检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Lungu, Nelson Tembo, Simon Walubita, Ngula Patra, Sudhansu Shekhar University of Zambia Electrical and Electronical Engineering Lusaka Zambia Mukuni Secondary School Livingstone Zambia KIIT Deemed to be University School of Computer Applications Bhubaneswar India

ISBN: (纸本)9798350317558

Graphics processing units (GPUs) are increasingly employed in security-sensitive domains, making side-channel attacks on shader execution a pressing threat. We present an integrated shader execution framework incorporating real-time performance monitoring, machine learning anomaly detection, and architecture-aware response primitives to detect and mitigate GPU side-channel vulnerabilities with minimal overhead reliably. A shader execution monitors non-invasively profiles hardware counters to extract execution features, passed to an isolation forest classifier for attack detection within 50ms. Transparent mitigations like cache flushing, warp throttling, and shuffle masking are triggered to disrupt identified side channels by leveraging GPU architectural capabilities. Evaluations against simulated attacks demonstrate that the framework reduces key leakage by 4-5x and achieves over 80% attack disruption for a 400ms attack at under 5% performance cost. The integrated GPU-specific security solution significantly enhances real-world shader execution protection against side-channel risks. This paper present an integrated shader execution framework that leverages advanced monitoring, anomaly detection, and finely tuned response mechanisms. © 2024 IEEE.

关键词： anomaly detection GPU security shader execution side-channel attacks

来源：评论

学校读者我要写书评

暂无评论

Probing Vulnerabilities in GPU Shader Execution 2

Probing Vulnerabilities in GPU Shader Execution

引用

2nd IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2024

作者： Lungu, Nelson Tembo, Simon Patra, Sudhansu Shekhar Walubita, Ngula Dash, Bibhuti Bhusan De, Utpal Chandra University of Zambia Electrical and Electronical Engineering Lusaka Zambia School of Computer Applications Kiit Deemed to Be University Bhubaneswar India Mukuni Secondary School Livingstone Zambia

ISBN: (纸本)9798350372847

Graphics processing units (GPUs) are increasingly used for general-purpose parallel computing. However, the rise of GPUs in security-sensitive domains has exposed vulnerabilities arising from architectural weaknesses. In particular, side-channel attacks on shader execution can leak sensitive data through mechanisms like timing analysis, contention monitoring, and access pattern observation. We present a detailed investigation into shader-based side channels on commercial GPUs. We introduce a taxonomy of attack vectors categorised as timing, contention, and access pattern channels. We use standard shader interfaces like CUDA and OpenCL to demonstrate proof-of-concept exploits on NVIDIA and AMD GPUs for each attack class. Our analysis reveals pervasive side-channel risks from fundamental GPU architectural traits like massive multithreading, memory hierarchies, and throughput-optimised pipelines. Results show that even academically proposed countermeasures are inadequate in practice. We conclude with an in-depth discussion on the root causes of GPU shader vulnerabilities to inform specialised hardware-software co-designed defences. We comprehensively evaluate real-world GPU shader execution risks to guide further research on security-aware accelerator design. © 2024 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Secure Shader Execution via Early Termination and Throttling-A Review of Recent Literature and Future Directions 4

Secure Shader Execution via Early Termination and Throttling...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Lungu, Nelson Tembo, Simon Dash, Bibhuti Bhusan Walubita, Ngula Patra, Sudhansu Shekhar University of Zambia Electrical and Electronical Engineering Lusaka Zambia School of Computer Applications KIIT Deemed to be University Bhubaneswar India Mukuni Secondary School Livingstone Zambia

ISBN: (纸本)9798350385793

Graphics processing units (GPUs) are increasingly used in security-sensitive domains, making side-channel attacks on shader execution a pressing concern. This paper reviews recent research on side-channel vulnerabilities in GPU shader execution and examines limitations in existing defences. The study highlights gaps like a lack of lightweight runtime attack monitoring leveraging GPU features, the absence of detection models suited to noisy shader data, and deficient response mechanisms exploiting unique GPU capabilities. The study then proposes research directions to develop a secure shader execution framework integrating continuous performance monitoring, isolation forest anomaly detection, and early termination and throttling defences customised to GPU architectures. The goal is to mitigate side-channel attacks on commercial GPU s reliably and with minimal overhead. © 2024 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Precision Countermeasures for GPU Side Channels Using Shader Execution Pattern Analysis 3

Precision Countermeasures for GPU Side Channels Using Shader...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Lungu, Nelson Tembo, Simon Sasmal, Gopal Charan Rout, Suchismita Gourisaria, Mahendra Kumar Patra, Sudhansu Shekhar University of Zambia Electrical and Electronical Engineering Lusaka Zambia Trident Academy of Creative Technology MCA Department Bhubaneswar India KIIT Deemed To be University School of Computer Engineering Bhubaneswar India KIIT Deemed to be University School of Computer Applications Bhubaneswar India

ISBN: (纸本)9798350372120

Graphics Processing Units (GPUs) have become increasingly susceptible to side-channel attacks, compromising the security of sensitive information processed on these devices. This paper presents a novel approach to mitigating GPU side-channel vulnerabilities using shader execution pattern analysis. The proposed technique enables the development of precision countermeasures that effectively obscure the timing and power consumption patterns exploited by adversaries. By leveraging insights gained from analysing shader execution patterns, we develop targeted countermeasures that combine data-dependent execution balancing, power consumption smoothing, and dynamic noise injection to provide comprehensive protection against a wide range of side-channel attacks. Experimental results demonstrate the efficacy of the proposed method in significantly reducing the leakage of sensitive information through GPU side channels while incurring minimal performance overhead. The findings of this research contribute to the advancement of GPU security and the protection of sensitive data in graphics-intensive applications, paving the way for more secure and trustworthy computing environments. © 2024 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Navigation On Mobile Computing Devices with A Walking Using Object-Oriented Techniques to Communicate Stick 3

Navigation On Mobile Computing Devices with A Walking Using ...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Ramesh Prabhakaran, R. Guhan, P. Raj, E George Dharma Prakash Karthika, K. Angel Maanu, P. Mizoram University Department of Computer Engineering Mizoram India Panimalar Engineering College Department of Electrical and Electronical Engineering Chennai India Bharathidasan University School of Computer Science and Engineering Trichy India Karpagam College of Engineering Department of Information Technology Coimbatore India Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331528201

Moving around in their surroundings is challenging for elderly people and people with visual impairments. The majority of functional sticks in use today are not intelligent and lack an innate ability to recognize obstacles. In an effort to address this issue, mobility and orientation specialists who assist the blind by teaching them to move freely and safely using their remaining senses are brought in. They can navigate around obstacles with the aid of guidance dogs as well. These techniques have drawbacks, such as the dogs' inability to comprehend complicated instructions, the high cost of maintaining these trained dogs, and the need to hire an expert. In light of the aforementioned difficulties, the "Smart walking stick"has become a potential answer. The "Mobile based walking stick"is a useful mobility aid with the capacity to call a relative who can help in the event of an accident, detect obstacles above ground level and pits using ultrasonic sensors, recognize when a collision has occurred, and call the user's mobile phone if it has been misplaced to share the location's GPS for use with GSM connectivity and to share with the user's mention contacts. With some visually disabled people as test subjects, a test case was run, and 95% of the time it was successful. © 2024 IEEE.

关键词： Ultrasonic sensors

来源：评论

学校读者我要写书评

暂无评论

Multi-vector Monitoring, Detecting and Classifying GPU Side-Channel Attack Vectors on a Secure GPU Execution Framework 8

Multi-vector Monitoring, Detecting and Classifying GPU Side-...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Lungu, Nelson Dash, Bibhuti Bhusan De, Utpal Chandra Dash, Bibek Bikram Singh, Satyendr Patra, Sudhansu Shekhar University of Zambia Electrical and Electronical Engineering Lusaka Zambia Kiit Deemed to be University School of Computer Applications Bhubaneswar India HealthWorksAI Bangalore India Bml Munjal University Computer Science & Engg Department Gurugram India

ISBN: (纸本)9798350376425

Graphics Processing Units (GPUs) are increasingly deployed in security-sensitive domains, but their parallel architectures introduce vulnerabilities enabling side-channel attacks to steal sensitive data. Recent works have shown feasible timing, contention, power, and access pattern side-channel attacks against cryptographic implementations, randomness protections, and other workloads on GPUs, highlighting risks of intellectual property theft, cryptographic key extraction, and spying. However, existing academic defences remain inadequate in systematically protecting real-world shader execution. This research aims to design, develop, and evaluate a secure GPU shader execution framework incorporating runtime monitoring, anomaly detection, and response mechanisms for commercial GPUs. The methodology involves implementing and assessing the framework against simulated side-channel attacks on shader benchmarks;this can help secure emerging GPU adoption in sectors like finance, healthcare, and government against rising data breaches. © 2024 IEEE.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

Hybrid Compiler and Hardware Approach to Mitigate Side-Channel Vulnerabilities in Parallel GPU Architectures 8

Hybrid Compiler and Hardware Approach to Mitigate Side-Chann...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Lungu, Nelson Dash, Bibhuti Bhusan De Chandra, Utpal Dash, Bibek Bikram Pattanayak, Binod Kumar Patra, Sudhansu Shekhar Electrical and Electronical Engineering University of Zambia Lusaka Zambia School of Computer Applications Kiit Deemed to be University Bhubaneswar India HealthWorksAI Bangalore India Iter Siksha 'O' Anusandhan University Department of Computer Science & Engineering Odisha Bhubaneswar India

ISBN: (纸本)9798350376425

Graphics processing units (GPUs) have become ubiquitous in computing systems, from personal devices to data centres. Their massively parallel architecture delivers tremendous performance for graphics and general-purpose workloads. However, the open nature of GPUs also introduces security vulnerabilities that can be exploited through side-channel attacks. Defending against such threats often incurs performance overhead, creating tradeoffs between security and speed. This article examines recent research analysing and mitigating GPU side channel attacks while maintaining acceptable performance and presented a multi-faceted defence strategy combining compiler transformations, runtime monitoring, and microarchitectural techniques to balance security and performance. The methodology integrates formal threat models, empirical side-channel evaluations, and rigorous benchmarking. It implements and evaluates prototypes demonstrating security improvement with minimal impact on representative workloads. The results provide promising directions for practical GPU security defences. © 2024 IEEE.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

JL-Hate: An Annotated Dataset for Joint Learning of Hate Speech and Target Detection 30

JL-Hate: An Annotated Dataset for Joint Learning of Hate Spe...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Buyukdemirci, Kaan Kucukkaya, Izzet Emre Olmez, Eren Toraman, Cagri Department of Electrical and Electronical Engineering Bilkent University Ankara Turkey School of Computation Information and Technology Technical University of Munich Munich Germany Department of Computer Engineering Middle East Technical University Ankara Turkey

ISBN: (纸本)9782493814104

The detection of hate speech is a subject extensively explored by researchers, and machine learning algorithms play a crucial role in this domain. The existing resources mostly focus on text sequence classification for the task of hate speech detection. However, the target of hateful content is another dimension that has not been studied in details due to the lack of data resources. In this study, we address this gap by introducing a novel tweet dataset for the task of joint learning of hate speech detection and target detection, called JL-Hate, for the tasks of sequential text classification and token classification, respectively. The JL-Hate dataset consists of 1,530 tweets divided equally in English and Turkish languages. Leveraging this dataset, we conduct a series of benchmark experiments. We utilize a joint learning model to concurrently perform sequence and token classification tasks on our data. Our experimental results demonstrate consistent performance with the prevalent studies, both in sequence and token classification tasks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Integrating knowledge bases to improve coreference and bridging resolution for the chemical domain

arXiv

引用

arXiv 2024年

作者： Lu, Pengcheng Poesio, Massimo School of Electronical Engineering and Computer Science Queen Mary University of London United Kingdom

Resolving coreference and bridging relations in chemical patents is important for better understanding the precise chemical process, where chemical domain knowledge is very critical. We proposed an approach incorporating external knowledge into a multi-task learning model for both coreference and bridging resolution in the chemical domain. The results show that integrating external knowledge can benefit both chemical coreference and bridging resolution. Copyright © 2024, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

R-Taichi: A Quadruped Robot with Deformed Wheels 20

R-Taichi: A Quadruped Robot with Deformed Wheels

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Ma, Tengyuan Cheng, Haoning Cheng, Zihan Wang, Cunkai Duan, Mingyu Jiang, Nanqing Wang, Hemiao Yao, Senge Tiangong University School of Mechanical Engineering Tianjin China Tiangong University School of Electronics & Information Engineering Tianjin China Tiangong University School of Electronical Engineering Tianjin China Tiangong University School of Computer Science and Technology Tianjin China Tiangong University School of Aeronautics and Astronautics Tianjin China

ISBN: (纸本)9798350320831

This paper presents the design of a quadruped robot with deformable wheels. In terms of structure, the robot successfully combines the wheel mode, RHex mode of varying heights, and leg mode with a simple link mechanism. The robot also adopts the form of motor-relative control installation to optimize energy consumption. In gait planning, we calculate forward and inverse kinematics, and design the RHex gait based on the characteristics of the deformable wheel, as well as a variety of gaits for flexible leg mode. Finally, we analyze the energy consumption and stability of each mode through experiments. The results show that the RHex mode has strong mobility and adaptability, as it can easily cross a 15cm obstacle. The wheel mode has obvious advantages in terms of energy consumption and stability. In the future, we can adapt more algorithms for leg patterns to fully take advantage of their flexibility. © 2023 IEEE.

关键词： Energy utilization

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：