检索结果-内蒙古大学图书馆

Fitness Landscape Optimization Makes Stochastic Symbolic Search By Genetic programming Easier

IEEE Transactions on Evolutionary Computation 2024年

作者： Huang, Zhixing Mei, Yi Zhang, Fangfang Zhang, Mengjie Banzhaf, Wolfgang Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Michigan State University BEACON Center for the Study of Evolution in Action and Ecology Evolution and Behavior Program Department of Computer Science and Engineering East LansingMI48864 United States

Searching for symbolic models plays an important role in a wide range of domains such as neural architecture search and automatic program synthesis. Genetic programming is a promising stochastic method for searching effective symbolic models within an acceptable time. The genetic programming performance is closely related to the hardness of the fitness landscape. A better fitness landscape with less local optima normally implies that it is easier to search for better solutions. In recent years, there have been many studies enhancing genetic programming performance by forming better fitness landscapes. However, the better design of the fitness landscape highly relies on specific domain knowledge and consumes a lot of expert effort. This paper proposes a fitness landscape optimization method to automatically design better fitness landscapes for genetic programming search than the manually designed ones. We optimize the landscapes by optimizing the neighborhood structures of symbolic solutions. We verify the effectiveness of the proposed method in both supervised learning and combinatorial optimization problems. The results show that the proposed method significantly reduces the hardness of fitness landscapes. By simply searching against the automatically optimized fitness landscapes, a genetic programming method can have a very competitive performance with state-of-the-art methods. © 1997-2012 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details

arXiv

引用

arXiv 2023年

作者： Hwang, Inwoo Kim, Hyeonwoo Kim, Young Min Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects. Guided by a reference image and text descriptions, our pipeline adds detailed texture on labeled 3D geometries in the room such that the generated colors respect the hierarchical structure or semantic parts that are often composed of similar materials. Instead of applying flat stylization on the entire scene at a single step, we obtain weak semantic cues from geometric segmentation, which are further clarified by assigning initial colors to segmented parts. Then we add texture details for individual objects such that their projections on image space exhibit feature embedding aligned with the embedding of the input. The decomposition makes the entire pipeline tractable to a moderate amount of computation resources and memory. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated datasets with high-quality textures designed by skillful artists. To the best of our knowledge, it is the first practical and scalable approach that can create detailed and realistic textures of the desired style that maintain structural context for scenes with multiple objects. © 2023, CC BY.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Learn2Evade: Learning-based generative model for evading PDF malware classifiers

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2021年第4期2卷 299-313页

作者： Bae, Ho Lee, Younghan Kim, Yohan Hwang, Uiwon Yoon, Sungroh Paek, Yunheung Department of Cyber Security EwhaWomans University Seoul03760 Korea Republic of Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Interdisciplinary Program in Bioinformatics Interdisciplinary Program in Artificial Intelligence Automation and Systems Research Institute Institute of NewMedia and Communications Institute of Engineering Research Seoul National University Seoul08826 Korea Republic of

Recent research has shown that a small perturbation to an input may forcibly change the prediction of a machine learning (ML) model. Such variants are commonly referred to as adversarial examples. Early studies have focused mostly on ML models for image processing and expanded to other applications, including those for malware classification. In this article, we focus on the problem of finding adversarial examples against ML-based portable document format (PDF) malware *** deem that our problem is more challenging than those againstMLmodels for image processing because of the highly complex data structure of PDF and of an additional constraint that the generated PDF should exhibit malicious behavior. To resolve our problem, we propose a variant of generative adversarial networks that generate evasive variant PDF malware (without any crash), which can be classified as benign by various existing classifiers yetmaintaining the original malicious behavior. Our model exploits the target classifier as the second discriminator to rapidly generate an evasive variant PDF with our new feature selection process that includes unique features extracted from malicious PDF files. We evaluate our technique against three representative PDF malware classifiers (Hidost 13, Hidost 16, and PDFrate-v2) and further examine its effectiveness with AntiVirus engines from VirusTotal. To the best of our knowledge, our work is the first to analyze the performance against the commercial AntiVirus engines. Our model finds, with great speed, evasive variants for all selected seeds against state-of-The-Art PDF malware classifiers and raises a serious security concern in the presence of adversaries. © 2021 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Improving Visual Prompt Tuning for Self-supervised Vision Transformers

arXiv

引用

arXiv 2023年

作者： Yoo, Seungryong Kim, Eunji Jung, Dahuin Lee, Jungbeom Yoon, Sungroh Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known as prompts, which steer the frozen pretrained ViTs. Although VPT has demonstrated its applicability with supervised vision transformers, it often underperforms with self-supervised ones. Through empirical observations, we deduce that the effectiveness of VPT hinges largely on the ViT blocks with which the prompt tokens interact. Specifically, VPT shows improved performance on image classification tasks for MAE and MoCo v3 when the prompt tokens are inserted into later blocks rather than the first block. These observations suggest that there exists an optimal location of blocks for the insertion of prompt tokens. Unfortunately, identifying the optimal blocks for prompts within each self-supervised ViT for diverse future scenarios is a costly process. To mitigate this problem, we propose a simple yet effective method that learns a gate for each ViT block to adjust its intervention into the prompt tokens. With our method, prompt tokens are selectively influenced by blocks that require steering for task adaptation. Our method outperforms VPT variants in FGVC and VTAB image classification and ADE20K semantic segmentation. The code is available at https://***/ryongithub/GatedPromptTuning. © 2023, CC BY-NC-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation

arXiv

引用

arXiv 2024年

作者： Oh, Yeongtak Lee, Jonghyun Choi, Jooyoung Jung, Dahuin Hwang, Uiwon Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Division of Digital Healthcare Yonsei University Korea Republic of

Test-time adaptation (TTA) addresses the unforeseen distribution shifts occurring during test time. In TTA, performance, memory consumption, and time consumption are crucial considerations. A recent diffusion-based TTA approach for restoring corrupted images involves image-level updates. However, using pixel space diffusion significantly increases resource requirements compared to conventional model updating TTA approaches, revealing limitations as a TTA method. To address this, we propose a novel TTA method that leverages an image editing model based on a latent diffusion model (LDM) and fine-tunes it using our newly introduced corruption modeling scheme. This scheme enhances the robustness of the diffusion model against distribution shifts by creating (clean, corrupted) image pairs and fine-tuning the model to edit corrupted images into clean ones. Moreover, we introduce a distilled variant to accelerate the model for corruption editing using only 4 network function evaluations (NFEs). We extensively validated our method across various architectures and datasets including image and video domains. Our model achieves the best performance with a 100 times faster runtime than that of a diffusion-based baseline. Furthermore, it is three times faster than the previous model updating TTA method that utilizes data augmentation, making an image-level updating approach more feasible. ∗ © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Object Driven Fuzzy Decision Model for Sugarcane Yield Prediction in Indonesia’s Sugar Industry

An Object Driven Fuzzy Decision Model for Sugarcane Yield Pr...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Ditdit Nugeraha Utama Muhammad Asrol Suharjito Christian Harito Napthaleni Muhammad Syafrudin Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia Industrial Engineering Department BINUS Graduate Program Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia Department of Artificial Intelligence and Data Science Sejong University Seoul South Korea

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

A sugarcane yield of one plantation area depends on several independent variables. Practically it is challenging to predict accurately by using conventional methods. This study aims to develop a decision model based on a combination of fuzzy logic and object-oriented methods to predict sugarcane yield. The research is conducted in four main stages, employing object-oriented methods for model design and fuzzy logic for model construction. Object and activity diagrams are used for the object-oriented model design. The fuzzy membership functions employed are a combination of trapezoidal and triangular shapes. The resulting decision model can simulate 2,225 data from plantation areas in Indonesia. Based on the 10 examples of plantation area data in Indonesia, plantation number one obtained the largest sugarcane yield, which was 4.79%, with a similarity value of 0.90 (when compared to manual calculations as its ground truth). This similarity value is a higher value when compared to the average similarity value, which is 0.89.

关键词： Fuzzy logic Seminars Shape Object oriented modeling Plantations Manuals Predictive models Sugar industry Intelligent systems Information technology

来源：评论

学校读者我要写书评

暂无评论

An Optimal Framework for SDN Based on Deep Neural Network

引用

computers, Materials & Continua 2022年第10期73卷 1125-1140页

作者： Abdallah Abdallah Mohamad Khairi Ishak Nor Samsiah Sani Imran Khan Fahad RAlbogamy Hirofumi Amano Samih M.Mostafa Department of Industrial Engineering School of Applied Technical Sciences German Jordanian UniversityAmman35247Jordan School of Electrical and Electronic Engineering Universiti Sains MalaysiaNibong Tebal14300Malaysia Center for Artificial Intelligence Technology Faculty of Information Science and TechnologyThe National University of Malaysia(UKM)Bangi43600SelangorMalaysia Department of Electrical Engineering University of Engineering and TechnologyPeshawar814Pakistan Turabah University College Computer Sciences ProgramTaif UniversityTaif21944Saudi Arabia Research Institute for Information Technology Kyushu UniversityFukuoka819-0395Japan Computer Science-Mathematics Department Faculty of ScienceSouth Valley UniversityQena83523Egypt

Software-defined networking(SDN)is a new paradigm that promises to change by breaking vertical integration,decoupling network control logic from the underlying routers and switches,promoting(logical)network control centralization,and introducing network ***,the controller is similarly vulnerable to a“single point of failure”,an attacker can execute a distributed denial of service(DDoS)attack that invalidates the controller and compromises the network security in *** address the problem of DDoS traffic detection in SDN,a novel detection approach based on information entropy and deep neural network(DNN)is *** approach contains a DNN-based DDoS traffic detection module and an information-based entropy initial inspection *** initial inspection module detects the suspicious network traffic by computing the information entropy value of the data packet’s source and destination Internet Protocol(IP)addresses,and then identifies it using the DDoS detection module based on *** assaults were found when suspected irregular traffic was *** reveal that the algorithm recognizes DDoS activity at a rate of more than 99%,with a much better accuracy *** false alarm rate(FAR)is much lower than that of the information entropy-based detection ***,the proposed framework can shorten the detection time and improve the resource utilization efficiency.

关键词： Deep neural network computer networks data security optimization

来源：评论

学校读者我要写书评

暂无评论

Application of Pose Estimation on Webcam for Fall Risk Assessment 8

Application of Pose Estimation on Webcam for Fall Risk Asses...

引用

Joint 8th International Conference on Digital Arts, Media and Technology and 6th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2023

作者： Uttama, Surapong Chumpoo, Patsakorn Rueangsirarak, Worasak Center of Excellence in Artificial Intelligence and Emerging Technologies School of Information Technology Mae Fah Luang University Chiang Rai Thailand School of Information Computer Science Program Technology Mae Fah Luang University Chiang Rai Thailand School of Information Technology Computer and Communication Engineering for Capacity Building Mae Fah Luang University Chiang Rai Thailand

ISBN: (纸本)9798350396546

Fall risk assessment is an effective and simple measure to evaluate the balance of people especially the elderly who are likely to have balance disorder. Lose of body balance increases a fall risk which could lead to severe damage to aging persons. In this paper, we propose to apply pose estimation technique based on PoseNet method to detect body joints from webcam's video for two types of fall risk assessment: Five Times Sit to Stand Test (FTSTS) and 30-Second Chair Stand Test (30CST). The experiments were performed with 17 volunteers concurrently with the measures of a healthcare expert. The results revealed that our proposed technique corresponds well with the measure of the expert evaluating by a Pearson correlation coefficient which equals to 0.903 and 0.980 for FTSTS and 30CST respectively. © 2023 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Membership Privacy-preserving GAN 33

Membership Privacy-preserving GAN

引用

33rd British Machine Vision Conference Proceedings, BMVC 2022

作者： Ha, Heonseok Hwang, Uiwon Jang, Jaehee Bae, Ho Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Cyber Security Ewha Womans University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

A membership inference attack (MIA) identifies if an instance was included in the victim model's train dataset. Without an appropriate defense mechanism, MIA can result in serious privacy breaches. Although several methods have been proposed to protect membership privacy in discriminative models, research into generative adversarial networks (GANs), remains insufficient despite their vulnerability to MIAs. In this study, we propose a membership privacy-preserving GAN (MP-GAN), which plays an additional adversarial game for membership privacy between an auxiliary membership inference network M and a GAN. M seeks to find out whether an instance belongs to the reference or train dataset, whereas the generator and discriminator of the GAN attempt to deceive M. Our theoretical analysis results demonstrate that the MP-GAN improves membership privacy by not learning sample-specific features. We perform extensive empirical evaluations to show that the MP-GAN can successfully defend against MIAs under advantageous scenarios to the attacker (for example, white-box access to networks and small training dataset size). Furthermore, we demonstrate that the MP-GAN has several advantages over other privacy-preserving GAN training techniques. © 2022. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards

arXiv

引用

arXiv 2024年

作者： Kwon, Hyeokjin Lee, Gunmin Lee, Junseo Oh, Songhwai Interdisciplinary Program in Artificial Intelligence ASRI Seoul National University Seoul08826 Korea Republic of Department of Electrical and Computer Engineering ASRI Seoul National University Seoul08826 Korea Republic of

In the realm of autonomous agents, ensuring safety and reliability in complex and dynamic environments remains a paramount challenge. Safe reinforcement learning addresses these concerns by introducing safety constraints, but still faces challenges in navigating intricate environments such as complex driving situations. To overcome these challenges, we present the safe constraint reward (Safe CoR) framework, a novel method that utilizes two types of expert demonstrations—reward expert demonstrations focusing on performance optimization and safe expert demonstrations prioritizing safety. By exploiting a constraint reward (CoR), our framework guides the agent to balance performance goals of reward sum with safety constraints. We test the proposed framework in diverse environments, including the safety gym, metadrive, and the real-world Jackal platform. Our proposed framework enhances the performance of algorithms by 39% and reduces constraint violations by 88% on the real-world Jackal platform, demonstrating the framework’s efficacy. Through this innovative approach, we expect significant advancements in real-world performance, leading to transformative effects in the realm of safe and reliable autonomous agents. Copyright © 2024, The Authors. All rights reserved.

关键词： Demonstrations

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：