检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Rahman, Md Abdur Shahriar, Hossain Wu, Fan Cuzzocrea, Alfredo Dept. of Intelligent Systems and Robotics University of West Florida PensacolaFL United States Center for Cybersecurity University of West Florida PensacolaFL United States Department of Computer Science Tuskegee University TuskegeeAL United States iDEA Lab University of Calabria Rende Italy

Large language models (LLMs) are renowned for their exceptional capabilities, and applying to a wide range of applications. However, this widespread use brings significant vulnerabilities. Also, it is well observed that there are huge gap which lies in the need for effective detection and mitigation strategies against malicious prompt injection attacks in large language models, as current approaches may not adequately address the complexity and evolving nature of these vulnerabilities in real-world applications. Therefore, this work focuses the impact of malicious prompt injection attacks which is one of most dangerous vulnerability on real LLMs applications. It examines to apply various BERT (Bidirectional Encoder Representations from Transformers) like multilingual BERT, DistilBert for classifying malicious prompts from legitimate prompts. Also, we observed how tokenizing the prompt texts and generating embeddings using multilingual BERT contributes to improve the performance of various machine learning methods: Gaussian Naive Bayes, Random Forest, Support Vector Machine, and Logistic Regression. The performance of each model is rigorously analyzed with various parameters to improve the binary classification to discover malicious prompts. Multilingual BERT approach to embed the prompts significantly improved and outperformed the existing works and achieves an outstanding accuracy of 96.55% by Logistic regression. Additionally, we investigated the incorrect predictions of the model to gain insights into its limitations. The findings can guide researchers in tuning various BERT for finding the most suitable model for diverse LLMs vulnerabilities. © 2024, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Modular Adaptive Aerial Manipulation under Unknown Dynamic Coupling Forces

arXiv

引用

arXiv 2024年

作者： Yadav, Rishabh Dev Dantu, Swati Pan, Wei Sun, Sihao Roy, Spandan Baldi, Simone Department of Computer Science The Univerity of Manchester United Kingdom Multi-robot systems group Faculty of Electrical Engineering Czech Technical University Prague Czech Republic Department of Cognitive Robotics Delft Univesrity of Technology Netherlands Robotics Research Center International Institute of Information Technology Hyderabad India School of Mathematics Southeast University Nanjing China

Successful aerial manipulation largely depends on how effectively a controller can tackle the coupling dynamic forces between the aerial vehicle and the manipulator. However, this control problem has remained largely unsolved as the existing control approaches either require precise knowledge of the aerial vehicle/manipulator inertial couplings, or neglect the state-dependent uncertainties especially arising during the interaction phase. This work proposes an adaptive control solution to overcome this long standing control challenge without any a priori knowledge of the coupling dynamic terms. Additionally, in contrast to the existing adaptive control solutions, the proposed control framework is modular, that is, it allows independent tuning of the adaptive gains for the vehicle position sub-dynamics, the vehicle attitude sub-dynamics, and the manipulator sub-dynamics. Stability of the closed loop under the proposed scheme is derived analytically, and real-time experiments validate the effectiveness of the proposed scheme over the state-of-the-art approaches. © 2024, CC BY.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Small Object Detection in the YOLOv8 model: A Comprehensive Analysis of the Optimized Model Head Adaptations

Enhancing Small Object Detection in the YOLOv8 model: A Comp...

引用

IEEE International Conference on Automation science and Engineering (CASE)

作者： Firozeh Solimani Angelo Cardellicchio Giovanni Dimauro Alba Mininni Maria Calabritto Roberto Di Biase Angelo Petrozza Stephan Summerer Francesco Cellini Vito Renò Institute of Intelligent Industrial Technologies and Systems for Advanced Manufacturing National Research Council of Italy Italy Department of Computer Science University of Bari Italy DiCEM Department University of Basilicata Matera Italy ALSIA Centro Ricerche Metapontum Agrobios Metaponto Italy

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Strawberry fruits, with their petite dimensions, possess an innate ability to blend into the surrounding foliage seamlessly. The size differences between the fruit and the background are such that they pose significant recognition challenges event to deep neural network models (DNN). With this in mind, this work is focused on exploring the latest model in the YOLO family, specifically YOLOv8, to address the complexities of a dataset gathered via a high-throughput phenotyping platform. As such, this study proposed a comprehensive analysis of optimized model head adaptations to enhance the detection of small objects starting from the base YOLOv8 architecture. This optimization is pursued while retaining the effectiveness of the model in identifying larger fruits and flowers. This optimization is poised to yield positive effects and contribute to more accurate and robust detection results on the proposed dataset.

关键词： YOLO Adaptation models Analytical models Artificial neural networks Flowering plants Data models Complexity theory Neck Standards Optimization

来源：评论

学校读者我要写书评

暂无评论

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

Augmented Box Replay: Overcoming Foreground Shift for Increm...

引用

International Conference on computer Vision (ICCV)

作者： Yuyang Liu Yang Cong Dipam Goswami Xialei Liu Joost van de Weijer State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences University of Chinese Academy of Sciences South China University of Technology Computer Vision Center Barcelona VCIP CS Nankai University Department of Computer Science Universitat Autònoma de Barcelona

In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Constrained Online Nonconvex Optimization with Compressed Communication

arXiv

引用

arXiv 2025年

作者： Zhang, Kunpeng Xu, Lei Yi, Xinlei Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Mechanical Engineering University of Victoria VictoriaBCV8W 2Y2 Canada Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai201210 China Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper considers distributed online nonconvex optimization with time-varying inequality constraints over a network of agents. For a time-varying graph, we propose a distributed online primal–dual algorithm with compressed communication to efficiently utilize communication resources. We show that the proposed algorithm establishes an O(T max{1−θ1,θ1}) network regret bound and an O(T 1−θ1/2) network cumulative constraint violation bound, where T is the number of iterations and θ1 ∈ (0, 1) is a user-defined trade-off parameter. When Slater’s condition holds (i.e, there is a point that strictly satisfies the inequality constraints at all iterations), the network cumulative constraint violation bound is reduced to O(T 1−θ1). These bounds are comparable to the state-of-the-art results established by existing distributed online algorithms with perfect communication for distributed online convex optimization with (time-varying) inequality constraints. Finally, a simulation example is presented to validate the theoretical results. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Community Detection in Large Hypergraphs

arXiv

引用

arXiv 2023年

作者： Ruggeri, Nicolò Contisciani, Martina Battiston, Federico De Bacco, Caterina Max Planck Institute for Intelligent Systems Cyber Valley Tübingen72076 Germany Department of Computer Science ETH Zürich8004 Switzerland Department of Network and Data Science Central European University Vienna1100 Austria

Hypergraphs, describing networks where interactions take place among any number of units, are a natural tool to model many real-world social and biological systems. In this work we propose a principled framework to model the organization of higher-order data. Our approach recovers community structure with accuracy exceeding that of currently available state-of-the-art algorithms, as tested in synthetic benchmarks with both hard and overlapping ground-truth partitions. Our model is flexible and allows capturing both assortative and disassortative community structures. Moreover, our method scales orders of magnitude faster than competing algorithms, making it suitable for the analysis of very large hypergraphs, containing millions of nodes and interactions among thousands of nodes. Our work constitutes a practical and general tool for hypergraph analysis, broadening our understanding of the organization of real-world higher-order systems. © 2023, CC BY-NC-SA.

关键词： Biological systems

来源：评论

学校读者我要写书评

暂无评论

Development of a VS ultrasound diagnostic system with image evaluation functions 11

Development of a VS ultrasound diagnostic system with image ...

引用

11th IEEE Global Conference on Consumer Electronics, GCCE 2022

作者： Zhou, Jiayi Koizumi, Norihiro Nishiyama, Yu Tsumura, Ryosuke Tsukihara, Hiroyuki Matsumoto, Naoki The University of Electro-Communications Department of Mechanical and Intelligent Systems Tokyo Japan The University of Electro-Communications Department of Computer and Network Engineering Tokyo Japan Health and Medical Research Institute National Institute of Advanced Industrial Science and Technology Tokyo Japan The University of Tokyo Graduate School of Engineering Tokyo Japan Nihon University Department of Gastroenterology and Hepatology Tokyo Japan

ISBN: (纸本)9781665492324

An inevitable feature of ultrasound-based diagnoses is that the quality of the ultrasound images produced depends directly on the skill of the physician operating the probe. This is because physicians have to constantly adjust the probe position to obtain a cross-section of the target organ, which is constantly shifting due to patient respiratory motions. Therefore, we developed an ultrasound diagnostic robot that works in cooperation with a visual servo system based on deep learning that will help alleviate the burdens imposed on physicians. Two different image processing methods (BiSeNet V2) were used to detect the target kidney location, as well as to evaluate the appropriateness of the obtained ultrasound images (ResNet 50) in developed system. © 2022 IEEE.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

Confidence Estimation Based on the Explanations of Model’s Predictions

Confidence Estimation Based on the Explanations of Model’s ...

引用

Neuromorphic Computing (ICNC), International Conference on

作者： Kaiyue Wu Changwu Huang Xin Yao Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

Estimating the confidence of a machine learning (ML) model plays an important role in minimizing undesirable outcomes and safety risks when using ML models in the real world, especially in high-stake application scenarios. However, the majority of existing confidence estimation methods do not work well without incorporating internal information from the model, such as the gradients, internal representations or checkpoints of its training process, which might compromise the security of the model. To alleviate such limitations, we intend to design a reliable confidence estimation method that requires as little internal model information as possible, yet precisely detecting uncertain samples for the model. In this work, we propose a confidence estimation approach that learns the confidence criterion (that is, the true class probability, TCP) based on the explanations of model’s predictions. The proposed approach utilizes the knowledge learned in the model with the leverage of the explanations for model’s prediction rather than directly extracting internal information of the model, so that it can be adopted in a wide range of applications. Several experiments, including experiments on different datasets, different models and non-IID (independent and identically distributed) test datasets, are conducted to examine the effectiveness of our confidence estimation method. The experimental results show that our proposed approach provides a reliable confidence estimation and generally performs better than the compared methods, especially in the capability of recognizing when a ML model makes errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-Convex Potential Games for Finding Global Solutions to Sensor Network Localization

Non-Convex Potential Games for Finding Global Solutions to S...

引用

European Control Conference (ECC)

作者： Gehui Xu Guanpu Chen Yiguang Hong Baris Fidan Thomas Parisini Karl H. Johansson Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Control Science and Engineering Tongji University Shanghai China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai China Department of Mechanical and Mechatronics Engineering University of Waterloo Waterloo ON Canada Department of Electrical and Electronic Engineering Imperial College London London UK Department of Engineering and Architecture University of Trieste Trieste Italy

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

Sensor network localization (SNL) problems require determining the physical coordinates of all sensors in a network. This process relies on the global coordinates of anchors and the available measurements between non-anchor and anchor nodes. Attributed to the intrinsic non-convexity, obtaining a globally optimal solution to SNL is challenging, as well as implementing corresponding algorithms. In this paper, we formulate a non-convex multi-player potential game for a generic SNL problem to investigate the identification condition of the global Nash equilibrium (NE) therein, where the global NE represents the global solution of SNL. We employ canonical duality theory to transform the non-convex game into a complementary dual problem. Then we develop a conjugation-based algorithm to compute the stationary points of the complementary dual problem. On this basis, we show an identification condition of the global NE: the stationary point of the proposed algorithm satisfies a duality relation. Finally, simulation results are provided to validate the effectiveness of the theoretical results.

关键词： Location awareness Coordinate measuring machines Simulation Current measurement Noise Europe Games

来源：评论

学校读者我要写书评

暂无评论

Feature Attribution Explanation to Detect Harmful Dataset Shift

Feature Attribution Explanation to Detect Harmful Dataset Sh...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ziming Wang Changwu Huang Xin Yao Research Institute of Trustworthy Autonomous Systems (RITAS) Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Detecting whether a distribution shift has occurred in the dataset is a critical aspect when implementing machine learning models, as even a small shift in the data distribution may largely affect the performance of a machine learning model and thus cause the deployed model to fail. In this work, we focus on detecting harmful dataset shifts, i.e., shifts that are detrimental to the performance of the machine learning model. The existing methods usually detect whether there is a shift between two datasets according to the following framework: first carrying out dimensionality reduction on the datasets, then determining whether dataset shift exists according to the two-sample statistical test(s) on the reduced datasets. The knowledge contained in the model trained on the dataset is not utilized in the above described dataset shift detection framework. To address this, this paper proposes to take advantage of explainable artificial intelligence (XAI) techniques to exploit the knowledge in trained models when detecting harmful dataset shifts. Specifically, we employ the feature attribution explanation (FAE) method to capture the knowledge in the model and combine it with a widely-used two-sample test method, i.e., maximum mean difference (MMD), to detect harmful dataset shifts. The experimental results on more than twenty different shifts in three widely used image datasets demonstrate that the proposed method is more effective in identifying harmful dataset shifts than existing methods. Moreover, experiments on several different models show that the method is robust and effective over different models, i.e., its detection performance is not sensitive to the model used.

关键词：

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：