检索结果-内蒙古大学图书馆

Bi-Directional Transformers vs. word2vec: Discovering Vulnerabilities in Lifted Compiled Code

学校读者我要写书评

暂无评论

arXiv 2024年

作者： McCully, Gary A. Hastings, John D. Xu, Shengjie Fortier, Adam The Beacom College of Computer and Cyber Sciences Dakota State University MadisonSD United States Department of Cyber Intelligence and Information Operations College of Applied Science & Technology University of Arizona TucsonAZ United States College of Computing Georgia Institute of Technology AtlantaGA United States

Detecting vulnerabilities within compiled binaries is challenging due to lost high-level code structures and other factors such as architectural dependencies, compilers, and optimization options. To address these obstacles, this research explores vulnerability detection using natural language processing (NLP) embedding techniques with word2vec, BERT, and RoBERTa to learn semantics from intermediate representation (LLVM IR) code. Long short-term memory (LSTM) neural networks were trained on embeddings from encoders created using approximately 48k LLVM functions from the Juliet dataset. This study is pioneering in its comparison of word2vec models with multiple bidirectional transformers (BERT, RoBERTa) embeddings built using LLVM code to train neural networks to detect vulnerabilities in compiled binaries. Word2vec Skip-Gram models achieved 92% validation accuracy in detecting vulnerabilities, outperforming word2vec Continuous Bag of Words (CBOW), BERT, and RoBERTa. This suggests that complex contextual embeddings may not provide advantages over simpler word2vec models for this task when a limited number (e.g. 48K) of data samples are used to train the bidirectional transformer-based models. The comparative results provide novel insights into selecting optimal embeddings for learning compiler-independent semantic code representations to advance machine learning detection of vulnerabilities in compiled binaries. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code

学校读者我要写书评

暂无评论

arXiv 2024年

Ransomware and other forms of malware cause significant financial and operational damage to organizations by exploiting long-standing and often difficult-to-detect software vulnerabilities. To detect vulnerabilities such as buffer overflows in compiled code, this research investigates the application of unidirectional transformer-based embeddings, specifically GPT-2. Using a dataset of LLVM functions, we trained a GPT-2 model to generate embeddings, which were subsequently used to build LSTM neural networks to differentiate between vulnerable and non-vulnerable code. Our study reveals that embeddings from the GPT-2 model significantly outperform those from bidirectional models of BERT and RoBERTa, achieving an accuracy of 92.5% and an F1-score of 89.7%. LSTM neural networks were developed with both frozen and unfrozen embedding model layers. The model with the highest performance was achieved when the embedding layers were unfrozen. Further, the research finds that, in exploring the impact of different optimizers within this domain, the SGD optimizer demonstrates superior performance over Adam. Overall, these findings reveal important insights into the potential of unidirectional transformer-based approaches in enhancing cybersecurity defenses. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayer neural networks

Bird Swarm Algorithm with Fuzzy Min-Max Neural Network for Financial Crisis Prediction

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第10期73卷 1541-1555页

作者： K.Pradeep Mohan Kumar S.Dhanasekaran I.S.Hephzi Punithavathi P.Duraipandy Ashit Kumar Dutta Irina V.Pustokhina Denis A.Pustokhin Department of Computing Technologies Associate ProfessorSRM Institute of Science and TechnologyKattankulathur603203India Department of Information Technology Kalasalingam Academy of Research and Education626126India Department of Computer Science and Engineering Sphoorthy Engineering CollegeHyderabadTelangana501510India Department of Electrical and Electronics Engineering J B Institute of Engineering and TechnologyHyderabadTelangana500075India Department of Computer Science and Information System College of Applied SciencesAlMaarefa UniversityRiyadh11597Kingdom of Saudi Arabia Department of Entrepreneurship and Logistics Plekhanov Russian University of Economics117997MoscowRussia Department of Logistics State University of Management109542MoscowRussia

Financial crisis prediction(FCP)models are used for predicting or forecasting the financial status of a company or financial *** is considered a challenging issue in the financial *** and machine learning(ML)models can be employed for the design of accurate FCP *** numerous works have existed in the literature,it is needed to design effective FCP models adaptable to different *** study designs a new bird swarm algorithm(BSA)with fuzzy min-max neural network(FMM-NN)model,named BSA-FMMNN for *** major intention of the BSA-FMMNN model is to determine the financial status of a firm or *** presented BSA-FMMNN model primarily undergoes minmax normalization to transform the data into uniformity ***,k-medoid clustering approach is employed for the outlier removal ***,the classification process is carried out using the FMMNN model,and the parameters involved in it are tuned by the use of *** utilization of proficient parameter selection process using BSA demonstrate the novelty of the *** experimental result analysis of the BSA-FMMNN model is validated using benchmark dataset and the comparative outcomes highlighted the supremacy of the BSA-FMMNN model over the recent approaches.

关键词： Financial crisis predictive model machine learning outlier removal clustering metaheuristics

NONLINEAR RECONSTRUCTION FOR OPERATOR LEARNING OF PDES WITH DISCONTINUITIES

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lanthaler, Samuel Molinaro, Roberto Hadorn, Patrik Mishra, Siddhartha Computing and Mathematical Science California Institute of Technology PasadenaCA United States Seminar for Applied Mathematics ETH Zurich Zurich Switzerland

A large class of hyperbolic and advection-dominated PDEs can have solutions with discontinuities. This paper investigates, both theoretically and empirically, the operator learning of PDEs with discontinuous solutions. We rigorously prove, in terms of lower approximation bounds, that methods which entail a linear reconstruction step (e.g. DeepONet or PCA-Net) fail to efficiently approximate the solution operator of such PDEs. In contrast, we show that certain methods employing a nonlinear reconstruction mechanism can overcome these fundamental lower bounds and approximate the underlying operator efficiently. The latter class includes Fourier Neural Operators and a novel extension of DeepONet termed shift-DeepONet. Our theoretical findings are confirmed by empirical results for advection equation, inviscid Burgers' equation and compressible Euler equations of aerodynamics. © 2022, CC BY.

关键词： Advection

Utilizing Deep Learning in Smart Cities for Environmental Monitoring

学校读者我要写书评

暂无评论

Utilizing Deep Learning in Smart Cities for Environmental Mo...

2024 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Hoang, Dinh Cong Devi, Shova Koner, Jonardan Dhandayuthapani, Bala Choudhury, Susanta Kumar Sahoo, Deepali Rani Institute for South Asian West Asian and African Studies Department of Middle East & West Asia Studies India Amity Law School Lucknow Amity University Uttar Pradesh UP India Nicmar University Pune India College of Computing and Information Sciences University of Technology and Applied Sciences Department of It Shinas Campus Oman Gietu University Department of Civil Engineering Odisha Gunupur India Symbiosis Law School Noida India Pune India

ISBN: (纸本)9798331543617

The effectiveness and dependability of services provided by smart cities are significantly impacted by the significant and difficult issue of intrusion detection. Replay attacks, which weaken security via improper authentication in a smart city network, are among the most common threats to this infrastructure. For example, replay attacks have the potential to severely damage the smart city structure, leading to the loss of crucial data and substantial monetary losses. As a result, we have developed a model based on deep learning to predict where attacks in smart cities would be replayed. The proposed approach is intriguing since it uses deep learning-based models as an application to differentiate replay assaults and increase recognition accuracy. Replay attacks are simulated on a real-world smart city dataset, and the model's performance is assessed by using this dataset. Our findings demonstrate that the suggested model may reasonably accurately discriminate between normal and assault actions. Furthermore, our suggested model performs better than both deep learning and conventional classification models, per the findings. © 2024 IEEE.

关键词： Sustainable city

Tri-Band Endfire Antenna Array with Wide Angles of Beam-Scanning Capability for 5G mmWave Mobile Communication

学校读者我要写书评

暂无评论

Tri-Band Endfire Antenna Array with Wide Angles of Beam-Scan...

2023 IEEE International Workshop on Technologies for Defense and Security, TechDefense 2023

作者： Zidour, Ali Ayad, Mouloud Alibakhshikenari, Mohammad Basherlou, Haleh Jahanbakhsh Parchin, Naser Ojaroudi See, Chan Hwang University of m'Hamed Bougara Faculty of Technology Department of Electrical Systems Engineering Boumerdes Algeria University of Bouira Faculty of Sciences and Applied Sciences Department of Electrical Systems Bouira Algeria Universidad Carlos Iii de Madrid Leganés Department of Signal Theory and Communications Madrid Spain Edinburgh Napier University School of Computing Engineering and the Built Environment Edinburgh United Kingdom

ISBN: (纸本)9798350319392

In this paper, a novel multiband phased array antenna with endfire radiation pattern is designed at millimeter-wave (mmWave) frequency bands for 5G mobile applications. The proposed antenna element is a compact quasi-Yagi with a modified dipole driver to generate multiband operation, arranged on low-loss RO4003C materiel. The antenna array achieves excellent performance and covers wide frequency ranges of (24.15-29.8 GHz), (36.2-50 GHz) to support 5G NR bands;26, 28, 39 and the new allocated 48 GHz. The array can exhibit a maximum realized gain from 8.4 dBi to 11.8 dBi. Meanwhile, wide beam-scanning angles from - 68° to 65° at 28 GHz, from 40° to 41° at 39 GHz, and from - 33° to 35° at 48 GHz are realized. © 2023 IEEE.

关键词： Millimeter waves

Nonstationary Sparse Spectral Permanental Process

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Zicheng Zhang, Yixuan Ling, Zenan Fan, Xuhui Zhou, Feng Center for Applied Statistics School of Statistics Renmin University of China China China-Austria Belt and Road Joint Laboratory on AI and AM Hangzhou Dianzi University China School of EIC Huazhong University of Science and Technology China School of Computing Macquarie University Australia Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing China

Existing permanental processes often impose constraints on kernel types or stationarity, limiting the model’s expressiveness. To overcome these limitations, we propose a novel approach utilizing the sparse spectral representation of nonstationary kernels. This technique relaxes the constraints on kernel types and stationarity, allowing for more flexible modeling while reducing computational complexity to the linear level. Additionally, we introduce a deep kernel variant by hierarchically stacking multiple spectral feature mappings, further enhancing the model’s expressiveness to capture complex patterns in data. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of our approach, particularly in scenarios with pronounced data nonstationarity. Additionally, ablation studies are conducted to provide insights into the impact of various hyperparameters on model performance. Code is publicly available at https://***/SZC20/DNSSPP. © 2024, CC BY.

关键词：

Advancing Simulations of Coupled Electron and Phonon Nonequilibrium Dynamics Using Adaptive and Multirate Time Integration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yao, Jia Maliyov, Ivan Gardner, David J. Woodward, Carol S. Bernardi, Marco Department of Applied Physics and Materials Science Department of Physics California Institute of Technology PasadenaCA91125 United States Mathematics for Materials Modeling Institute of Mathematics Institute of Materials EPFL LausanneCH-1015 Switzerland Center for Applied Scientific Computing Lawrence Livermore National Laboratory LivermoreCA94550 United States

Electronic structure calculations in the time domain provide a deeper understanding of nonequilibrium dynamics in materials. The real-time Boltzmann equation (rt-BTE), used in conjunction with accurate interactions computed from first principles, has enabled reliable predictions of coupled electron and lattice dynamics. However, the timescales and system sizes accessible with this approach are still limited, with two main challenges being the different timescales of electron and phonon interactions and the cost of computing collision integrals. As a result, only a few examples of these calculations exist, mainly for two-dimensional (2D) materials. Here we leverage adaptive and multirate time integration methods to achieve a major step forward in solving the coupled rt-BTEs for electrons and phonons. Relative to conventional (non-adaptive) time-stepping, our approach achieves a 10x speedup for a given target accuracy, or greater accuracy by 3–6 orders of magnitude for the same computational cost, enabling efficient calculations in both 2D and bulk materials. This efficiency is showcased by computing the coupled electron and lattice dynamics in graphene up to ∼100 ps, as well as modeling ultrafast lattice dynamics and thermal diffuse scattering maps in a bulk material (silicon). These results open new opportunities for quantitative studies of nonequilibrium physics in materials. Copyright © 2024, The Authors. All rights reserved.

关键词： Boltzmann equation

A Survey of Fault Tolerance in Cloud computing

学校读者我要写书评

暂无评论

A Survey of Fault Tolerance in Cloud Computing

Systems, Advanced Technologies and Knowledge (ISSATK), International Symposium of

作者： Om Kolthoum Elhajjej Nouha Alyaoui Samia Dardouri Karim Chabir Research Laboratory Modeling Aanalysis Control of System (MACS) LR16ES22 National engineering school of Gabes (ENIG) University of Gabes Tunisia Computer Science and Telecommunications Department Laboratory of Modeling Analysis and Control of Systems (MACS) Higher Institute of Applied Sciences and Technology Zarroug Gafsa Gafsa University Tunisia Department of Computer Science College of Computing and Information Technology Shaqra University Saudi Arabia InnoV’COM Laboratory-Sup’Com University of Carthage Tunisia

ISBN: (数字)9798331540173

ISBN: (纸本)9798331540180

This paper is designed to provide a comprehensive overview of the latest developments in fault tolerance methods for cloud computing. Maintaining high availability and reliability of cloud environments requires fault tolerance. This paper explores fault tolerance in the context of cloud computing and discusses recent challenges and innovations in the field. Moreover, it examines the ongoing research efforts to improve fault-tolerance architectures. At the end of the paper, the paper presents system-level metrics that are relevant to fault tolerance.

关键词： Measurement Surveys Cloud computing Fault tolerance Technological innovation Scalability Fault tolerant systems Computer architecture Software Software reliability