检索结果-内蒙古大学图书馆

Graft: Efficient Inference Serving for Hybrid Deep Learning with SLO Guarantees via DNN Re-alignment

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Jing Wang, Lin Jin, Qirui Liu, Fangming The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab in The School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China Paderborn University TU Darmstadt Germany Peng Cheng Laboratory Huazhong University of Science and Technology China

Deep neural networks (DNNs) have been widely adopted for various mobile inference tasks, yet their ever-increasing computational demands are hindering their deployment on resource-constrained mobile devices. Hybrid deep learning partitions a DNN into two parts and deploys them across the mobile device and a server, aiming to reduce inference latency or prolong battery life of mobile devices. However, such partitioning produces (non-uniform) DNN fragments which are hard to serve efficiently on the server. This paper presents Graft—an efficient inference serving system for hybrid deep learning with latency service-level objective (SLO) guarantees. Our main insight is to mitigate the non-uniformity by a core concept called DNN re-alignment, allowing multiple heterogeneous DNN fragments to be restructured to share layers. To fully exploit the potential of DNN re-alignment, Graft employs fine-grained GPU resource sharing. Based on that, we propose efficient algorithms for merging, grouping, and re-aligning DNN fragments to maximize request batching opportunities, minimizing resource consumption while guaranteeing the inference latency SLO. We implement a Graft prototype and perform extensive experiments with five types of widely used DNNs and real-world network traces. Our results show that Graft improves resource efficiency by up to 70% compared with the state-of-the-art inference serving systems. © 2023, CC BY-NC-ND.

关键词： Deep neural networks

Fed-AugMix: Balancing Privacy and Utility via Data Augmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Haoyang Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

Gradient leakage attacks pose a significant threat to the privacy guarantees of federated learning. While distortion-based protection mechanisms are commonly employed to mitigate this issue, they often lead to notable performance degradation. Existing methods struggle to preserve model performance while ensuring privacy. To address this challenge, we propose a novel data augmentation-based framework designed to achieve a favorable privacy-utility trade-off, with the potential to enhance model performance in certain cases. Our framework incorporates the AugMix algorithm at the client level, enabling data augmentation with controllable severity. By integrating the Jensen-Shannon divergence into the loss function, we embed the distortion introduced by AugMix into the model gradients, effectively safeguarding privacy against deep leakage attacks. Moreover, the JS divergence promotes model consistency across different augmentations of the same image, enhancing both robustness and performance. Extensive experiments on benchmark datasets demonstrate the effectiveness and stability of our method in protecting privacy. Furthermore, our approach maintains, and in some cases improves, model performance, showcasing its ability to achieve a robust privacy-utility trade-off. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

Can Large Language Models Serve as Evaluators for Code Summarization?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Yang Wan, Yao Chu, Zhaoyang Zhao, Wenting Liu, Ye Zhang, Hongyu Shi, Xuanhua Yu, Philip S. Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Big Data and Social Computing Lab University of Illinois Chicago Chicago United States Salesforce Research Palo Alto United States School of Big Data and Software Engineering Chongqing University Chongqing China

Code summarization facilitates program comprehension and software maintenance by converting code snippets into natural-language descriptions. Over the years, numerous methods have been developed for this task, but a key challenge remains: effectively evaluating the quality of generated summaries. While human evaluation is effective for assessing code summary quality, it is labor-intensive and difficult to scale. Commonly used automatic metrics, such as BLEU, ROUGE-L, METEOR, and BERTScore, often fail to align closely with human judgments. In this paper, we explore the potential of Large Language Models (LLMs) for evaluating code summarization. We propose CODERPE (Role-Player for Code Summarization Evaluation), a novel method that leverages role-player prompting to assess the quality of generated summaries. Specifically, we prompt an LLM agent to play diverse roles, such as code reviewer, code author, code editor, and system analyst. Each role evaluates the quality of code summaries across key dimensions, including coherence, consistency, fluency, and relevance. We further explore the robustness of LLMs as evaluators by employing various prompting strategies, including chain-of-thought reasoning, in-context learning, and tailored rating form designs. The results demonstrate that LLMs serve as effective evaluators for code summarization methods. Notably, our LLM-based evaluator, CODERPE, achieves an 81.59% Spearman correlation with human evaluations, outperforming the existing BERTScore metric by 17.27%. © 2024, CC BY.

关键词： Software agents

MalScan: Fast Market-Wide Mobile Malware Scanning by Social-Network Centrality Analysis

学校读者我要写书评

暂无评论

MalScan: Fast Market-Wide Mobile Malware Scanning by Social-...

IEEE International Conference on Automated Software Engineering (ASE)

作者： Yueming Wu Xiaodi Li Deqing Zou Wei Yang Xin Zhang Hai Jin Cluster and Grid Computing Lab Services Computing Technology and System Lab National Engineering Research Center for Big Data Technology and System School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China University of Texas at Dallas Shenzhen Huazhong University of Science and Technology Research Institute School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Malware scanning of an app market is expected to be scalable and effective. However, existing approaches use either syntax-based features which can be evaded by transformation attacks or semantic-based features which are usually extracted by performing expensive program analysis. Therefor, in this paper, we propose a lightweight graph-based approach to perform Android malware detection. Instead of traditional heavyweight static analysis, we treat function call graphs of apps as social networks and perform social-network-based centrality analysis to represent the semantic features of the graphs. Our key insight is that centrality provides a succinct and fault-tolerant representation of graph semantics, especially for graphs with certain amount of inaccurate information (e.g., inaccurate call graphs). We implement a prototype system, MalScan, and evaluate it on datasets of 15,285 benign samples and 15,430 malicious samples. Experimental results show that MalScan is capable of detecting Android malware with up to 98% accuracy under one second which is more than 100 times faster than two state-of-the-art approaches, namely MaMaDroid and Drebin. We also demonstrate the feasibility of MalScan on market-wide malware scanning by performing a statistical study on over 3 million apps. Finally, in a corpus of dataset collected from Google-Play app market, MalScan is able to identify 18 zero-day malware including malware samples that can evade detection of existing tools.

关键词： Malware Social networking (online) Feature extraction Semantics Analysis of variance Static analysis Robustness

Cross-Language Binary-Source Code Matching with Intermediate Representations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gui, Yi Wan, Yao Zhang, Hongyu Huang, Huifang Sui, Yulei Xu, Guandong Shao, Zhiyuan Jin, Hai 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 Wuhan China The University of Newcastle Australia School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan China School of Computer Science University of Technology Sydney Australia

Binary-source code matching plays an important role in many security and software engineering related tasks such as malware detection, reverse engineering and vulnerability assessment. Currently, several approaches have been proposed for binary-source code matching by jointly learning the embeddings of binary code and source code in a common vector space. Despite much effort, existing approaches target on matching the binary code and source code written in a single programming language. However, in practice, software applications are often written in different programming languages to cater for different requirements and computing platforms. Matching binary and source code across programming languages introduces additional challenges when maintaining multi-language and multi-platform applications. To this end, this paper formulates the problem of cross-language binary-source code matching, and develops a new dataset for this new problem. We present a novel approach XLIR, which is a Transformer-based neural network by learning the intermediate representations for both binary and source code. To validate the effectiveness of XLIR, comprehensive experiments are conducted on two tasks of cross-language binary-source code matching, and cross-language source-source code matching, on top of our curated dataset. Experimental results and analysis show that our proposed XLIR with intermediate representations significantly outperforms other state-of-the-art models in both of the two tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Binary codes

M2CF-Net: A Multi-Resolution and Multi-Scale Cross Fusion Network for Segmenting Pathology Lesion of the Focal Lymphocytic Sialadenitis

学校读者我要写书评

暂无评论

M2CF-Net: A Multi-Resolution and Multi-Scale Cross Fusion Ne...

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Hao Han Feng Lu Yanhan Deng Xiaofang Luo Hai Jin Wei Tu Xia Xie 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 Wuhan China Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Hainan University Haikou China

In the medical realm, the pivotal role of pathological Whole Slide Images (WSIs) in detecting cancer, tracking disease progression, and evaluating treatment efficacy is indisputable. Nevertheless, the identification and quantification of lesion areas in these gigapixel WSIs present a significant challenge due to their substantial size and the intricate details of lesions. To address these issues, we developed a novel multi-resolution and multi-scale cross fusion network (M 2 CF-Net), adept at managing large-scale pathological WSIs and capturing both fine details and context. Our model particularly focuses on segmenting local lymphocyte infiltration lesions in pathological WSIs of patients diagnosed with primary Sjogren's syndrome. By employing a patch-based training approach and combining interconnected elements via a multi-scale fusion technique, we enhance our model's capacity to detect and analyze structures and features in minor salivary gland section WSIs. Extensive experiments and ablation studies conducted on real-world clinical datasets affirm our model's superior accuracy in identifying lymphocyte-infiltrated regions over state-of-the-art models, with a performance improvement of up to 4.32% in terms of the Dice Similarity Coefficient.

关键词：

Sysevr: A framework for using deep learning to detect software vulnerabilities

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Zhen Zou, Deqing Xu, Shouhuai Jin, Hai Zhu, Yawei Chen, Zhaoxuan Services Computing Technology and System Lab Cluster and Grid Computing Lab Big Data Security Engineering Research Center School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Texas at San Antonio San AntonioTX78249 United States

The detection of software vulnerabilities (or vulnerabilities for short) is an important problem that has yet to be tackled, as manifested by many vulnerabilities reported on a daily basis. This calls for machine learning methods to automate vulnerability detection. Deep learning is attractive for this purpose because it does not require human experts to manually define features. Despite the tremendous success of deep learning in other domains, its applicability to vulnerability detection is not systematically understood. In order to fill this void, we propose the first systematic framework for using deep learning to detect vulnerabilities. The framework, dubbed Syntax-based, Semantics-based, and Vector Representations (SySeVR), focuses on obtaining program representations that can accommodate syntax and semantic information pertinent to vulnerabilities. Our experiments with 4 software products demonstrate the usefulness of the framework: we detect 15 vulnerabilities that are not reported in the National Vulnerability Database. Among these 15 vulnerabilities, 7 are unknown and have been reported to the vendors, and the other 8 have been "silently" patched by the vendors when releasing newer versions of the products. Copyright © 2018, The Authors. All rights reserved.

关键词： Syntactics

Continual learning via inter-task synaptic mapping

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fubing, Mao Weiwei, Weng Pratama, Mahardhika Kien Yee, Edward Yapp 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 Wuhan430074 China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Singapore Institute of Manufacturing Technology A*Star Singapore Singapore

Learning from streaming tasks leads a model to catastrophically erase unique experiences it absorbs from previous episodes. While regularization techniques such as LWF, SI, EWC have proven themselves as an effective avenue to overcome this issue by constraining important parameters of old tasks from changing when accepting new concepts, these approaches do not exploit common information of each task which can be shared to existing neurons. As a result, they do not scale well to large-scale problems since the parameter importance variables quickly explode. An Inter-Task Synaptic Mapping (ISYANA) is proposed here to underpin knowledge retention for continual learning. ISYANA combines task-to-neuron relationship as well as concept-to-concept relationship such that it prevents a neuron to embrace distinct concepts while merely accepting relevant concept. Numerical study in the benchmark continual learning problems has been carried out followed by comparison against prominent continual learning algorithms. ISYANA exhibits competitive performance compared to state of the arts. Codes of ISYANA is made available in https://***/ContinualAL/ISYANAKBS. © 2021, CC BY-NC-SA.

关键词： Neurons

FedMoS: Taming Client Drift in Federated Learning with Double Momentum and Adaptive Selection

学校读者我要写书评

暂无评论

FedMoS: Taming Client Drift in Federated Learning with Doubl...

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Xiong Wang Yuxin Chen Yuqing Li Xiaofei Liao Hai Jin Bo Li 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 Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) enables massive clients to collaboratively train a global model by aggregating their local updates without disclosing raw data. Communication has become one of the main bottlenecks that prolongs the training process, especially under large model variances due to skewed data distributions. Existing efforts mainly focus on either single momentum-based gradient descent, or random client selection for potential variance reduction, yet both often lead to poor model accuracy and system efficiency. In this paper, we propose FedMoS, a communication-efficient FL framework with coupled double momentum-based update and adaptive client selection, to jointly mitigate the intrinsic variance. Specifically, FedMoS maintains customized momentum buffers on both server and client sides, which track global and local update directions to alleviate the model discrepancy. Taking momentum results as input, we design an adaptive selection scheme to provide a proper client representation during FL aggregation. By optimally calibrating clients’ selection probabilities, we can effectively reduce the sampling variance, while ensuring unbiased aggregation. Through a rigid analysis, we show that FedMoS can attain the theoretically optimal ${{\mathcal{O}}}\left({{T^{ - 2/3}}}\right)$ convergence rate. Extensive experiments using real-world datasets further validate the superiority of FedMoS, with 58%-87% communication reduction for achieving the same target performance compared to state-of-the-art techniques.

关键词：