidades Através da Análise do Tráfego de Rede IoT

Tensor‐based gated graph neural network for automatic vulnerability detection in source code

Contact Info

Product

Resources

About