检索结果-内蒙古大学图书馆

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Kohli, Varun Kohli, Bhavya Aman, Muhammad Naveed Sikdar, Biplab National University of Singapore Department of Electrical and Computer Engineering Singapore Center for Machine Intelligence and Data Science Indian Institute of Technology Bombay India School of Computing University of Nebraska-Lincoln United States

ISBN: (纸本)9798331508050

Consumer Internet of Things (IoT) networks have gained widespread popularity due to their convenience, automation, and security provisions in personal and home environments. Ubiquitous resource-constrained devices, however, are plagued with security issues that often arise from firmware-related issues and their propagated effects. While various studies on firmware attestation are available, they require firmware copies, specific hardware, and complex computation on the IoT device. This paper presents a study on the application of Graph Transformer Networks (GTN) in verifying the firmware integrity of consumer IoT swarms using SRAM as an attestation feature. The proposed method achieves an overall 0.99 accuracy on authentic samples from development and physical twin networks, 0.99 on malware, and 0.97 on propagated misbehavior at a ∼ 10^-4 second inference latency on a laptop CPU. © 2025 IEEE.

关键词： Anomaly Detection Firmware Attestation Graph Neural Network (GNN) Internet of Things (IoT) Malware Detection Security Swarm Attestation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Jailbreak Attacks via Compliance-Refusal-Based Initialization

arXiv

引用

arXiv 2025年

作者： Levi, Amit Himelstein, Rom Nemcovsky, Yaniv Mendelson, Avi Baskin, Chaim Department of Computer Science Technion - Israel Institute of Technology Department of Data and Decision Science Technion - Israel Institute of Technology School of Electrical and Computer Engineering Ben-Gurion University of The Negev

Jailbreak attacks aim to exploit large language models (LLMs) and pose a significant threat to their proper conduct;they seek to bypass models’ safeguards and often provoke transgressive behaviors. However, existing automatic jailbreak attacks require extensive computational resources and are prone to converge on suboptimal solutions. In this work, we propose Compliance Refusal Initialization (CRI), a novel, attack-agnostic framework that efficiently initializes the optimization in the proximity of the compliance subspace of harmful prompts. By narrowing the initial gap to the adversarial objective, CRI substantially improves adversarial success rates (ASR) and drastically reduces computational overhead—often requiring just a single optimization step. We evaluate CRI on the widely-used AdvBench dataset over the standard jailbreak attacks of GCG and AutoDAN. Results show that CRI boosts ASR and decreases the median steps to success by up to ×60. The project page, along with the reference implementation, is publicly available at . © 2025, CC BY-NC-SA.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Liver Disease Classification by Analysing Salient Features of Liver Function Test (LFT): An Explainable Machine Learning Approach

Liver Disease Classification by Analysing Salient Features o...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Anmol Agrawal Tirtharaj Sen Amar Sinha Pranabes Gangopadhyay Department of Electronics and Communication Engineering IIIT Naya Raipur India Data Science Virtusa Consulting Services Pvt. Ltd. Hyderabad India Department of Computer Science and Engineering IIIT Naya Raipur India Department of Computer Science and Engineering Asansol Engineering College India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

The liver is a vital organ that performs numerous crucial functions for overall health. However, liver malfunctions can prove fatal, underscoring the urgency of early disease detection. Traditional liver disease classification methods are hampered by complexity and variability, prompting the adoption of Machine Learning (ML) algorithms. In this study, we endeavor to develop a soft computing model leveraging Liver Function Tests (LFTs) for accurate disease classification. Notably, our analysis revealed L2 regularized XGBoost as the standout performer, achieving an impressive 99.94% accuracy. Moreover, our investigation delved deeper into the root causes of liver diseases, shedding light on their underlying mechanisms and relationship to liver function components. By integrating Explainable AI (XAI), our model ensures transparency and provides invaluable insights for informed decision-making. Our project aims to deliver an efficient and robust classification model for liver diseases, poised to significantly impact early detection and patient outcomes.

关键词： Technological innovation Accuracy Machine learning algorithms Liver diseases Explainable AI Computational modeling Decision making Complexity theory Classification algorithms Diseases

来源：评论

学校读者我要写书评

暂无评论

MetaDE: Evolving Differential Evolution by Differential Evolution

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Chen, Minyang Feng, Chenchen Cheng, Ran Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China The Hong Kong Polytechnic University Department of Data Science and Artificial Intelligence The Department of Computing Hong Kong

As a cornerstone in the Evolutionary Computation (EC) domain, Differential Evolution (DE) is known for its simplicity and effectiveness in handling challenging black-box optimization problems. While the advantages of DE are well-recognized, achieving peak performance heavily depends on its hyperparameters such as the mutation factor, crossover probability, and the selection of specific DE strategies. Traditional approaches to this hyperparameter dilemma have leaned towards parameter tuning or adaptive mechanisms. However, identifying the optimal settings tailored for specific problems remains a persistent challenge. In response, we introduce MetaDE, an approach that evolves DE's intrinsic hyperparameters and strategies using DE itself at a meta-level. A pivotal aspect of MetaDE is a specialized parameterization technique, which endows it with the capability to dynamically modify DE's parameters and strategies throughout the evolutionary process. To augment computational efficiency, MetaDE incorporates a design that leverages parallel processing through a GPU-accelerated computing framework. Within such a framework, DE is not just a solver but also an optimizer for its own configurations, thus streamlining the process of hyperparameter optimization and problem-solving into a cohesive and automated workflow. Extensive evaluations on the CEC2022 benchmark suite demonstrate MetaDE's promising performance. Moreover, when applied to robot control via evolutionary reinforcement learning, MetaDE also demonstrates promising performance. © 1997-2012 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Avoiding exp(Rmax) scaling in RLHF through Preference-based Exploration

arXiv

引用

arXiv 2025年

作者： Chen, Mingyu Chen, Yiding Sun, Wen Zhang, Xuezhou Department of Electrical & Computer Engineering Boston University United States Department of Computer Science Cornell University United States Faculty of Computing & Data Sciences Boston University United States

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for large language model (LLM) alignment. This paper studies the setting of online RLHF and focus on improving sample efficiency. All existing algorithms in online RLHF, whether doing passive exploration or active exploration, suffer from a sample complexity that scales exponentially with the scale of the reward function. This fundamental limitation hinders their effectiveness in scenarios with heavily skewed preferences, e.g. questions with a unique correct solution. To address this, we introduce Self-Exploring Preference-Incentive Online Preference Optimization (SE-POPO), an online RLHF algorithm that for the first time achieves a sample complexity that scales polynomially with the reward scale, answering an open problem raised by Xie et al. (2024). Theoretically, we demonstrate that the sample complexity of SE-POPO dominates that of existing exploration algorithms. Empirically, our systematic evaluation confirms that SE-POPO is more sample-efficient than both exploratory and non-exploratory baselines, in two primary application scenarios of RLHF as well as on public benchmarks, marking a significant step forward in RLHF algorithm design. The code is available at https://***/MYC000801/SE-POPO. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

OHMiner: An Overlap-centric System for Efficient Hypergraph Pattern Mining 25

OHMiner: An Overlap-centric System for Efficient Hypergraph ...

引用

20th European Conference on computer Systems, EuroSys 2025, co-located 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2025

作者： Qi, Hao Luo, Kang He, Ligang Zhang, Yu Cai, Minzhi Dai, Jingxin He, Bingsheng Jin, Hai Zhang, Zhan Zhao, Jin Yue, Hengshan Yu, Hui Liao, Xiaofei National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science University of Warwick United Kingdom National University of Singapore Singapore Zhejiang Lab China Jilin University China

ISBN: (纸本)9798400711961

Hypergraph Pattern Mining (HPM) aims to identify all the instances of user-interested subhypergraphs (patterns) in hypergraphs, which has been widely used in various applications. However, existing solutions either need significant enumeration overhead because they extend subhypergraphs at the granularity of vertices, or suffer from massive redundant computations because they often need to repeatedly fetch and process the same incident hyperedges for different vertices. This paper presents an overlap-centric system named OHMiner to efficiently support HPM. OHMiner proposes an overlap-centric execution model to determine the subhypergraphs isomorphism through computing and comparing overlaps among hyperedges using set operations. This model aims to efficiently handle the vertices that collectively share the same incident hyperedges. To automatically and precisely retrieve an arbitrary pattern’s overlapping semantics without performing redundant set computations, OHMiner further proposes a redundancy-free compiler, which constructs an Overlap Intersection Graph (OIG) for the pattern, optimizes the OIG, and generates an overlap-centric execution plan to guide the procedure of HPM. Moreover, OHMiner designs an overlap-centric parallel execution engine, which adopts an incremental overlap-pruned approach to fast validate candidates for HPM. Additionally, it proposes a degree-aware data store to support efficient generation of candidates. Through evaluating OHMiner on a broad range of real-world hypergraphs with various patterns, our experimental results show that OHMiner outperforms the state-of-the-art HPM system by 5.4×-22.2×. © 2025 Copyright held by the owner/author(s).

关键词： Compiler

来源：评论

学校读者我要写书评

暂无评论

Navigating the Complexities of Municipal Waste Management: Enhancing Cost Prediction for Sustainable Urban Solutions 1st

Navigating the Complexities of Municipal Waste Management: E...

引用

1st International Research Conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Minu, M.S. Samal, Tushar Bisani, Khushi Tewari, Aishwarya Department of Computer Science and Engineering with Specialisation in Big Data Analytics SRM Institute of Science and Technology Ramapuram Campus Chennai India

ISBN: (纸本)9783031823824

The escalating rates of municipal waste generation in urban areas worldwide present a critical challenge for effective waste management. This paper examines the complexities surrounding municipal waste management, emphasizing the significance of accurate cost prediction for sustainable decision-making. Urbanization, driven by population growth and rising standards of living, intensifies waste generation, while shifts in consumption patterns further complicate waste management efforts. Environmental concerns and regulatory pressures mandate innovative waste reduction strategies. Accurate cost prediction is paramount for budgetary planning and resource allocation, enabling proactive measures to optimize operational efficiency and mitigate financial risks. Emerging methodologies, including data analytics and predictive modeling, offer promising avenues for enhancing cost prediction accuracy by capturing the multifaceted drivers of cost variability. By leveraging these methodologies, decision-makers can forecast municipal waste management costs with precision, informing strategic initiatives to foster sustainable waste management practices in urban areas. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

data Augmentation for Cognitive Behavioral Therapy: Leveraging ERNIE Language Models using Artificial Intelligence

Data Augmentation for Cognitive Behavioral Therapy: Leveragi...

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Bosubabu Sambana Kondreddygari Archana Suram Indhra Sena Reddy Shaik Meethaigar Jameer Basha Shaik Karishma Department of Computer Science and Engineering (Data Science) School of Computing Mohan Babu University Tirupati India Department of Information Technology Sree Vidyanikethan Engineering College Tirupati India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Cognitive Behavioral Therapy (CBT) is a proven approach for addressing the irrational thought patterns associated with mental health disorders, but its effectiveness relies on accurately identifying cognitive pathways to provide targeted treatment. In today's digital age, individuals often express negative emotions on social media, where they may reveal cognitive distortions, and in severe cases, exhibit suicidal tendencies. However, there is a significant gap in methodologies designed to analyze these cognitive pathways, which could be critical for psychotherapists aiming to deliver timely and effective interventions in online environments. Cognitive Behavioral Therapy (CBT) framework leveraging acceptance, commitment and data augmentation to categorize and address both textual and visual content as positive or negative. Specifically, the system employs BERT, RoBERTa for Sentiment Analysis and T5, PEGASUS for Text Summarization, mT5 for Text Translation in Multiple Languages focusing on detecting negative emotions and cognitive distortions within social media data. While existing models are primarily designed to identify negative thoughts, the proposed system goes beyond this by predicting additional negative side effects and other potential mental health disorders likes Phobias, Eating Disorders. This enhancement allows for a more comprehensive understanding and intervention strategy, offering psychotherapists a powerful tool for early detection and treatment of various psychological issues.

关键词： Sentiment analysis Social networking (online) Mood Anxiety disorders Medical treatment Mental health data augmentation Distortion Classification algorithms Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Dimensionality and dynamics for next-generation artificial neural networks

Patterns

引用

Patterns 2025年

作者： Wang, Ge Fan, Feng-Lei Department of Biomedical Engineering Department of Electrical Computer and Systems Engineering Department of Computer Science Center for Computational Innovations Biomedical Imaging Center Center for Biotechnology and Interdisciplinary Studies Rensselaer Polytechnic Institute TroyNY United States Department of Data Science City University of Hong Kong Kowloon Hong Kong

The recent awarding of the Nobel Prize in Physics to Geoffrey E. Hinton and John J. Hopfield highlights their profound impact on artificial neural networks. In this perspective, we explore how their foundational insights can drive the advancement of next-generation artificial intelligence (AI) models. We propose expanding beyond conventional architectures by introducing dimensionality through intra-layer links and dynamics via feedback loops. Network height and additional dimensions, alongside traditional width and depth, enhance learning capabilities, while entangled loops across scales induce emergent behaviors akin to phase transitions in physics. We discuss how these principles extend beyond transformers, fostering a new paradigm of intelligence inspired by physics-driven models and biological cognition mechanisms. © 2025 The Author(s)

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

WebShield 5.0: Harnessing AI and NLP to combat web threats in Industry 5.0

引用

Alexandria engineering Journal 2025年 127卷 677-689页

作者： Verma, Priyanka Newe, Thomas Vidyarthi, Ankit Gupta, Deepak Ali, Jabir Aldawsari, Hamad Breslin, John G. School of Computer Science University of Galway University road Galway H91 TK33 Ireland Department of Electronics and Computer Engineering University of Limerick Castletroy Limerick V94 T9PX Ireland Digital Engineering University of Limerick Castletroy Limerick V94 T9PX Ireland Department of CSE&IT Jaypee Institute of Information Technology sector 62 Noida 201309 India Maharaja Agrasen Institute of Technology Delhi India School of Computer Science Engineering and Technology Bennett University Greater Noida Delhi India Department of Computer Science Haql University College University of Tabuk Tabuk Saudi Arabia Data Science Institute University of Galway University road Galway H91 TK33 Ireland

Industry 5.0 characterized by the integration of human intelligence and advanced technologies is inherently more connected and interdependent than previous industrial paradigms. This increased connectivity exposes to various web-based attacks and calls for strong security controls. To address the challenges and enhance attack detection, this paper introduces Ingress Manager (IM), a novel approach that amalgamates Natural Language Processing (NLP) with Machine Learning (ML) to mitigate web-based threats. By combining multimodal data and utilizing the Mayfly optimization algorithm for feature selection, IM carries out a thorough analysis for efficient web-based attack detection. Mayfly Optimization is considered to be a variation of Particle Swarm Optimization (PSO), combining the benefits of Firefly Algorithm, Genetic Algorithm (GA), and PSO. Experiments on the HTTP CSIC-2010 dataset show that this integration is effective, as evidenced by the notable gains in accuracy, precision, and F-score above baseline models. Notable performance metrics such as accuracy of 98.5753% along with thorough component analysis (ablation study) add deeper understanding to the proposed approach. The paper's contributions lie in its utilization of Industry 5.0 principles, the incorporation of Mayfly optimization for feature selection, and the innovative combination of NLP and ML for robust web-based attack detection. © 2025

关键词： AI Cybersecurity Industry 5.0 Mayfly optimization NLP Web-based attacks

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：