检索结果-内蒙古大学图书馆

Pinpointing the memory behaviors of DNN training

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Jiansong Dong, Xiao Li, Guangli Zhao, Peng Wang, Xueying Chen, Xiaobing Yu, Xianzhi Yang, Yongxin Jiang, Zihan Cao, Wei Liu, Lei Feng, Xiaobing State Key Laboratory of Computer Architecture Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Youtu Lab Tencent Shanghai China Huawei Technology Co. Ltd Beijing China

关键词： Deep neural networks

Software Defect Prediction via Deep Belief Network

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第5期28卷 925-932页

作者： WEI Hua SHAN Chun HU Changzhen ZHANG Yu YU Xiao School of Computer Science and Technology Beijing Institute of Technology China Information Technology Security Evaluation Center Beijing Key Laboratory of Software Security Engineering Technology Beijing Institute of Technology School of Electrical and Information Engineering and Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture State Key Laboratory in China for Geomechanics and Deep Underground Engineering (Beijing) China University of Mining and Technology School of Computer Science and Technology Shandong University of Technology

Defect distribution prediction is a meaningful topic because software defects are the fundamental cause of many attacks and data loss. Building accurate prediction models can help developers find bugs and prioritize their testing efforts. Previous researches focus on exploring different machine learning algorithms based on the features that encode the characteristics of *** problem of data redundancy exists in software defect data set, which has great influence on prediction *** propose a defect distribution prediction model(Deep belief network prediction model, DBNPM), a system for detecting whether a program module contains defects. The key insight of DBNPM is Deep belief network(DBN)technology, which is an effective deep learning technique in image processing and natural language processing,whose features are similar to defects in source *** results show that DBNPM can efficiently extract and process the data characteristics of source program and the performance is better than Support vector machine(SVM), Locally linear embedding SVM(LLE-SVM), and Neighborhood preserving embedding SVM(NPE-SVM).

关键词： Defect prediction Software security Deep belief network(DBN)

Sampling methods for efficient training of graph convolutional networks: A survey

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Xin Yan, Mingyu Deng, Lei Li, Guoqi Ye, Xiaochun Fan, Dongrui State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100086 China Department of Precision Instrument Center for Brain Inspired Computing Research Tsinghua University Beijing100084 China School of Computer Science and Technology University of Chinese Academy of Sciences

—Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations. Although GCN performs well compared with other methods, it still faces challenges. Training a GCN model for large-scale graphs in a conventional way requires high computation and storage costs. Therefore, motivated by an urgent need in terms of efficiency and scalability in training GCN, sampling methods have been proposed and achieved a significant effect. In this paper, we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN. To highlight the characteristics and differences of sampling methods, we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories. Finally, we discuss some challenges and future research directions of the sampling methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

SEIMI: Efficient and Secure SMAP-Enabled Intra-process Memory Isolation

学校读者我要写书评

暂无评论

SEIMI: Efficient and Secure SMAP-Enabled Intra-process Memor...

IEEE Symposium on Security and Privacy

作者： Zhe Wang Chenggang Wu Mengyao Xie Yinqian Zhang Kangjie Lu Xiaofeng Zhang Yuanming Lai Yan Kang Min Yang State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences The Ohio State University University of Minnesota Fudan University

ISBN: (数字)9781728134970

ISBN: (纸本)9781728134987

Memory-corruption attacks such as code-reuse attacks and data-only attacks have been a key threat to systems security. To counter these threats, researchers have proposed a variety of defenses, including control-flow integrity (CFI), code-pointer integrity (CPI), and code (re-)randomization. All of them, to be effective, require a security primitive-intra-process protection of confidentiality and/or integrity for sensitive data (such as CFI's shadow stack and CPI's safe region).In this paper, we propose SEIMI, a highly efficient intra-process memory isolation technique for memory-corruption defenses to protect their sensitive data. The core of SEIMI is to use the efficient Supervisor-mode Access Prevention (SMAP), a hardware feature that is originally used for preventing the kernel from accessing the user space, to achieve intra-process memory isolation. To leverage SMAP, SEIMI creatively executes the user code in the privileged mode. In addition to enabling the new design of the SMAP-based memory isolation, we further develop multiple new techniques to ensure secure escalation of user code, e.g., using the descriptor caches to capture the potential segment operations and configuring the Virtual Machine Control Structure (VMCS) to invalidate the execution result of the control registers related operations. Extensive experimental results show that SEIMI outperforms existing isolation mechanisms, including both the Memory Protection keys (MPK) based scheme and the Memory Protection Extensions (MPX) based scheme, while providing secure memory isolation.

关键词： Hardware Kernel Security Runtime Registers Data structures Switches

Sequence Triggered Hardware Trojan in Neural Network Accelerator

学校读者我要写书评

暂无评论

Sequence Triggered Hardware Trojan in Neural Network Acceler...

VLSI Test Symposium

作者： Zizhen Liu Jing Ye Xing Hu Huawei Li Xiaowei Li Yu Hu State Key Laboratory of Computer Architecture Institution of Computing Technology Chinese Academy of Sciences Department of Electrical and Computer Engineering University of California Santa Barbara

ISBN: (数字)9781728153599

ISBN: (纸本)9781728153605

With the rapid development of deep learning techniques, the security issue for Neural Network (NN) systems has emerged as an urgent and severe problem. Hardware Trojan attack is one of the threatens, which provides attackers backdoors to control the prediction results of NN systems. This paper proposes a sequence triggered hardware Trojan. Normal images but with specific sequence are used to trigger the hardware Trojan and let attackers fully control the prediction results. This kind of trigger is not only robust to image pre-processing, but also unrecognizable by human beings. In comparison with existing hardware Trojan design, it is more practical and less hardware overhead. The experiments on MNIST, CIFAR100, and ISLVRC show that the proposed hardware Trojan is rarely triggered in normal working status while the hardware cost is reduced by 19X.

关键词：

AIBench scenario: Scenario-distilling AI benchmarking

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gao, Wanling Tang, Fei Zhan, Jianfeng Wen, Xu Wang, Lei Cao, Zheng Lan, Chuanxin Luo, Chunjie Liu, Xiaoli Jiang, Zihan State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Alibaba

Modern real-world application scenarios like Internet services consist of a diversity of AI and non-AI modules with huge code sizes and long and complicated execution paths, which raises serious benchmarking or evaluating challenges. Using AI components or micro benchmarks alone can lead to error-prone conclusions. This paper presents a methodology to attack the above challenge. We formalize a real-world application scenario as a Directed Acyclic Graph-based model and propose the rules to distill it into a permutation of essential AI and non-AI tasks, which we call a scenario benchmark. Together with seventeen industry partners, we extract nine typical scenario benchmarks. We design and implement an extensible, configurable, and flexible benchmark framework. We implement two Internet service AI scenario benchmarks based on the framework as proxies to two real-world application scenarios. We consider scenario, component, and micro benchmarks as three indispensable parts for evaluating. Our evaluation shows the advantage of our methodology against using component or micro AI benchmarks alone. The specifications, source code1, testbed, and results are publicly available from https://***/aibench/scenario/. © 2020, CC BY.

关键词： Benchmarking

I/O lower bounds for auto-tuning of convolutions in CNNs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Xiaoyang Xiao, Junmin Tan, Guangming State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Science China

Convolution is the most time-consuming part in the computation of convolutional neural networks (CNNs), which have achieved great successes in numerous practical applications. Due to the complex data dependency and the increase in the amount of model samples, the convolution suffers from high overhead on data movement (i.e., memory access). This work provides comprehensive analysis and methodologies to minimize the communication for the convolution in CNNs. With an in-depth analysis of the recent I/O complexity theory under the red-blue game model, we develop a general I/O lower bound theory for a composite algorithm which consists of several different sub-computations. Based on the proposed theory, we establish the data movement lower bound results for two main convolution algorithms in CNNs, namely the direct convolution and Winograd algorithm, which represents the direct and indirect implementations of a convolution respectively. Next, derived from I/O lower bound results, we design the near I/O-optimal dataflow strategies for the two main convolution algorithms by fully exploiting the data reuse. Furthermore, in order to push the envelope of performance of the near I/O-optimal dataflow strategies further, an aggressive design of auto-tuning based on I/O lower bounds, is proposed to search an optimal parameter configuration for the direct convolution and Winograd algorithm on GPU, such as the number of threads and the size of shared memory used in each thread block. Finally, experiment evaluation results on the direct convolution and Winograd algorithm show that our dataflow strategies with the auto-tuning approach can achieve about 3.32× performance speedup on average over cuDNN. In addition, compared with TVM, which represents the state-of-the-art technique for auto-tuning, not only our auto-tuning method based on I/O lower bounds can find the optimal parameter configuration faster, but also our solution has higher performance than the optimal solution provided

关键词： Convolution

A systematic view of leakage risks in deep neural network systems

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Hu, Xing Liang, Ling Chen, Xiaobing Deng, Lei Ji, Yu Ding, Yufei Du, Zidong Guo, Qi Sherwood, Timothy Xie, Yuan State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Department of Electrical and Computer Engineering University of California Santa Barbara United States Department of Computer Science University of California Santa Barbara United States Tsinghua University China University of California Santa Barbara United States

As deep neural networks (DNNs) continue their reach into a wide range of application domains, the neural network architecture of DNN models becomes an increasingly sensitive subject, due to either intellectual property protection or risks of adversarial attacks. In observing the large gap between the architectural surfaces exploration and the model integrity study, this paper first presents the formulated schema of the model leakage risks. Then, we propose DeepSniffer, a learning-based model extraction framework, to obtain the complete model architecture information without any prior knowledge of the victim model. It is robust to architectural and system noises introduced by the complex memory hierarchy and diverse run-time system optimizations. Taking GPU platforms as a showcase, DeepSniffer performs model extraction by learning both the architecture-level execution features of kernels and the inter-layer temporal association information introduced by the common practice of DNN design. We demonstrate that DeepSniffer works experimentally in the context of an off-the-shelf Nvidia GPU platform running a variety of DNN models. The extracted models are directly helpful to the attempting of crafting adversarial inputs. The DeepSniffer project has been released in https://***/xinghu7788/DeepSniffer. © 2021, CC0.

关键词： Deep neural networks

Rockburst prediction using artificial intelligence techniques:A review

学校读者我要写书评

暂无评论

岩石力学通报（英文）

岩石力学通报（英文） 2024年第3期3卷 1-13页

作者： Yu Zhang Kongyi Fang Manchao He Dongqiao Liu Junchao Wang Zhengjia Guo School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing100044China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and ArchitectureBeijing100044China State Key Laboratory for Geomechanics and Deep Underground Engineering China University of Mining and TechnologyBeijing100083China School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing100044China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and ArchitectureBeijing100044China State Key Laboratory for Geomechanics and Deep Underground Engineering China University of Mining and TechnologyBeijing100083China Thomas Lord Department of Computer Science University of Southern CaliforniaLos Angeles90007CAUSA

Rockburst is a phenomenon where sudden,catastrophic failure of the rock mass occurs in underground deep regions or areas with high tectonic stress during the excavation *** disasters endanger the safety of people's lives and property,national energy security,and social interests,so it is very important to accurately predict *** rockburst prediction has not been able to find an effective prediction method,and the study of the rockburst mechanism is facing a *** the development of artificial intelligence(AI)techniques in recent years,more and more experts and scholars have begun to introduce AI techniques into the study of the rockburst *** previous research,several scholars have attempted to summarize the application of AI techniques in rockburst ***,these studies either are not specifically focused on reviews of the application of AI techniques in rockburst prediction,or they do not provide a comprehensive *** on the advantages of extensive interdisciplinary research and a deep understanding of AI techniques,this paper conducts a comprehensive review of rockburst prediction methods leveraging AI ***,pertinent definitions of rockburst and its associated hazards are ***,the applications of both traditional prediction methods and those rooted in AI techniques for rockburst prediction are summarized,with emphasis placed on the respective advantages and disadvantages of each ***,the strengths and weaknesses of prediction methods leveraging AI are summarized,alongside forecasting future research trends to address existing challenges,while simultaneously proposing directions for improvement to advance the field and meet emerging demands effectively.

关键词： Rockburst Rockburst prediction Artificial intelligence techniques