检索结果-内蒙古大学图书馆

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Du, Xiaohu Wen, Ming Zhu, Jiahao Xie, Zifan Ji, Bin Liu, Huijun Shi, Xuanhua Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China College of Computer National University of Defense Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab HUST Wuhan430074 China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security HUST Wuhan430074 China JinYinHu Laboratory Wuhan430077 China Cluster and Grid Computing Lab HUST Wuhan430074 China

Code Pre-trained Models (CodePTMs) based vulnerability detection have achieved promising results over recent years. However, these models struggle to generalize as they typically learn superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities, resulting in poor performance in real-world scenarios beyond the training instances. To tackle this challenge, we introduce VulLLM, a novel framework that integrates multi-task learning with Large Language Models (LLMs) to effectively mine deep-seated vulnerability features. Specifically, we construct two auxiliary tasks beyond the vulnerability detection task. First, we utilize the vulnerability patches to construct a vulnerability localization task. Second, based on the vulnerability features extracted from patches, we leverage GPT-4 to construct a vulnerability interpretation task. VulLLM innovatively augments vulnerability classification by leveraging generative LLMs to understand complex vulnerability patterns, thus compelling the model to capture the root causes of vulnerabilities rather than overfitting to spurious features of a single task. The experiments conducted on six large datasets demonstrate that VulLLM surpasses seven state-of-the-art models in terms of effectiveness, generalization, and robustness. © 2024, CC BY.

关键词： Large datasets

Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xia, Tianle Ding, Liang Wan, Guojia Zhan, Yibing Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia JD Explore Academy China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging task. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements (brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art. Copyright © 2024, The Authors. All rights reserved.

关键词： Binary trees

PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Shengshan Zhang, Junwei Liu, Wei Hou, Junhui Li, Minghui Zhang, Leo Yu Jin, Hai Sun, Lichao School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China Cluster and Grid Computing Lab China National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Services Computing Technology and System Lab China City University of Hong Kong Hong Kong Deakin University Australia Lehigh University United States

Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their powerful capabilities, their robustness against adversarial attacks, which have been proven to be fatally malicious towards deep neural networks, remains unknown. In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes. In order to evaluate the robustness of the completion models, we propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones, while being completed as another object with totally different semantic information. Specifically, we minimize the representation discrepancy between the adversarial example and the target point set to jointly explore the adversarial point clouds in the geometry space and the feature space. Furthermore, to launch a stealthier attack, we innovatively employ the neighbourhood density information to tailor the perturbation constraint, leading to geometry-aware and distribution-adaptive modification for each point. Extensive experiments against different premier point cloud completion networks show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01. We conclude that existing completion models are severely vulnerable to adversarial examples, and state-of-the-art defenses for point cloud classification will be partially invalid when applied to incomplete and uneven point cloud data. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

A wong-zakai approximation for random slow manifolds with application to parameter estimation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： He, Ziying Zhang, Xinyong Jiang, Tao Liu, Xianming Center for Mathematical Sciences Huazhong University of Sciences and Technology Wuhan430074 China School of Mathematics and Statistics Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Sciences and Technology Wuhan430074 China Department of Mathematical Sciences Tsinghua University Beijing100084 China Collaborative Innovation Center of China Pilot Reform Exploration and Assessment Hubei Sub-Center Hubei University of Economics Wuhan430205 China

We study a Wong-Zakai approximation for the random slow manifold of a slow-fast stochastic dynamical system. We first deduce the existence of the random slow manifold about an approximation system driven by an integrated Ornstein-Uhlenbeck (O-U) process. Then we compute the slow manifold of the approximation system, in order to gain insights of the long time dynamics of the original stochastic system. By restricting this approximation system to its slow manifold, we thus get a reduced slow random system. This reduced slow random system is used to accurately estimate a system parameter of the original system. An example is presented to illustrate this *** Codes Primary: 37L55, 35R60, Secondary: 60H15, 58J65 Copyright © 2018, The Authors. All rights reserved.

关键词： Parameter estimation

APT traffic construction and detection method for virtual power plant

学校读者我要写书评

暂无评论

APT traffic construction and detection method for virtual po...

4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)

作者： Chang Liu Jin Wang Kailong Yu Qiuyu Lu June Li State Grid Hubei Electric Power Research Institute Wuhan People's Republic of China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan People's Republic of China

ISBN: (数字)9781837242924

As an important infrastructure of carbon peaking and carbon neutrality goals, virtual power plant (VPP) is likely to be the target of advanced persistent threat (APT), at the same time, the lack of APT data of VPP makes it difficult to realize APT detection in VPP. Thus, this paper proposed an APT traffic construction and detection method for VPP. Firstly, transfer component analysis (TCA) is used to select similar traffic features in different domains and reduce the difference in data distribution, so as to construct a traffic dataset suitable for APT detection in VPP. Then, based on sequence generative adversarial nets (SeqGAN), data augmentation is carried out on minority class traffic to improve the detection performance of APT in corresponding stages, forward and reverse min-max normalization is introduced to reduce the computational complexity and improve the data augmentation ability of SeqGAN. Finally, an APT detection method based on information gain-adaptive boosting (IG-Adaboost) is proposed to further improve the overall detection performance of APT. The experimental results show that the proposed method can construct traffic data suitable for APT detection in VPP, realize effective detection of VPP’s APT, and achieve the highest detection accuracy of 98.47%.

关键词：

Most Probable Transition Pathways and Maximal Likely Trajectories in a Genetic Regulatory System

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Cheng, Xiujun Wang, Hui Wang, Xiao Duan, Jinqiao Li, Xiaofan Center for Mathematical Sciences School of Mathematics and Statistics Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan430074 China School of Mathematics and Statistics Henan University Kaifeng475000 China Department of Applied Mathematics Illinois Institute of Technology Chicago60616 United States School of Mathematics and Statistics Zhengzhou University Zhengzhou450001 China

We study the most probable transition pathways and maximal likely trajectories in a genetic regulation model of the transcription factor activator’s concentration evolution, with Gaussian noise and non-Gaussian stable Lévy noise in the synthesis reaction rate taking into account, respectively. We compute the most probable transition pathways by the Onsager-Machlup least action principle, and calculate the maximal likely trajectories by spatially maximizing the probability density of the system path, i.e., the solution of the associated nonlocal Fokker-Planck equation. We have observed the rare most probable transition pathways in the case of Gaussian noise, for certain noise intensity, evolution time scale and system parameters. We have especially studied the maximal likely trajectories starting at the low concentration metastable state, and examined whether they evolve to or near the high concentration metastable state (i.e., the likely transcription regime) for certain parameters, in order to gain insights into the transcription processes and the tipping time for the transcription likely to occur. This enables us: (i) to visualize the progress of concentration evolution (i.e., observe whether the system enters the transcription regime within a given time period);(ii) to predict or avoid certain transcriptions via selecting specific noise parameters in particular regions in the parameter space. Moreover, we have found some peculiar or counter-intuitive phenomena in this gene model system, including: (a) A smaller noise intensity may trigger the transcription process, while a larger noise intensity can not, under the same asymmetric Lévy noise. This phenomenon does not occur in the case of symmetric Lévy noise;(b) The symmetric Lévy motion always induces transition to high concentration, but certain asymmetric Lévy motions do not trigger the switch to transcription. These findings provide insights for further experimental research, in order to achieve or to avoid sp

关键词： Trajectories

Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Hangtao Yao, Zeming Zhang, Leo Yu Hu, Shengshan Chen, Chao Liew, Alan Li, Zhetao School of Cyber Science and Engineering Huazhong University of Science and Technology China Swinburne University of Technology Australia Griffith University Australia National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China RMIT University Australia Xiangtan University China

Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisoning attacks that optimize the amplitude of malicious perturbations along certain prescribed directions to cause DoS, we propose a Flexible Model Poisoning Attack (FMPA) that can achieve versatile attack goals. We consider a practical threat scenario where no extra knowledge about the FL system (e.g., aggregation rules or updates on benign devices) is available to adversaries. FMPA exploits the global historical information to construct an estimator that predicts the next round of the global model as a benign reference. It then fine-tunes the reference model to obtain the desired poisoned model with low accuracy and small perturbations. Besides the goal of causing DoS, FMPA can be naturally extended to launch a fine-grained controllable attack, making it possible to precisely reduce the global accuracy. Armed with precise control, malicious FL service providers can gain advantages over their competitors without getting noticed, hence opening a new attack surface in FL other than DoS. Even for the purpose of DoS, experiments show that FMPA significantly decreases the global accuracy, outperforming six state-of-the-art attacks. © 2023, CC BY.

关键词： Federated learning

Securing Sdn/Nfv-Enabled Campus Networks with Software-Defined Perimeter-Based Zero-Trust Architecture

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Ruambo, Francis A. Zou, Deqing Lopes, Ivandro O. Yuan, Bin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Distributed System Security Wuhan China Hubei Engineering Research Center on Big Data Security Wuhan China National Engineering Research Center for Big Data Technology and System Wuhan China Services Computing Technology and System Lab Wuhan China Cluster and Grid Computing Lab Wuhan China Mbeya university of Science and Technology Mbeya131 Tanzania United Republic of Nucleo Operacional para a Sociedade de Informacao Cape Verde Songshan Laboratory Zhengzhou China

Network softwarization is a breakthrough in designing modern networks and providing numerous new network operations and services. This change is exemplified by Software Defined Networks (SDN) and Network Function Virtualization (NFV). As a result, the combination of SDN and NFV (SDN/NFV) frameworks and individual SDN and NFV frameworks have gained substantial traction in network security over the past decade, significantly supporting on-demand protection measures. However, the inherent security shortcomings of SDN, NFV, and SDN/NFV frameworks provide the fundamental issue in implementing security procedures via network softwarization. To solve this issue, we present a Software-Defined Perimeter (SDP)-powered Zero-Trust Architecture (ZTA) to improve security in the SDN/NFV-enabled campus network holistically. In addition to this, we also propose a threat model and quantitatively assess the suggested approach's performance and security. Furthermore, we highlight potential zero-trust network security function implementations in SDN/NFV-enabled infrastructure to increase protection for endpoint devices, network resources, and flows for detecting threats and responding effectively with minimal latency and overhead. © 2023, The Authors. All rights reserved.

关键词： Access control

Potential numerical techniques and challenges for atmospheric modeling

学校读者我要写书评

暂无评论

Potential numerical techniques and challenges for atmospheri...

作者： Li, J. Steppeler, J. Fang, F. Pain, C.C. Zhu, J. Peng, X. Dong, L. Li, Y. Tao, L. Leng, W. Wang, Y. Zheng, J. International Center for Climate and Environment Sciences Institute of Atmospheric Physics Chinese Academy of Sciences Beijing China Hamburg Germany Applied Modelling and Computation Group Department of Earth Science and Engineering Imperial College London London United Kingdom International Center for Climate and Environment Sciences Institute of Atmospheric Physics Chinese Academy of Sciences Department of Atmospheric Sciences University of Chinese Academy of Sciences Beijing China State Key Laboratory of Severe Weather Chinese Academy of Meteorological Sciences Beijing China State Key Laboratory of Numerical Modeling for Atmospheric Sciences and Geophysical Fluid Dynamics Institute of Atmospheric Physics Chinese Academy of Sciences Beijing China State Key Laboratory of Scientific and Engineering Computing Chinese Academy of Sciences Beijing China School of Mathematics and Statistics Henan University Kaifeng China Center for Excellence in Regional Atmospheric Environment Institute of Urban Environment Chinese Academy of Sciences Xiamen China