检索结果-内蒙古大学图书馆

UniASM: binary code similarity detection without fine-tuning

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

binary code Representation With Well-Balanced Instruction Normalization

引用

IEEE ACCESS 2023年 11卷 29183-29198页

作者： Koo, Hyungjoon Park, Soyeon Choi, Daejin Kim, Taesoo Sungkyunkwan Univ Dept Comp Sci & Engn Suwon 16419 South Korea Georgia Inst Technol Sch Comp Sci Atlanta GA 30332 USA Incheon Natl Univ Dept Comp Sci & Engn Incheon 22012 South Korea

The recovery of contextual meanings on a machine code is required by a wide range of binary analysis applications, such as bug discovery, malware analysis, and code clone detection. To accomplish this, advancements on binary code analysis borrow the techniques from natural language processing to automatically infer the underlying semantics of a binary, rather than replying on manual analysis. One of crucial pipelines in this process is instruction normalization, which helps to reduce the number of tokens and to avoid an out-of-vocabulary (OOV) problem. However, existing approaches often substitutes the operand(s) of an instruction with a common token (e.g., callee target ? FOO), inevitably resulting in the loss of important information. In this paper, we introduce well-balanced instruction normalization (WIN), a novel approach that retains rich code information while minimizing the downsides of code normalization. With large swaths of binary code, our finding shows that the instruction distribution follows Zipf's Law like a natural language, a function conveys contextually meaningful information, and the same instruction at different positions may require diverse code representations. To show the effectiveness of WIN, we present DeepSemantic that harnesses the BERT architecture with two training phases: pre-training for generic assembly code representation, and fine-tuning for building a model tailored to a specialized task. We define a downstream task of binary code similarity detection, which requires underlying code semantics. Our experimental results show that our binary similarity model with WIN outperforms two state-of-the-art binary similarity tools, DeepBinDiff and SAFE, with an average improvement of 49.8% and 15.8%, respectively.

关键词： Task analysis binary codes Bit error rate Semantics Computer architecture Computational modeling Transformers binary code code representation BERT well-balanced instruction normalization binary code similarity detection

来源：评论

学校读者我要写书评

暂无评论

binary code Optimized for Partial Encryption

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2020年第11期68卷 7201-7217页

作者： Kafi, Mehrshad Dumitrescu, Sorina McMaster Univ Dept Elect & Comp Engn Hamilton ON L8S 4K1 Canada

A common technique for the partial encryption of compressed images and videos encrypts only the sign bits of some syntax elements such as the quantized transform coefficients or the motion vector differences. The sign bit can be interpreted as the most significant bit (MSB) in the binary representation of the syntax element. Our work is motivated by the key observation that the binary code used for this representation has an impact on the quality of the reconstruction at the eavesdropper and on the size of the stream to be encrypted. Therefore, we address the problem of optimal binary code design for partial encryption. Ideally, the goal is to simultaneously maximize the eavesdropper's distortion and minimize the length of the compressed MSB stream. Since these two objectives are conflicting in general, we formulate the problem as the maximization of a weighted sum of the eavesdropper's distortion and of the probability of the MSB being 0. We cast the problem as a binary integer linear program equivalent to a maximum weight matching problem, which has a polynomial-time solution algorithm. We show that when the source to be quantized and the quantizer are symmetric, the problem can be converted to a linear program of a smaller size, for a family of distortion metrics. Extensive experiments assess the performance of the optimized binary code in comparison with existing approaches. The results reveal that certain existing partial encryption schemes could benefit from the proposed design.

关键词： Encryption binary codes Image coding Videos Distortion Syntactics Partial selective encryption binary code maximum weight matching linear programming

来源：评论

学校读者我要写书评

暂无评论

Runtime Vectorization Transformations of binary code

引用

INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING 2017年第6期45卷 1536-1565页

作者： Hallou, Nabil Rohou, Erven Clauss, Philippe INRIA Rennes France Univ Strasbourg ICube Lab INRIA Strasbourg France

In many cases, applications are not optimized for the hardware on which they run. Several reasons contribute to this unsatisfying situation, such as legacy code, commercial code distributed in binary form, or deployment on compute farms. In fact, backward compatibility of ISA guarantees only the functionality, not the best exploitation of the hardware. In this work, we focus on maximizing the CPU efficiency for the SIMD extensions. The first contribution was originally published in the International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS XV, July 2015, Agios Konstantinos, Greece. It is a binary-to-binary optimization framework where loops vectorized for an older version of the processor SIMD extension are automatically converted to a newer one. It is a lightweight mechanism that does not include a vectorizer, but instead leverages what a static vectorizer previously did. We show that many loops compiled for x86 SSE can be dynamically converted to the more recent and more powerful AVX;as well as, how correctness is maintained with regards to challenges such as data dependencies and reductions. We obtain speedups in line with those of a native compiler targeting AVX. The second contribution is the runtime vectorization of loops in binary codes that were not originally vectorized. For this purpose, we use open source frameworks that we have tuned and integrated to (1) dynamically lift the x86 binary into the Intermediate Representation form of the LLVM compiler, (2) abstract hot loops in the polyhedral model, (3) use the power of this mathematical framework to vectorize them, and (4) finally compile them back into executable form using the LLVM Just-In-Time compiler. In most cases, the obtained speedups are close to the number of elements that can be simultaneously processed by the SIMD unit. The re-vectorizer and auto-vectorizer are implemented inside a dynamic optimization platform;it is completely transparent to the us

关键词： Performance Runtime optimization binary code Dynamic binary optimization Vectorization Polyhedral model

来源：评论

学校读者我要写书评

暂无评论

Securing binary code

引用

IEEE SECURITY & PRIVACY 2017年第6期15卷 77-81页

作者： Hawkins, William Hiser, Jason D. Anh Nguyen-Tuong Co, Michele Davidson, Jack W. Univ Virginia Charlottesville VA 22903 USA Univ Virginia Comp Sci Charlottesville VA 22903 USA

The Zipr tool reverse-engineers binary code and applies specific and generic code transformations, with the goal of securing binary code.

关键词： Security Transforms binary codes Aerospace electronics Reverse engineering Runtime INSPEC: Controlled Indexing binary codes reverse engineering security of data INSPEC: Non-Controlled Indexing binary code security Zipr tool reverse engineering generic code transformations Author Keywords Resilient Security software of unknown provenance (SOUP) binary code Cyber Grand Challenge Zipr reverse engineering software engineering security.

来源：评论

学校读者我要写书评

暂无评论

Reversible binary to Grey and Grey to binary code Converter using QCA

引用

IETE JOURNAL OF RESEARCH 2015年第3期61卷 223-229页

作者： Das, Jadav Chandra De, Debashis West Bengal Univ Technol Dept Comp Sci & Engn Kolkata 700064 India

Quantum dot-cellular automata (QCA) is an emerging nanotechnological archetype and has widespread applications in designing nanoscale reversible circuit for nanocomputing. The low power consumption, faster operating speed, and low circuit area of QCA pledge the energy efficient design of logic circuit having high device complexity. This paper demonstrates the design of reversible binary to grey and grey to binary code converter based on Feynman gate using QCA for the first time. Both the proposed reversible code converter circuits have quantum cost as 2. The conversion of binary to grey code is achieved with only one garbage value and the grey to binary code conversion is achieved without any garbage value. The proposed Feynman gate circuit required only 38,880 nm(2) areas and three clocking zones. The reversible binary to grey circuit required only 92,664 nm(2) areas and three clocking zones whereas the reversible grey to binary circuit required only 139,968 nm(2) areas and four clocking zones. The proposed design can be used to realise the nanoarchitecture in computer communication having low power consumption. The evaluation of simulation outcomes of proposed circuit with theoretical knowledge established the functional efficiency of the circuits. The circuits are designed and simulated by QCA Designer-2.0.3.

关键词： binary code FG Gate Grey code QCA

来源：评论

学校读者我要写书评

暂无评论

Design of (4,8) binary code with MDS and Zigzag-Decodable Property

引用

WIRELESS PERSONAL COMMUNICATIONS 2016年第1期89卷 1-13页

作者： Dai, Mingjun Lu, Zexin Shen, Dan Wang, Hui Chen, Bin Lin, Xiaohui Zhang, Shengli Zhang, Li Liu, Hongwei Shenzhen Univ Shenzhen Key Lab Adv Commun & Informat Proc Coll Informat Engn Shenzhen Peoples R China Shenzhen Univ Shenzhen Key Lab Media Secur Coll Informat Engn Shenzhen Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Xian Peoples R China

Dedicated to network code structured distributed storage system, a novel (4, 8) storage code is designed. The code possesses the following properties: operation within binary field , maximum distance separable property, zigzag decodable, requiring symmetric storage overhead among multiple storage nodes, and requiring little storage overhead . In the design of such a storage code, we first let original packets shift to the right by several bits and then add them together within binary field in bitwise manner . We propose a smart design on a cyclic matrix that represents the number of bits shifted by those packet. Existing works do not hold these properties simultaneously , which have the drawback of high encoding and decoding complexity, large storage overhead, and complicated storage room allocation procedure, etc.

关键词： MDS Distributed storage Network code Zigzag decoding binary code

来源：评论

学校读者我要写书评

暂无评论

Transforming binary code for low-power embedded processors

引用

IEEE MICRO 2004年第3期24卷 21-33页

作者： Petrov, P Orailoglu, A Univ Calif San Diego Dept Comp Sci & Engn La Jolla CA 92093 USA

TWO PROGRAM code TRANSFORMATION METHODOLOGIES REDUCE THE POWER CONSUMPTION OF INSTRUCTION COMMUNICATION BUSES IN EMBEDDED PROCESSORS. AIMED AT DEEP-SUBMICRON PROCESS TECHNOLOGIES, THESE TECHNIQUES OFFER AN EFFICIENT S... 详细信息

关键词： LOW POWER program code embedded processor embedding Transforming Quality factor low power consumption Power consumption PROCESSOR binary code

来源：评论

学校读者我要写书评

暂无评论

Every binary code can be realized by convex sets

引用

ADVANCES IN APPLIED MATHEMATICS 2018年 99卷 83-93页

作者： Franke, Megan Muthiah, Samuel Univ Calif Santa Barbara Dept Math Santa Barbara CA 93106 USA Westmont Coll Dept Math & Comp Sci Santa Barbara CA 93108 USA

Much work has been done to identify which binary codes can be represented by collections of open convex or closed convex sets. While not all binary codes can be realized by such sets, here we prove that every binary code can be realized by convex sets when there is no restriction on whether the sets are all open or closed. We achieve this by constructing a convex realization for an arbitrary code with k nonempty codewords in Rk-1. This result justifies the usual restriction of the definition of convex neural codes to include only those that can be realized by receptive fields that are all either open convex or closed convex. We also show that the dimension of our construction cannot in general be lowered. (C) 2018 Elsevier Inc. All rights reserved.

关键词： binary code Convex Helly's Theorem Neural code

来源：评论

学校读者我要写书评

暂无评论

On the Representation of Results of binary code Reverse Engineering

引用

PROGRAMMING AND COMPUTER SOFTWARE 2018年第3期44卷 200-206页

作者： Padaryan, V. A. Ledovskikh, I. N. Russian Acad Sci Inst Syst Programming Moscow 109004 Russia

A representation of algorithms extracted from binary code by reverse engineering is discussed. Both intermediate representations designed for automatic analysis and final representations passed to the end user are considered. The two main tasks of reverse engineering-automatic detection of exploitable vulnerabilities and discovery of undocumented features- are analyzed. The basic scheme of the system implementing the automatic detection of exploitable vulnerabilities is presented and the key properties of the intermediate representation designed for solving this problem using an efficient generation of a system of equations for an SMT solver are described. The workflow for discovering undocumented features is described. These steps are the localization of the algorithm, its representation in the form that is convenient for analysis, and investigation of its properties. To automate the first phase, a combined static and dynamic representation is constructed, which includes OS-level events and calls to library functions;they serve as anchor points used by the analyst for the algorithm localization. The further support of localization uses code slicing and navigation algorithms. Once the algorithm is localized, the further work goes in two directions: interactive construction of a compact annotated representation of the algorithm by a flowchart and automated investigation of the algorithm properties aimed at determining declared and undeclared data flows. The representation of the algorithm is based on the construction of simplified models of functions taking into account input and output buffers and on the automatic detection of data dependences between buffers of various function calls. The overall scenario of the analyst' work with such a flowchart in the context of discovering undocumented features is described;this scenario is based on annotating the declared data flows and on the automatic detection of undeclared data flows. In conclusion, an example of the resul

关键词： binary code combined analysis intermediate representation

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：