检索结果-内蒙古大学图书馆

Asia and South Pacific Design Automation Conference

作者： Zhiteng Chao Xindi Zhang Junying Huang Jing Ye Shaowei Cai Huawei Li Xiaowei Li State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences CASTEST Co. Ltd State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences

Minimizing the testing cost is crucial in the context of the design for test (DFT) flow. In our observation, the test patterns generated by commercial ATPG tools in test compression mode still contain redundancy. To tackle this obstacle, we propose a post-flow static test compaction method that utilizes a partial fault dictionary instead of a full fault dictionary, and leverages a dedicated Pure-MaxSAT solver to re-compact the test patterns generated by commercial ATPG tools. We also observe that commercial ATPG tools offer a more comprehensive selection of candidate patterns for compaction in the “n-detect” mode, leading to superior compaction efficacy. In experiments on iscas89, ITC99, and open-source RISC-V CPU benchmarks, our method achieves an average reduction of 21.58% and a maximum of 29.93% in test cycles evaluated by commercial tools while maintaining fault coverage. Furthermore, our approach demonstrates improved performance compared with existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Can We Half the Work with Double Results: Rethinking Machine Learning Algorithms for Network Intrusion Detection System 9

Can We Half the Work with Double Results: Rethinking Machine...

引用

9th International Conference on Advanced Cloud and Big Data, CBD 2021

作者： Li, Shuren Lu, Yifei Li, Jingqi Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210096 China State Key Lab of Mathematical Engineering and Advanced Computing Wuxi214215 China

ISBN: (纸本)9781665407458

Machine Learning algorithms have been wildly applied in the intrusion detection system(IDS). However, in the IoT environment where the resources are limited and the flow data is of huge amount, we need more efficient and effective ML algorithms to train the detection models. Aiming to have comprehensive performance indicators of the ML algorithms, we compared 15 machine learning for both binary classification and Multi-classification under the criterion of IoT traffic circumstance by indicators in temporal dimension and spatial dimension. We finally suggested using non-linear algorithms, especially tree algorithms training or retraining models to identify malicious network traffic in the IoT IDS. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization

arXiv

引用

arXiv 2025年

作者： Liu, Chaohu Gui, Tianyi Liu, Yu Xu, Linli School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tongyi Lab China

Large Vision-Language Models (LVLMs), such as GPT-4o and LLaVA, have recently witnessed remarkable advancements and are increasingly being deployed in real-world applications. However, inheriting the sensitivity of visual neural networks, LVLMs remain vulnerable to adversarial attacks, which can result in erroneous or malicious outputs. While existing efforts utilize adversarial fine-tuning to enhance robustness, they often suffer from performance degradation on clean inputs. In this paper, we proposes AdPO, a novel adversarial defense strategy for LVLMs based on preference optimization. For the first time, we reframe adversarial training as a preference optimization problem, aiming to enhance the model’s preference for generating normal outputs on clean inputs while rejecting the potential misleading outputs for adversarial examples. Notably, AdPO achieves this by solely modifying the image encoder, e.g., CLIP ViT, resulting in superior clean and adversarial performance in a variety of downsream tasks. Considering that training involves large language models (LLMs), the computational cost increases significantly. We validate that training on smaller LVLMs and subsequently transferring to larger models can achieve competitive performance while maintaining efficiency comparable to baseline methods. Our comprehensive experiments confirm the effectiveness of the proposed AdPO, which provides a novel perspective for future adversarial defense research. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CoCGAN: Contrastive Learning for Adversarial Category Text Generation 29

CoCGAN: Contrastive Learning for Adversarial Category Text G...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Sheng, Xin Xu, Linli Xu, Yinlong Bao, Changcun Chen, Huang Ren, Bo Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tencent Youtu Lab China

The task of generating texts of different categories has attracted more and more attention in the area of natural language generation recently. Meanwhile, generative adversarial net (GAN) has demonstrated its effectiveness on text generation, and is further applied to category text generation in later works. Different from existing methods, which mainly consider the pairwise relations between the text embedding and the corresponding fixed one-hot class label (data-to-class relations), this paper proposes a novel Contrastive Category Generative Adversarial Net (CoCGAN) to incorporate contrastive learning into adversarial category text generation, considering more flexible data-to-class relations as well as relations between the multiple text embeddings in the same batch (data-to-data relations). The discriminator of CoCGAN discriminates the authenticity of given samples and optimizes a contrastive learning objective to capture both more flexible data-to-class relations and data-to-data relations among training samples. Accordingly, the generator tries to produce more realistic samples which can confuse the discriminator. Experimental results on both synthetic and real category text generation datasets demonstrate that CoCGAN can achieve significant improvements over the baseline category text generation models. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

BOBBLE: A Mixed Routing-Granularity Distributed Load Balancing for Data Center Networks 23

BOBBLE: A Mixed Routing-Granularity Distributed Load Balanci...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Xu, Zhengzhi Lu, Yifei Ma, Xu School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210096 China State Key Lab of Mathematical Engineering and Advanced Computing Wuxi214215 China

ISBN: (纸本)9781665494571

In current Datacenter Networks (DCNs), Equal-Cost Multipath (ECMP) is a default load balancing scheme. However, using ECMP may result in rapid growth of Flow Completion Time (FCT) due to its well-known drawbacks. In order to solve the problem of ECMP, load balancing schemes with per-packet granularity (such as RPS) and per-flowlet granularity (such as LetFlow) are proposed. These two different granularities have their own features, but there's no existing load balancing considering both their advantages. In this paper, we mix per-flowlet and per-packet in scheduling decisions and introduce the potential performance bottleneck in mixed granularities load balancing. Based on this idea, we propose a hybrid scheme for load balancing, referred to as BOBBLE. The key idea of BOBBLE is to distinguish elephant and mouse flows and schedule them with different granularity. We evaluate BOBBLE in simulations with NS-3. Experiment shows that BOBBLE slightly sacrifices elephant flows FCT but it is worthy because our results demonstrate that BOBBLE is a good trade-off which outperforms RPS and LetFlow in mouse flows FCT in both symmetric and asymmetric topology. © 2021 IEEE.

关键词： Data centers Network topology Smart cities Load management Routing Mice computer networks

来源：评论

学校读者我要写书评

暂无评论

GTN-Cell: Efficient Standard Cell Characterization Using Graph Transformer Network

GTN-Cell: Efficient Standard Cell Characterization Using Gra...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Lihao Liu Yunhui Li Beisi Lu Li Shang Fan Yang State Key Lab of Integrated Chips and Systems School of Microelectronics Fudan University Shanghai China State Key Lab of Integrated Chips and Systems School of Computer Science Fudan University Shanghai China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Lookup table (LUT)-based libraries of standard cell characterization is crucial to accurate static timing analysis (STA). However, with the continuous scaling of technology nodes and the increasing complexity of circuit designs, the traditional nonlinear delay model (NLDM) is progressively unable to meet the required accuracy for cell modeling. The current source model (CSM) offers a more precise characterization of cells at advanced nodes and is able to handle arbitrary electrical waveforms. However, the CSM is highly time-consuming because it requires extensive transistor-level simulations, posing severe challenges to efficient standard cell library design. This work presents GTN-Cell, an efficient graph transformer network (GTN)-based method for library-compatible LUT-based CSM waveform prediction of standard cell characterization. GTN-Cell represents the transistor-level structures of standard cells as graphs, learning the local structural information of each cell. By incorporating the transformer encoder into the model and embedding path-related positional encodings, GTN -Cell captures the global relationships between distant nodes within each cell. Compared with HSPICE, the GTN-Cell achieves an average error of 2.27% on predicted voltage waveforms among different standard cells and timing arcs while reducing the number of simulations by 70%.

关键词： Training Accuracy Voltage Predictive models Transformers Libraries Encoding Integrated circuit modeling Standards Load modeling

来源：评论

学校读者我要写书评

暂无评论

Tailor : Datacenter Load Balancing for Accelerating Distributed Deep Learning 9

Tailor : Datacenter Load Balancing for Accelerating Distribu...

引用

9th International Conference on Advanced Cloud and Big Data, CBD 2021

作者： Xu, Zhengzhi Lu, Yifei Li, Jingqi Ma, Xu Qian, Lei Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210096 China State Key Lab of Mathematical Engineering and Advanced Computing Wuxi214215 China

ISBN: (纸本)9781665407458

Accelerating Distributed Deep Learning draws increasing attention recently. Existing solutions like gradient compression, pipelining computation/communication, flow scheduling based on gradient disparities, neglect load balancing for Distributed Deep Learning (DDL) flows in DataCenter Network. In this paper, we review the PS traffic pattern in usual DDL training and propose that minimizing tail Flow Completion Time (FCT) of DDL flows is objective for DDL traffic Load Balancing. Besides, traffics of DDL differ from traditional DataCenter in temporal and spatial distribution. Current DCN Load Balancing become unadaptable to optimization requirements of DDL traffic, so we propose Tailor, a brand new load balancing scheme for DDL traffics training in DCN. Tailor is a solution without complex switch modification that sufficiently leverages the known parameter amount of DDL flows to discover congestion and reroutes by ECMP-like hash function to compensate bandwidth for slower flows. With large-scale simulation, we validate the effectiveness of Tailor. Tailor behaves well in both symmetric and asymmetric topology. It reduces time cost of DDL training by decreasing about 20-30% tail FCT than other load balancing mechanisms. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

GhostNets on Heterogeneous Devices via Cheap Operations

arXiv

引用

arXiv 2022年

作者： Han, Kai Wang, Yunhe Xu, Chang Guo, Jianyuan Xu, Chunjing Wu, Enhua Tian, Qi State Key Lab. of Computer Science ISCAS University of Chinese Academy of Sciences China Huawei Noah’s Ark Lab The University of Sydney Australia University of Macau China

Deploying convolutional neural networks (CNNs) on mobile devices is difficult due to the limited memory and computation resources. We aim to design efficient neural networks for heterogeneous devices including CPU and GPU, by exploiting the redundancy in feature maps, which has rarely been investigated in neural architecture design. For CPU-like devices, we propose a novel CPU-efficient Ghost (C-Ghost) module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features. The proposed C-Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. C-Ghost bottlenecks are designed to stack C-Ghost modules, and then the lightweight C-GhostNet can be easily established. We further consider the efficient networks for GPU devices. Without involving too many GPU-inefficient operations (e.g., depth-wise convolution) in a building stage, we propose to utilize the stage-wise feature redundancy to formulate GPU-efficient Ghost (G-Ghost) stage structure. The features in a stage are split into two parts where the first part is processed using the original block with fewer output channels for generating intrinsic features, and the other are generated using cheap operations by exploiting stage-wise redundancy. Experiments conducted on benchmarks demonstrate the effectiveness of the proposed C-Ghost module and the G-Ghost stage. C-GhostNet and G-GhostNet can achieve the optimal trade-off of accuracy and latency for CPU and GPU, respectively. Code is available at https: //***/huawei-noah/CV-Backbones. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CAD-IDS: A Cooperative Adaptive Distributed Intrusion Detection System with Fog Computing 25

CAD-IDS: A Cooperative Adaptive Distributed Intrusion Detect...

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

ISBN: (纸本)9781665405270

Nowadays, the IoT (internet of things) botnet has become a huge threat to network security. In response to this threat, we present a cooperative adaptive network intrusion detection system (IDS) framework with fog computing. The core part is cooperation detection architecture based on online adaptive machine learning algorithms. Our CAD-IDS aims to decrease the new attack detection time for all the IoT nodes and reduce the complexity of the cooperative IDS framework. The results of the experiment indicate that our CAD-IDS can detect IoT attacks efficiently and timely. Our ML code is available in https://***/LiQianchang/CAD-IDS-ML-Code. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems

arXiv

引用

arXiv 2025年

作者： Tian, Haoxiang Han, Xingshuo Wu, Guoquan Guo, An Zhou, Yuan Zhang, Jie Li, Shuo Wei, Jun Zhang, Tianwei Key Lab of System Software CAS State Key Lab of Computer Science ISCAS Beijing China University of CAS Beijing China Nanyang Technological University Singapore Continental-NTU Corporate Lab Singapore Nanjing Institute of Software Technology University of CAS Nanjing China Nanjing University Nanjing China Zhejiang Sci-Tech University Hangzhou China CFAR IHPC A*STAR Singapore

Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep learning (MCDL) systems face challenges in enhancing the search efficiency while maintaining the diversity. To combat these, this paper proposes µMOEA, the first LLM-empowered adaptive evolutionary search algorithm to detect safety violations in MCDL systems. Inspired by the context-understanding ability of Large Language Models (LLMs), µMOEA promotes the LLM to comprehend the optimization problem and generate an initial population tailed to evolutionary objectives. Subsequently, it employs adaptive selection and variation to iteratively produce offspring, balancing the evolutionary efficiency and diversity. During the evolutionary process, to navigate away from the local optima, µMOEA integrates the evolutionary experience back into the LLM. This utilization harnesses the LLM's quantitative reasoning prowess to generate differential seeds, breaking away from current optimal solutions. We evaluate µMOEA in finding safety violations of MCDL systems, and compare its performance with state-of-the-art MOEA methods. Experimental results show that µMOEA can significantly improve the efficiency and diversity of the evolutionary search. © 2025, CC BY.

关键词： Adversarial machine learning

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：