VulSeeker: a semantic learning based vulnerability seeker for cross-platform binary

Gao, Jian; Yang, Xin; Fu, Ying; Jiang, Yu; Sun, Jun

doi:10.1145/3238147.3240480

Cited by 118 publications

(137 citation statements)

References 9 publications

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…However, the solution heavily relies on CFG features and block-level attributes. Gao et al [17] present VulSeeker, a semantic learning-based vulnerability seeker for cross-platform binary. By integrating the CFG and the DFG of the binary function, they capture more function semantics and acquires a higher accuracy and efficiency.…”

Section: Related Workmentioning

confidence: 99%

“…CABS [14], BinGo [15] and Esh [16] divide the CFG into different parts, and improve their robustness to CFG changes by computing the overall CFG and CFG fragments similarities. To minimize the cost of the computation, DiscovRE [8], Genius [9], Gemini [10] and VulSeeker [17] extract some numeric features from CFGs or basic blocks. DiscovRE [8] employs these features as a pre-filter on CFGs and uses the KNN algorithm to identify a small set of candidate functions.…”

Section: Introductionmentioning

confidence: 99%

“…Gemini [10] uses a neural network to compute the embedding of ACFGs and get better performance. VulSeeker [17] uses the CFG and DFG (data flow graph) to construct the labeled semantic flow graph (LSFG) and captures more function semantics and acquires a higher accuracy and efficiency.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Lightweight Cross-Version Binary Code Similarity Detection Based on Similarity and Correlation Coefficient Features

Guo

Huang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The technique of binary code similarity detection (BCSD) has been applied in many fields, such as malware detection, plagiarism detection and vulnerability search, etc. Existing solutions for the BCSD problem usually compare specific features between binaries based on the control flow graphs of functions from binaries or compute the embedding vector of binary functions and solve the problem based on deep learning algorithms. In this paper, from another research perspective, we propose a new and lightweight method to solve cross-version BCSD problem based on multiple features. It transforms binary functions into vectors and signals and computes the similarity coefficient value and correlation coefficient value for solving cross-version BCSD problem. Without relying on the CFG of functions, deep learning algorithms and other related attributes, our method works directly on the raw bytes of each binary and it can be used as an alternative method to coping with various complex situations that exist in the real-world environment. We implement the method and evaluate it on a custom dataset with about 423,282 samples. The result shows that the method could perform well in cross-version BCSD field, and the recall of our method could reach 96.63%, which is almost the same as the state-of-the-art static solution.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Lightweight Cross-Version Binary Code Similarity Detection Based on Similarity and Correlation Coefficient Features

Guo

Huang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Such applications are of pa interest to hackers, because finding vulnerabilities in them does not require special embedded systems background. There are many different file systems for embedded devices including SquashFS 26 , UBIFS 27 , YAFFS2 28 , and JFFS2 29 .…”

Section: Firmware Extractionmentioning

confidence: 99%

“…blocks of IR instructions [24] and conditional formulas [25]. Recently, machine learning algorithms have also been leveraged in order to quickly find code similar to a known vulnerable component [26], [27], [28].…”

Section: Finding Potentially Vulnerable Componentsmentioning

confidence: 99%

IoT Hacking – A Primer

Papp¹,

Tamás²,

Buttyán³

2019

Infocommunications journal

View full text Add to dashboard Cite

The Internet of Things (IoT) enables many new and exciting applications, but it also creates a number of new risks related to information security. Several recent attacks on IoT devices and systems illustrate that they are notoriously insecure. It has also been shown that a major part of the attacks resulted in full adversarial control over IoT devices, and the reason for this is that IoT devices themselves are weakly protected and they often cannot resist even the most basic attacks. Penetration testing or ethical hacking of IoT devices can help discovering and fixing their vulnerabilities that, if exploited, can result in highly undesirable conditions, including damage of expensive physical equipment or even loss of human life. In this paper, we give a basic introduction into hacking IoT devices. We give an overview on the methods and tools for hardware hacking, firmware extraction and unpacking, and performing basic firmware analysis. We also provide a survey on recent research on more advanced firmware analysis methods, including static and dynamic analysis of binaries, taint analysis, fuzzing, and symbolic execution techniques. By giving an overview on both practical methods and readily available tools as well as current scientific research efforts, our work can be useful for both practitioners and academic researchers.

show abstract

Multigranularity semantics based vulnerability search method for cross‐platform binary

Líu

Zhang

2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Semantic learning is a common method for binary vulnerability detection, which can analyze the assembly structure of the binary code. The existing methods such as control flow graphs and labeled semantic flow graphs perform single semantic analysis to determine whether a known vulnerability is hidden in the binary function. However, challenge arises when they perform vulnerability detection cross‐platforms. In this paper, we propose a multigranularity semantic‐based vulnerability search method to deal with the challenge of cross‐platform vulnerability detection, and implement its prototype Taurus. Given the binary function to be searched and vulnerability function, Taurus first extracts their inter‐basic‐block, inter‐function, and inter‐module semantic features respectively, and then calculates the similarity distance between them at three levels. Finally, three similarity scores are combined to rank in descending order to obtain the vulnerability detection report. The performance comparison indicates that Taurus outperforms the state‐of‐the‐art approaches in terms of accuracy.

show abstract

VulSeeker: a semantic learning based vulnerability seeker for cross-platform binary

Cited by 118 publications

References 9 publications

A Lightweight Cross-Version Binary Code Similarity Detection Based on Similarity and Correlation Coefficient Features

A Lightweight Cross-Version Binary Code Similarity Detection Based on Similarity and Correlation Coefficient Features

IoT Hacking – A Primer

Multigranularity semantics based vulnerability search method for cross‐platform binary

Contact Info

Product

Resources

About