GANFuzz

Hu, Zhicheng; Shi, Jian; Huang, Yanhong; Xiong, Jiawen; Bu, Xiangxing

doi:10.1145/3203217.3203241

Cited by 56 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several scholars have already applied deep learning knowledge to fuzzing in the field of industrial control, achieving notable results. Hu et al [31] proposed a fuzzing framework for ICPs based on Generative Adversarial Networks (GANs), known as GANFuzz, which generates fuzzing cases by learning the syntax structure of ICPs in an adversarial manner. Based on GANFuzz, Li et al [32] designed a fully connected adversarial learning neural network model based on Wasserstein GAN, which, while keeping the neural network relatively simple, has a high pass rate for test cases.…”

Section: Related Workmentioning

confidence: 99%

DiffusionFuzz: Fuzzing Framework of Industrial Control Protocols Based on Denoising Diffusion Probabilistic Model

Zong,

Luo,

Ning

et al. 2024

IEEE Access

View full text Add to dashboard Cite

With the opening of industrial networks in the information age, the characteristic of Industrial Control Protocols (ICPs) to transmit plaintext without encryption exposes serious security risks, threatening the safe and stable operation of Industrial Control Systems (ICSs). Exploring the work of mining vulnerabilities in ICPs can use fuzzing to mine potential vulnerabilities in protocols to ensure the safe operation of ICS. However, traditional fuzzing methods require the construction of test cases based on expert experience and the format syntax specification of ICPs. This process is time-consuming, labor-intensive, inefficient, and limited when facing unknown ICPs. In response to these issues, this paper proposes an automated fuzzing method for ICPs based on the Denoising Diffusion Probabilistic Model (DDPM). Specifically, DDPM achieves the conversion from noise to data samples, which can easily and quickly generate test cases. On this basis, we designed a universal fuzzing framework, DiffusionFuzz, that can be applied to most ICPs. The experimental results obtained on ICPs such as Modbus/TCP in the Industrial Attack-Defense Range of the Key Laboratory of Information Security for Petrochemical Industry in Liaoning Province demonstrate that the test cases generated by this method are diverse, and outperform other fuzzing methods in terms of acceptance rate and ability to trigger exceptions. Certainly, DiffusionFuzz can enhance the effectiveness of fuzzing, identify vulnerabilities in ICPs, and thereby reduce potential economic risks and impacts.INDEX TERMS Vulnerability mining, Fuzzing, Industrial control protocols, Denoising diffusion probabilistic model.

show abstract

Section: Related Workmentioning

confidence: 99%

DiffusionFuzz: Fuzzing Framework of Industrial Control Protocols Based on Denoising Diffusion Probabilistic Model

Zong,

Luo,

Ning

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…DARWIN [31] is 48.26% faster than MOPT while, in the MAGMA benchmark test, after 5 hours of fuzzing, DARWIN was able to find 15 bugs (a total of 21). [40] discovered 5 bugs per 10,000 test cases. COMFORT [47] detected 158 unique vulnerabilities by automatically running on 250k self-generated test cases for 200 hours, of which 129 have been verified and 115 have been fixed by developers.…”

Section: Efficiencymentioning

confidence: 99%

“…GANFuzz proposed an automated test case generation method that enables the generation of test cases without relying on protocol-specific format specifications [40]. Firstly, a real protocol message corpus is used as training data and is partitioned using three clustering strategies.…”

mentioning

confidence: 99%

“…Firstly, a real protocol message corpus is used as training data and is partitioned using three clustering strategies. Then, a test case generation model is built using Generative Adversarial Networks (GANs) [40]. By using the generated model based on real protocol messages, fake protocol messages with different degrees of similarity to real protocols can be generated.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning-Based Fuzz Testing Techniques: A Survey

Zhang,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Fuzz testing is a vulnerability discovery technique that tests the robustness of target programs by providing them with unconventional data. With the rapid increase in software quantity, scale and complexity, traditional fuzzing has revealed issues such as incomplete logic coverage, low automation level and insufficient test cases. Machine learning, with its exceptional capabilities in data analysis and classification prediction, presents a promising approach for improve fuzzing. This paper investigates the latest research results in fuzzing and provides a systematic review of machine learning-based fuzzing techniques. Firstly, by outlining the workflow of fuzzing, it summarizes the optimization of different stages of fuzzing using machine learning. Specifically, it focuses on the application of machine learning in the preprocessing phase, test case generation phase, input selection phase and result analysis phase. Secondly, it mentally focuses on the optimization methods of machine learning in the process of mutation, generation and filtering of test cases and compares and analyzes its technical principles. Furthermore, it analyzes the performance gains brought by applying machine learning techniques to fuzzing, mainly including coverage, vulnerability detection capability, efficiency and effectiveness of test cases. Lastly, it concludes by summarizing the challenges and difficulties in combining machine learning with fuzzing and presents prospects for future trends in this field.

show abstract

“…Traffic-analysis-based methods utilize network communication data flows to obtain network protocol syntax knowledge, but there are challenges in improving information comprehensiveness. Besides, encrypted traffic makes data unreadable thus further limiting the analysis of protocol syntax [15][16][17]. Artificial intelligence methods use machine learning or natural language processing technology to extract structured information from text documents by learning protocol grammar rules [18][19][20].…”

Section: Introductionmentioning

confidence: 99%

A Novel Network Protocol Syntax Extracting Method for Grammar-Based Fuzzing

Li,

Zhang,

Zhao

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Network protocol syntax information plays a crucial role in grammar-based fuzzing. Current network protocol syntax extraction methods are less versatile, inefficient, and the extracted information is not comprehensive. This paper proposes a novel method for extracting syntax information, which innovatively extracts network protocol syntax from Wireshark protocol dissector files. The extracted syntax information includes packet types of the protocol, the constituent fields of each packet type, and detailed attributes of each field. Based on this method, an automated system for network protocol syntax information extraction was developed. The experiment was conducted with this system on a variety of protocols including DCCP, DNP3.0, Modbus TCP, and S7COMM. The experimental results show that compared with the current methods, our method has a better performance in terms of efficiency and versatility and at the same time ensures the comprehensiveness and accuracy of the extracted syntax information.

show abstract

GANFuzz

Cited by 56 publications

References 9 publications

DiffusionFuzz: Fuzzing Framework of Industrial Control Protocols Based on Denoising Diffusion Probabilistic Model

DiffusionFuzz: Fuzzing Framework of Industrial Control Protocols Based on Denoising Diffusion Probabilistic Model

Machine Learning-Based Fuzz Testing Techniques: A Survey

A Novel Network Protocol Syntax Extracting Method for Grammar-Based Fuzzing

Contact Info

Product

Resources

About