检索结果-内蒙古大学图书馆

Large Language Model Supply Chain: A Research Agenda

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Shenao Zhao, Yanjie Hou, Xinyi Wang, Haoyu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

The rapid advancement of large language models (LLMs) has revolutionized artificial intelligence, introducing unprecedented capabilities in natural language processing and multimodal content generation. However, the increasing complexity and scale of these models have given rise to a multifaceted supply chain that presents unique challenges across infrastructure, foundation models, and downstream applications. This paper provides the first comprehensive research agenda of the LLM supply chain, offering a structured approach to identify critical challenges and opportunities through the dual lenses of software engineering (SE) and security & privacy (S&P). We begin by establishing a clear definition of the LLM supply chain, encompassing its components and dependencies. We then analyze each layer of the supply chain, presenting a vision for robust and secure LLM development, reviewing the current state of practices and technologies, and identifying key challenges and research opportunities. This work aims to bridge the existing research gap in systematically understanding the multifaceted issues within the LLM supply chain, offering valuable insights to guide future efforts in this rapidly evolving domain. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

WaDec: Decompiling WebAssembly Using Large Language Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： She, Xinyu Zhao, Yanjie Wang, Haoyu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

WebAssembly (abbreviated Wasm) has emerged as a cornerstone of web development, offering a compact binary format that allows high-performance applications to run at near-native speeds in web browsers. Despite its advantages, Wasm’s binary nature presents significant challenges for developers and researchers, particularly regarding readability when debugging or analyzing web applications. Therefore, effective decompilation becomes crucial. Unfortunately, traditional decompilers often struggle with producing readable outputs. While some large language model (LLM)-based decompilers have shown good compatibility with general binary files, they still face specific challenges when dealing with Wasm. In this paper, we introduce a novel approach, WaDec, which is the first use of a fine-tuned LLM to interpret and decompile Wasm binary code into a higher-level, more comprehensible source code representation. The LLM was meticulously fine-tuned using a specialized dataset of wat-c code snippets, employing self-supervised learning techniques. This enables WaDec to effectively decompile not only complete wat functions but also finer-grained wat code snippets. Our experiments demonstrate that WaDec markedly outperforms current state-of-the-art tools, offering substantial improvements across several metrics. It achieves a code inflation rate of only 3.34%, a dramatic 97% reduction compared to the state-ofthe-art’s 116.94%. Unlike the output of baselines that cannot be directly compiled or executed, WaDec maintains a recompilability rate of 52.11%, a re-execution rate of 43.55%, and an output consistency of 27.15%. Additionally, it significantly exceeds state-of-the-art performance in AST edit distance similarity by 185%, cyclomatic complexity by 8%, and cosine similarity by 41%, achieving an average code similarity above 50%. In summary, WaDec enhances understanding of the code’s structure and execution flow, facilitating automated code analysis, optimization, and security auditin

关键词： Web browsers

MalWuKong: Towards Fast, Accurate, and Multilingual Detection of Malicious Code Poisoning in OSS Supply Chains

学校读者我要写书评

暂无评论

MalWuKong: Towards Fast, Accurate, and Multilingual Detectio...

IEEE International Conference on Automated Software Engineering (ASE)

作者： Ningke Li Shenao Wang Mingxi Feng Kailong Wang Meizhen Wang Haoyu Wang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

In the face of increased threats within software registries and management systems, we address the critical need for effective malicious code detection. In this paper, we propose an innovative approach that integrates source code slicing, inter-procedural analysis, and cross-file inter-procedural analysis, thereby enhancing the detection precision and reducing false positives. This approach has been encapsulated within a multi-analysis-based framework for automatic detection of malicious code in real-world software packages. In its application to major third-party software registries like PyPI and NPM, our framework has proven effective, identifying 130 malicious packages from a total of 169,640 monitored over a continuous period of five weeks. This work advances the current state-of-the-art solution to malicious code detection, demonstrating significant practical impact in strengthening the software supply chain defense.

关键词：

AutoSlicer: Automatic Program Partitioning for Securing Sensitive data Based-on data Dependency Analysis and Code Refactoring

学校读者我要写书评

暂无评论

AutoSlicer: Automatic Program Partitioning for Securing Sens...

IEEE International Conference on Trust, security and Privacy in Computing and Communications (TrustCom)

作者： Weizhong Qiang Hao Luo Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

Legacy programs are normally monolithic (that is, all code runs in a single process and is not partitioned), and a bug in a program may result in the entire program being vulnerable and therefore untrusted. Program partitioning can be used to separate a program into multiple partitions, so as to isolate sensitive data or privileged operations. Manual program partitioning requires programmers to rewrite the entire source code, which is cumbersome, error-prone, and not generic. Automatic program partitioning tools can separate programs according to the dependency graph constructed based on data or programs. However, programmers still need to manually implement remote service interfaces for inter-partition communication. Therefore, in this paper, we propose AutoSlicer, whose purpose is to partition a program more automatically, so that the programmer is only required to annotate sensitive data. AutoSlicer constructs accurate data dependency graphs (DDGs) by enabling execution flow graphs, and the DDG-based partitioning algorithm can compute partition information based on sensitive annotations. In addition, the code refactoring toolchain can automatically transform the source code into sensitive and insensitive partitions that can be deployed on the remote procedure call framework. The experimental evaluation shows that AutoSlicer can effectively improve the accuracy (13%-27%) of program partitioning by enabling EFG, and separate real-world programs with a relatively smaller performance overhead (0.26%-9.42%).

关键词： Privacy Codes Source coding Computer bugs Prototypes Transforms Manuals

Ranking on Heterogeneous Manifold for Multimodal Information Retrieval 21

学校读者我要写书评

暂无评论

Ranking on Heterogeneous Manifold for Multimodal Information...

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Jin, Zhenkun Wan, Xingshi Nie, Xin Zhou, Xinlei Yi, Yuanyuan Zhou, Gefei Wuhan Business University Wuhan Research Institute of Posts and Telecommunications Wuhan China Wuhan Research Institute of Posts and Telecommunications Wuhan China Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Wuhan China Huazhong University of Science and Technology School of Journalism and Information Communication Wuhan China Huazhong University of Science and Technology School of Computer Science & Technology Wuhan China

ISBN: (纸本)9798350329223

In light of recent advancements in Internet of Multimedia Things (IoMT) and 5G technology, both the variety and quantity of data have been rapidly increasing. Consequently, handling zero-shot cross-modal retrieval (ZSCMR) of unlabeled multi-modal data has emerged as a prominent research topic. Early models utilized generative adversarial networks and class embeddings to assist in building a common feature space. However, this approach resulted in a loss of reliability in the feature distributions of individual modalities. In this paper, we propose a method called Ranking on Heterogeneous Manifold (RHM) to address the aforementioned issue. Our model comprises three feature extractors, each dedicated to extracting features from text, images and multimodal data. Subsequently, the relationship structures derived from these feature extractors are employed to construct a heterogeneous manifold. A diffusion process is then conducted on this heterogeneous manifold, ultimately yielding the final ranking scores. Comprehensive experiments demonstrate that the proposed modal has the capability to acquire more effective knowledge representation, thus enhancing the effectiveness of ZSCMR. © 2023 IEEE.

关键词： Knowledge representation

Traceable Ring Signature Scheme in Internet of Vehicles Based on Lattice Cryptography

学校读者我要写书评

暂无评论

Traceable Ring Signature Scheme in Internet of Vehicles Base...

IEEE International Conference on Big data and Cloud Computing (BdCloud)

作者： Wei Liao Lansheng Han Peng Chen Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

Lattice cryptography, as a recognized Cryptosystem that can resist quantum computation, has great potential for development. Lattice based signature scheme is currently a research focus. In this paper, the traceable ring signature scheme based on lattice cryptography in the Internet of Vehicles (IoV) environment is studied. Firstly, users’ public and private keys are generated on the lattice, which effectively reduces the key size and time cost. Secondly, the scheme also achieves traceability by adding additional information. The scheme satisfies strong unforgeability, traceability, and anonymity. In addition, the traceable ring signature scheme based on lattice cryptography is applied in the IoV environment to effectively protect user privacy. Model communication can not only protect user privacy, but also trace the signer when necessary, achieving a balance between security and privacy. The simulation results show that the average delay of IoV of our scheme is better than that of similar schemes. The research in this paper improves the security of data transmission in the IoV environment, enables it to adapt to the complex and changeable new network environment, and effectively guarantees the information security of vehicles and owners.

关键词：

Intersecting-boundary-sensitive fingerprinting for tampering detection of DNN models 24

学校读者我要写书评

暂无评论

Intersecting-boundary-sensitive fingerprinting for tampering...

Proceedings of the 41st International Conference on Machine Learning

作者： Xiaofan Bai Chaoxiang He Xiaojing Ma Bin Benjamin Zhu Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security Microsoft School of Computer Science and Technology Huazhong University of Science and Technology and National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab.

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF.

关键词：

SMPC Task Decomposition: A Theory for Accelerating Secure Multi-party Computation Task

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Yuanqing Bai, Tao Lu, Songfeng Tang, Xueming Wu, Junjun Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

Today, we are in the era of big data, and data are becoming more and more important, especially private data. Secure Multi-party Computation (SMPC) technology enables parties to perform computing tasks without revealing original data. However, the underlying implementation of SMPC is too heavy, such as garbled circuit (GC) and oblivious transfer(OT). Every time a piece of data is added, the resources consumed by GC and OT will increase a lot. Therefore, it is unacceptable to process large-scale data in a single SMPC task. In this work, we propose a novel theory called SMPC Task Decomposition (SMPCTD), which can securely decompose a single SMPC task into multiple SMPC sub-tasks and multiple local tasks without leaking the original data. After decomposition, the computing time, memory and communication consumption drop sharply. We then decompose three machine learning (ML) SMPC tasks using our theory and implement them based on a hybrid protocol framework called ABY. Furthermore, we use incremental computation technique to expand the amount of data involved in these three SMPC tasks. The experimental results show that after decomposing these three SMPC tasks, the time, memory and communication consumption are not only greatly reduced, but also stabilized within a certain range. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Quantum-inspired Hash Function Based on Parity-dependent Quantum Walks with Memory

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Qing Tang, Xueming Lu, Songfeng Yang, Hao Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

In this paper, we develop a generic controlled alternate quantum walk model (called CQWM-P) by combining parity-dependent quantum walks with distinct arbitrary memory lengths and then construct a quantum-inspired hash function (called QHFM-P) based on this model. Numerical simulation shows that QHFM-P has near-ideal statistical performance and is on a par with the state-of-the-art hash functions based on discrete quantum walks in terms of sensitivity of hash value to message, diffusion and confusion properties, uniform distribution property, and collision resistance property. Stability test illustrates that the statistical properties of the proposed hash function are robust with respect to the coin parameters, and theoretical analysis indicates that QHFM-P has the same computational complexity as that of its peers. © 2023, CC BY.

关键词： Hash functions