检索结果-内蒙古大学图书馆

OpTrans: enhancing binary code similarity detection with function inlining re-optimization

EMPIRICAL SOFTWARE ENGINEERING 2025年第2期30卷 1-25页

作者： Sha, Zihan Lan, Yang Zhang, Chao Wang, Hao Gao, Zeyu Zhang, Bolun Shu, Hui Minist Educ Key Lab Cyberspace Secur Zhengzhou Peoples R China Tsinghua Univ Beijing Peoples R China Inst Informat Engn CAS Beijing Peoples R China

Binary code similarity detection (BCSD) is pivotal in system security including reverse engineering, vulnerability detection and software component analysis. Recent studies on BCSD have proliferated, yet they exhibit poor performance when confronting semantic alterations (e.g., function inlining) caused by compiler optimization. To tackle this challenge, we present OpTrans, an innovative framework that fuses binary code Optimization techniques with the Transformer model for BCSD. OpTrans employs an algorithm based on binary program analysis to determine which functions should be inlined, followed by binary rewriting techniques to effectuate re-optimization on binaries. This innovative method significantly reduces false positives and enhances model performance in real-world BCSD tasks. We evaluated OpTrans on the BinaryCorp datasets, and it outperformed the state-of-the-art BCSD solutions by 21.5% on average. The inline re-optimization improved all BCSD solutions by up to 32.1%. Our ablation study and vulnerability experiment demonstrate the practicality of inline re-optimization in real-world detection scenarios, showing the usefulness of our approach.

关键词： Static analysis similarity detection Optimization Neural networks

来源：评论

学校读者我要写书评

暂无评论

UniASM: Binary code similarity detection without fine-tuning

引用

NEUROCOMPUTING 2025年 630卷

作者： Gu, Yeming Shu, Hui Kang, Fei Hu, Fan Minist Educ Key Lab Cyberspace Secur Zhengzhou Peoples R China

Binary code similarity detection (BCSD) is widely used in various binary analysis tasks such as vulnerability search, malware detection, clone detection, and patch analysis. Recent studies have shown that the learning- based binary code embedding models perform better than the traditional feature-based approaches. However, previous studies have not delved deeply into the key factors that affect model performance. In this paper, we design extensive ablation studies to explore these influencing factors. The experimental results have provided us with many new insights. We have made innovations in both code representation and model selection: we propose a novel rich-semantic function representation technique to ensure the model captures the intricate nuances of binary code, and we introduce the first UniLM-based binary code embedding model, named UniASM, which includes two newly designed training tasks to learn representations of binary functions. The experimental results show that UniASM outperforms the state-of-the-art (SOTA) approaches on the evaluation datasets. The average scores of Recall@1 on cross-compilers, cross-optimization-levels, and cross-obfuscations have improved by 12.7%, 8.5%, and 22.3%, respectively, compared to the best of the baseline methods. Besides, in the real-world task of known vulnerability search, UniASM outperforms all the current baselines.

关键词： similarity detection Embedding Binary code Assembly language Vulnerability

来源：评论

学校读者我要写书评

暂无评论

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第14期83卷 41597-41636页

作者： Chen, Gang Zhu, Donglin Chen, Xiangyu Fuzhou Univ Coll Phys & Informat Engn Fuzhou 350108 Peoples R China JiangXi Univ Sci & Technol Sch Informat Engn Ganzhou 341000 Peoples R China

Although image detection technology is widely used in various fields, there is still a large gap in the similarity detection of science fiction painting. Therefore, a similarity detection method for science fiction painting is proposed. Firstly, a k-layer pyramid image is created for the source image to be detected and the template image. Then, multi-strategy improved sparrow algorithm (MISSA) is used to perform rough matching in the top subgraph of the source image to obtain the coordinates of the initial matching target, the location transferred from the layer above each layer is the starting point of search, and pixel by pixel matching is carried out within the set window range. Finally, pHash is used as the similarity measure to calculate the similarity of matching results. The hybrid search strategy based on step function, multi-stage dynamic control of safety threshold, and food search strategy based on Logistic model are used to improve sparrow search algorithm, thereby forming MISSA to improve the accuracy and real-time performance in the matching process. In terms of performance verification of MISSA, the rationality and effectiveness of the three improved strategies are verified by ablation experiment, and the experimental results on CEC2017 benchmark function show that the optimization performance and convergence performance of MISSA are better than that of peer algorithms. The comparison results in the similarity detection experiment of science fiction painting fully verify that the proposed detection method has strong robustness in meeting the requirements of real-time and accuracy of matching.

关键词： Sparrow search algorithm Gaussian pyramid Multi-strategy improvements Science fiction painting similarity detection

来源：评论

学校读者我要写书评

暂无评论

引用

JOURNAL OF SYMBOLIC COMPUTATION 2018年 85卷 4-24页

作者： Gerardo Alcazar, Juan Hermoso, Carlos Muntingh, Georg Univ Alcala Dept Fis & Matemat E-28871 Madrid Spain Sintef Ict POB 124 Blindern N-0314 Oslo Norway

We provide an algorithm to check whether two rational space curves are related by a similarity. The algorithm exploits the relationship between the curvatures and torsions of two similar curves, which is formulated in a computer algebra setting. Helical curves, where curvature and torsion are proportional, need to be distinguished as a special case. The algorithm is easy to implement, as it involves only standard computer algebra techniques, such as greatest common divisors and resultants, and Grobner basis for the special case of helical curves. Details on the implementation and experimentation carried out using the computer algebra system Maple 18 are provided. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： similarity detection Space algebraic curves Rational curves Recognition

来源：评论

学校读者我要写书评

暂无评论

引用

2nd International Conference on Video and Image Processing (ICVIP)

作者： Ding, Wenjia Xie, Yi Wang, Yulin Wuhan Univ Shenzhen Res Inst Wuhan Hubei Peoples R China

ISBN: (纸本)9781450366137

With the wider use of huge amount of images, more reasonable retrieval algorithms are becoming more and more important. This paper proposed an image similarity detection algorithm for image content based retrieval. The algorithm can extract the main color of the image, and improve the traditional methods in similarity detection performance. Because the eigenvalues of different regions of the image may be quite different, only using the global features of the image as matching eigenvalues will lead to a large error in similarity judgment, so image segmentation technology has always been the key technology in color image processing. In this paper, a more advanced block technology is used to segment the image of different regions, which can effectively reflect the spatial information of different images.

关键词： Color image processing ISODATA clustering similarity detection

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE Symposium on Computers and Communications (ISCC)

作者： Congduc Pham Makhoul, Abdallah Diop, Mamour Univ Pau Pau France DISC FEMTO ST Paris France Univ Gaston Berger St Louis Senegal

ISBN: (纸本)9781728129990

LPWAN refers to highly energy-efficient wireless communication over very long distances. Nonetheless, even with the increased range, I-hop connectivity can he difficult to achieve in real-world deployment scenario, especially for remote and rural areas where density of gateways is low and where devices/gateway are usually deployed for a specific application. Therefore a smart and transparent 2-hop approach has been proposed in a previous work to leverage these connectivity issues. This article extents this approach with similarity detection features in order to (i) reduce the power consumption when waking-up to relay packets and (ii) reduce the radio activity time when running under duty-cycle regulated constraints.

关键词： LoRa Low-power IoT similarity detection

来源：评论

学校读者我要写书评

暂无评论

引用

21st International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision

作者： Dang, Quoc-Viet Mouysset, Sandrine Morin, Geraldine Univ Toulouse Toulouse France

ISBN: (纸本)9788086943756

In this article, we propose a framework for detecting local similarities in free-form parametric models, in particular on B-Splines or NURBS based B-reps: patches similar up to an approximated isometry are identified. Many recent articles have tackled similarity detection on 3D objects, in particular on 3D meshes. The parametric B-splines, or NURBS models are standard in the CAD (Computer Aided Design) industry, and similarity detection opens the door to interesting applications in this domain, such as model editing, objects comparison or efficient coding. Our contributions are twofold: we adapt the current technique called votes transformation space for parametric surfaces and we improve the identification of isometrics. First, an orientation technique independent of the parameterization permits to identify direct versus indirect transformations. Second, the validation step is generalized to extend to the whole B-rep. Then, by classifying the isometries according to their fixed points, we simplify the clustering step. We also apply an unsupervised spectral clustering method which improves the results but also automatically estimates the number of clusters.

关键词： similarity detection parametric surfaces isometry spectral clustering

来源：评论

学校读者我要写书评

暂无评论

BinCola: Diversity-Sensitive Contrastive Learning for Binary Code similarity detection

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2024年第10期50卷 2485-2497页

作者： Jiang, Shuai Fu, Cai He, Shuai Lv, Jianqiang Han, Lansheng Hu, Hong Huazhong Univ Sci & Technol Sch Cyber Sci & Engn Wuhan 430074 Peoples R China Penn State Univ Coll Informat Sci & Technol University Pk PA 16802 USA

Binary Code similarity detection (BCSD) is a fundamental binary analysis technique in the area of software security. Recently, advanced deep learning algorithms are integrated into BCSD platforms to achieve superior performance on well-known benchmarks. However, real-world large programs embed more complex diversities due to different compilers, various optimization levels, multiple architectures and even obfuscations. Existing BCSD solutions suffer from low accuracy issues in such complicated real-world application scenarios. In this paper, we propose BinCola, a novel Transformer-based dual diversity-sensitive contrastive learning framework that comprehensively considers the diversity of compiler options and candidate functions in the real-world application scenarios and employs the attention mechanism to fuse multi-granularity function features for enhancing generality and scalability. BinCola simultaneously compares multiple candidate functions across various compilation option scenarios to learn the differences caused by distinct compiler options and different candidate functions. We evaluate BinCola's performance in a variety of ways, including binary similarity detection and real-world vulnerability search in multiple application scenarios. The results demonstrate that BinCola achieves superior performance compared to state-of-the-art (SOTA) methods, with improvements of 2.80%, 33.62%, 22.41%, and 34.25% in cross-architecture, cross-optimization level, cross-compiler, and cross-obfuscation scenarios, respectively.

关键词： Feature extraction Contrastive learning Vectors Source coding Software Semantics Training Diversity sensitive binary analysis similarity detection attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A time series representation model for accurate and fast similarity detection

引用

PATTERN RECOGNITION 2009年第11期42卷 2998-3014页

作者： Gullo, Francesco Ponti, Giovanni Tagarelli, Andrea Greco, Sergio Univ Calabria Dept Elect Comp & Syst Sci I-187036 Arcavacata Di Rende CS Italy

similarity search and detection is a central problem in time series data processing and management. Most approaches to this problem have been developed around the notion of dynamic time warping, whereas several dimensionality reduction techniques have been proposed to improve the efficiency of similarity searches. Due to the continuous increasing of sources of time series data and the cruiciality of real-world applications that use such data, we believe there is a challenging demand for supporting similarity detection in time series in a both accurate and fast way. Our proposal is to define a concise yet feature-rich representation of time series, on which the dynamic time warping can be applied for effective and efficient similarity detection of time series. We present the Derivative time series Segment Approximation (DSA) representation model, which originally features derivative estimation, segmentation and segment approximation to provide both high sensitivity in capturing the main trends of time series and data compression. We extensively compare DSA with state-of-the-art similarity methods and dimensionality reduction techniques in clustering and classification frameworks. Experimental evidence from effectiveness and efficiency tests on various datasets shows that DSA is well-suited to Support both accurate and fast similarity detection. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Time series data Representation models similarity detection Dimensionality reduction Clustering Classification

来源：评论

学校读者我要写书评

暂无评论

A comprehensive system for evaluation of remote sequence similarity detection

引用

BMC BIOINFORMATICS 2007年第1期8卷 1-19页

作者： Qi, Yuan Sadreyev, Ruslan I. Wang, Yong Kim, Bong-Hyun Grishin, Nick V. Univ Texas Southwestern Med Ctr Howard Hughes Med Inst Dallas TX 75390 USA Univ Texas Southwestern Med Ctr Dept Biochem Dallas TX 75390 USA Univ N Carolina Lineberger Comprehens Canc Ctr Chapel Hill NC 27599 USA

Background: Accurate and sensitive performance evaluation is crucial for both effective development of better structure prediction methods based on sequence similarity, and for the comparative analysis of existing methods. Up to date, there has been no satisfactory comprehensive evaluation method that (i) is based on a large and statistically unbiased set of proteins with clearly defined relationships;and (ii) covers all performance aspects of sequence-based structure predictors, such as sensitivity and specificity, alignment accuracy and coverage, and structure template quality. Results: With the aim of designing such a method, we (i) select a statistically balanced set of divergent protein domains from SCOP, and define similarity relationships for the majority of these domains by complementing the best of information available in SCOP with a rigorous SVM-based algorithm;and (ii) develop protocols for the assessment of similarity detection and alignment quality from several complementary perspectives. The evaluation of similarity detection is based on ROC-like curves and includes several complementary approaches to the definition of true/false positives. Reference-dependent approaches use the 'gold standard' of pre-defined domain relationships and structure-based alignments. Reference-independent approaches assess the quality of structural match predicted by the sequence alignment, with respect to the whole domain length (global mode) or to the aligned region only (local mode). Similarly, the evaluation of alignment quality includes several reference-dependent and independent measures, in global and local modes. As an illustration, we use our benchmark to compare the performance of several methods for the detection of remote sequence similarities, and show that different aspects of evaluation reveal different properties of the evaluated methods, highlighting their advantages, weaknesses, and potential for further development. Conclusion: The presented benchmark pro

关键词： Support Vector Machine Correct Match Domain Pair Alignment Quality similarity detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：