检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhao, Jian Wang, Shenao Zhao, Yanjie Hou, Xinyi Wang, Kailong Gao, Peiming Zhang, Yuanchao Wei, Chen Wang, Haoyu Huazhong University of Science and Technology Wuhan China MYbank Ant Group Hangzhou China 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 China

The proliferation of pre-trained models (PTMs) and datasets has led to the emergence of centralized model hubs like Hugging Face, which facilitate collaborative development and reuse. However, recent security reports have uncovered vulnerabilities and instances of malicious attacks within these platforms, highlighting growing security concerns. This paper presents the first systematic study of malicious code poisoning attacks on pre-trained model hubs, focusing on the Hugging Face platform. We conduct a comprehensive threat analysis, develop a taxonomy of model formats, and perform root cause analysis of vulnerable formats. While existing tools like Fickling and ModelScan offer some protection, they face limitations in semantic-level analysis and comprehensive threat detection. To address these challenges, we propose MalHug, an end-to-end pipeline tailored for Hugging Face that combines dataset loading script extraction, model deserialization, in-depth taint analysis, and heuristic pattern matching to detect and classify malicious code poisoning attacks in datasets and models. In collaboration with Ant Group, a leading financial technology company, we have implemented and deployed MalHug on a mirrored Hugging Face instance within their infrastructure, where it has been operational for over three months. During this period, MalHug has monitored more than 705K models and 176K datasets, uncovering 91 malicious models and 9 malicious dataset loading scripts. These findings reveal a range of security threats, including reverse shell, browser credential theft, and system reconnaissance. This work not only bridges a critical gap in understanding the security of the PTM supply chain but also provides a practical, industry-tested solution for enhancing the security of pre-trained model hubs. Copyright © 2024, The Authors. All rights reserved.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

research on Domain Event Extraction Methods Based on Pre-Trained Model

Research on Domain Event Extraction Methods Based on Pre-Tra...

引用

2022 International Conference on Signal Processing, Computer Networks, and Communications, SPCNC 2022

作者： Meng, Fanshen Zhang, Yonggang Liu, Xuhong Liu, Xiulei Yu, Junyang Institute of Data Science and Information Analysis Beijing Information Science & Technology University Beijing100029 China Center for Information Research Academy of Military Sciences Beijing100142 China Beijing Key Laboratory of Network Culture and Digital Communication Beijing Information Science & Technology University Beijing100029 China Beijing Advanced Innovation Center of Materials Genome Engineering Beijing Information Science & Technology University Beijing100029 China School of Software Henan University Henan 475001 China

ISBN: (纸本)9781510664616

One of the important research directions in information extraction is event extraction(EE). It aims at recognizing event types and event arguments from natural language texts, which is an important technical basis for artificial intelligence application that serves for the information work in business, science and technology, military and other fields. Currently, data annotation samples of the relevant field based on encyclopedia and news data are relatively rare and lack relevant datasets. Therefore, there are only a few public research on the event extraction in the relevant intelligence field. By integrating universal information extraction, the event extraction method which use the pre-trained model for the relevant intelligence field can handle the problem of rare data annotation samples for the event extraction in the relevant field. By expanding training samples automatically, the context information of encyclopedia and news data is learnt effectively to extract relevant events from encyclopedia and news data. Compared with other event extraction methods, using precision, recall and F1 value as assessment indicators, in event recognition tasks, the value of F1 enhances 1.26%, and in argument recognition tasks, the value of F1 enhances 1.58%. The method can significantly boost the extraction performance in small samples shown in the experimental results. © 2023 SPIE.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

BADROBOT: JAILBREAKING EMBODIED LLMS IN THE PHYSICAL WORLD

arXiv

引用

arXiv 2024年

作者： Zhang, Hangtao Zhu, Chenyu Wang, Xianlong Zhou, Ziqi Yin, Changgan Li, Minghui Xue, Lulu Wang, Yichen Hu, Shengshan Liu, Aishan Guo, Peijin Zhang, Leo Yu National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Beihang University China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated task planning. However, a critical safety issue remains overlooked: could these embodied LLMs perpetrate harmful behaviors? In response, we introduce BADROBOT, a novel attack paradigm aiming to make embodied LLMs violate safety and ethical constraints through typical voice-based user-system interactions. Specifically, three vulnerabilities are exploited to achieve this type of attack: (i) manipulation of LLMs within robotic systems, (ii) misalignment between linguistic outputs and physical actions, and (iii) unintentional hazardous behaviors caused by world knowledge’s flaws. Furthermore, we construct a benchmark of various malicious physical action queries to evaluate BADROBOT’s attack performance. Based on this benchmark, extensive experiments against existing prominent embodied LLM frameworks (e.g., Voxposer, Code as Policies, and ProgPrompt) demonstrate the effectiveness of our BADROBOT. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Tracking Objects and Activities with Attention for Temporal Sentence Grounding

Tracking Objects and Activities with Attention for Temporal ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zeyu Xiong Daizong Liu Pan Zhou Jiahao Zhu 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 Wangxuan Institute of Computer Technology Peking University

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video. Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Specifically, we propose a novel Temporal Sentence Tracking Network (TSTNet), which contains (A) a Cross-modal Targets Generator to generate multi-modal templates and search space, filtering objects and activities, and (B) a Temporal Sentence Tracker to track multi-modal targets for modeling the targets’ behavior and to predict query-related segment. Extensive experiments and comparisons with state-of-the-arts are conducted on challenging benchmarks: Charades-STA and TACoS. And our TSTNet achieves the leading performance with a considerable real-time speed.

关键词： Solid modeling Target tracking Three-dimensional displays Grounding Benchmark testing Signal processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Towards Effective and Efficient Error Handling Code Fuzzing Based on Software Fault Injection

Towards Effective and Efficient Error Handling Code Fuzzing ...

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Kang Chen Ming Wen Haoxiang Jia Rongxin Wu Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology (HRUST) Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security Jin YinHu Laboratory Wuhan China School of Informatics Xiamen University Xiamen China School of Computer Science and Technology HUST Wuhan China Cluster and Grid Computing Lab

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

Software systems often encounter various errors or exceptions in practice, and thus proper error handling code is essential to ensure the reliability of software systems. Unfortunately, error handling code is often bug-prone, while sufficiently testing them is challenging as such code often cannot be triggered under normal conditions. Motivated by this, recent studies have proposed to leverage software fault injection (SFI) based fuzzing to discover potential bugs in complicated error handling code. Despite the promising results achieved, their effectiveness and efficiency are still compromised in practice due to the huge search space of error sites, inadequate fuzzing guidance, and the overhead induced by context-sensitive SFI. To achieve effective and efficient testing of error handling code, this study presents AFL-FI, which first utilizes a similarity-based method to identify suspicious error sites, and then incorporates the idea of error site coverage to guide the fuzzing process. Finally, the design of lightweight context-sensitive SFI enables AFL-FI to execute test cases efficiently. We evaluate AFL-FI on eight large-scale open-source projects, and the results show that it can outperform existing state-of-the-art fuzzing tools significantly in terms of branch code coverage. More importantly, AFL-FI has discovered 13 previously unknown bugs, and all of them have been confirmed while 12 of them have been fixed. Besides, our evaluation also demonstrates that all the key designs of AFL- F I are effective that contribute significantly to its overall performance.

关键词： Codes Computer bugs Fuzzing Software systems Software reliability Testing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning is All You Need: A Simple Token-Based Approach for Effective Code Clone Detection

Machine Learning is All You Need: A Simple Token-Based Appro...

引用

International Conference on Software engineering (ICSE)

作者： Siyue Feng Wenqi Suo Yueming Wu Deqing Zou Yang Liu Hai Jin Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab Jinyinhu Laboratory Wuhan China School of Cyber Science and Engineering HUST Wuhan China Nanyang Technological University Singapore School of Computer Science and Technology HUST Wuhan China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

As software engineering advances and the code demand rises, the prevalence of code clones has increased. This phenomenon poses risks like vulnerability propagation, underscoring the growing importance of code clone detection techniques. While numerous code clone detection methods have been proposed, they often fall short in real-world code environments. They either struggle to identify code clones effectively or demand substantial time and computational resources to handle complex clones. This paper introduces a code clone detection method namely Toma using tokens and machine learning. Specifically, we extract token type sequences and employ six similarity calculation methods to generate feature vectors. These vectors are then input into a trained machine learning model for classification. To evaluate the effectiveness and scalability of Toma, we conduct experiments on the widely used BigCloneBench dataset. Results show that our tool outperforms token-based code clone detectors and most tree-based clone detectors, demonstrating high effectiveness and significant time savings.

关键词： Codes Scalability Computational modeling Cloning Machine learning Detectors Feature extraction

来源：评论

学校读者我要写书评

暂无评论

3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack

3DHacker: Spectrum-based Decision Boundary Generation for Ha...

引用

International Conference on Computer Vision (ICCV)

作者： Yunbo Tao Daizong Liu Pan Zhou Yulai Xie Wei Du Wei Hu 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 Wangxuan Institute of Computer Technology Peking University

With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation. Previous 3D adversarial attackers either follow the white-box setting to iteratively update the coordinate perturbations based on gradients, or utilize the output model logits to estimate noisy gradients in the black-box setting. However, these attack methods are hard to be deployed in real-world scenarios since realistic 3D applications will not share any model details to users. Therefore, we explore a more challenging yet practical 3D attack setting, i.e., attacking point clouds with black-box hard labels, in which the attacker can only have access to the prediction label of the input. To tackle this setting, we propose a novel 3D attack method, termed 3D Hard-label attacker (3DHacker), based on the developed decision boundary algorithm to generate adversarial samples solely with the knowledge of class labels. Specifically, to construct the class-aware model decision boundary, 3DHacker first randomly fuses two point clouds of different classes in the spectral domain to craft their intermediate sample with high imperceptibility, then projects it onto the decision boundary via binary search. To restrict the final perturbation size, 3DHacker further introduces an iterative optimization strategy to move the intermediate sample along the decision boundary for generating adversarial point clouds with smallest trivial perturbations. Extensive evaluations show that, even in the challenging hard-label setting, 3DHacker still competitively outperforms existing 3D attacks regarding the attack performance as well as adversary quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Large-Scale Empirical Study on Semantic Versioning in Golang Ecosystem 23

A Large-Scale Empirical Study on Semantic Versioning in Gola...

引用

Proceedings of the 38th IEEE/ACM International Conference on Automated Software engineering

作者： Wenke Li Feng Wu Cai Fu Fan Zhou School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China AND Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Platform and Content Group Tencent Technology (Shenzhen) Co.Ltd Shenzhen China

ISBN: (纸本)9798350329964

Third-party libraries (TPLs) have become an essential component of software, accelerating development and reducing maintenance costs. However, breaking changes often occur during the upgrades of TPLs and prevent client programs from moving forward. Semantic versioning (SemVer) has been applied to standardize the versions of releases according to compatibility, but not all releases follow SemVer compliance. Lots of work focuses on SemVer compliance in ecosystems such as Java and JavaScript beyond Golang (Go for short). Due to the lack of tools to detect breaking changes and dataset for Go, developers of TPLs do not know if breaking changes occur and affect client programs, and developers of client programs may hesitate to upgrade dependencies in terms of breaking *** bridge this gap, we conduct the first large-scale empirical study in the Go ecosystem to study SemVer compliance in terms of breaking changes and their impact. In detail, we propose GoSVI (Go Semantic Versioning Insight) to detect breaking changes and analyze their impact by resolving identifiers in client programs and comparing their types with breaking changes. Moreover, we collect the first large-scale Go dataset with a dependency graph from GitHub, including 124K TPLs and 532K client programs. Based on the dataset, our results show that 86.3% of library upgrades follow SemVer compliance and 28.6% of no-major upgrades introduce breaking changes. Furthermore, the tendency to comply with SemVer has improved over time from 63.7% in 2018/09 to 92.2% in 2023/03. Finally, we find 33.3% of downstream client programs may be affected by breaking changes. These findings provide developers and users of TPLs with valuable insights to help make decisions related to SemVer.

关键词： semantic versioning

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：