Unauthorized hardware or firmware modifications, known as Trojans, can steal information, drain the battery, or damage IoT devices. This paper presents a stand-off self-referencing technique for detecting unauthorized activity. The proposed technique processes involuntary electromagnetic emissions on a separate hardware, which is physically decoupled from the device under test. When the device enter the test mode, it runs a predefined application repetitively with a fixed period. The periodicity ensures that the spectral electromagnetic power of the test application concentrates at known frequencies, leaving the remaining frequencies within the operation bandwidth at the noise level. Any deviations from the noise level for these unoccupied frequency locations indicates the presence of unknown (unauthorized) activity. Experiments based on hardware measurements show that the proposed technique achieves close to 100% detection accuracy at up to 120 cm distance.
{"title":"Work-in-progress: remote detection of unauthorized activity via spectral analysis","authors":"F. Karabacak, Ümit Y. Ogras, S. Ozev","doi":"10.1145/3276770","DOIUrl":"https://doi.org/10.1145/3276770","url":null,"abstract":"Unauthorized hardware or firmware modifications, known as Trojans, can steal information, drain the battery, or damage IoT devices. This paper presents a stand-off self-referencing technique for detecting unauthorized activity. The proposed technique processes involuntary electromagnetic emissions on a separate hardware, which is physically decoupled from the device under test. When the device enter the test mode, it runs a predefined application repetitively with a fixed period. The periodicity ensures that the spectral electromagnetic power of the test application concentrates at known frequencies, leaving the remaining frequencies within the operation bandwidth at the noise level. Any deviations from the noise level for these unoccupied frequency locations indicates the presence of unknown (unauthorized) activity. Experiments based on hardware measurements show that the proposed technique achieves close to 100% detection accuracy at up to 120 cm distance.","PeriodicalId":141215,"journal":{"name":"2017 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126072914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Arman Iranfar, Marina Zapater, David Atienza Alonso
High Efficiency Video Coding (HEVC) provides high efficiency at the cost of increased computational complexity followed by increased power consumption and temperature of current Multi- Processor Systems-on-Chip (MPSoCs). In this paper, we propose a machine learning-based power and thermal management approach that dynamically learns the best encoder configuration and core frequency for each of the several video streams running in an MPSoC, using information from frame compression, quality, performance, total power and temperature. We implement our approach in an enterprise multicore server and compare it against state-of-the-art techniques. Our approach improves video quality and performance by 17% and 11%, respectively, while reducing average temperature by 12%, without degrading compression or increasing power.
{"title":"Work-in-progress: a machine learning-based approach for power and thermal management of next-generation video coding on MPSoCs","authors":"Arman Iranfar, Marina Zapater, David Atienza Alonso","doi":"10.1145/3125502.3125533","DOIUrl":"https://doi.org/10.1145/3125502.3125533","url":null,"abstract":"High Efficiency Video Coding (HEVC) provides high efficiency at the cost of increased computational complexity followed by increased power consumption and temperature of current Multi- Processor Systems-on-Chip (MPSoCs). In this paper, we propose a machine learning-based power and thermal management approach that dynamically learns the best encoder configuration and core frequency for each of the several video streams running in an MPSoC, using information from frame compression, quality, performance, total power and temperature. We implement our approach in an enterprise multicore server and compare it against state-of-the-art techniques. Our approach improves video quality and performance by 17% and 11%, respectively, while reducing average temperature by 12%, without degrading compression or increasing power.","PeriodicalId":141215,"journal":{"name":"2017 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132860640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Over the last five years Deep Neural Nets have offered more accurate solutions to many problems in speech recognition, and computer vision, and these solutions have surpassed a threshold of acceptability for many applications. As a result, Deep Neural Networks have supplanted other approaches to solving problems in these areas, and enabled many new applications. While the design of Deep Neural Nets is still something of an art form, in our work we have found basic principles of design space exploration used to develop embedded microprocessor architectures to be highly applicable to the design of Deep Neural Net architectures. In particular, we have used these design principles to create a novel Deep Neural Net called SqueezeNet that requires only 480KB of storage for its model parameters. We have further integrated all these experiences to develop something of a playbook for creating small Deep Neural Nets for embedded systems.
{"title":"Keynote: small neural nets are beautiful: enabling embedded systems with small deep-neural- network architectures","authors":"F. Iandola, K. Keutzer","doi":"10.1145/3125502.3125606","DOIUrl":"https://doi.org/10.1145/3125502.3125606","url":null,"abstract":"Over the last five years Deep Neural Nets have offered more accurate solutions to many problems in speech recognition, and computer vision, and these solutions have surpassed a threshold of acceptability for many applications. As a result, Deep Neural Networks have supplanted other approaches to solving problems in these areas, and enabled many new applications. While the design of Deep Neural Nets is still something of an art form, in our work we have found basic principles of design space exploration used to develop embedded microprocessor architectures to be highly applicable to the design of Deep Neural Net architectures. In particular, we have used these design principles to create a novel Deep Neural Net called SqueezeNet that requires only 480KB of storage for its model parameters. We have further integrated all these experiences to develop something of a playbook for creating small Deep Neural Nets for embedded systems.","PeriodicalId":141215,"journal":{"name":"2017 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133388141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Over the past few years, NAND flash-based Solid State Drives (SSDs) are progressively replacing Hard Disk Drives (HDDs) in various applications ranging from personal computers to large-scale storage servers, due to their high performance and low power consumption. However, SSDs suffer from limited endurance, which is a major concern for their utilization in the server domain. Based on the unique characteristics of SSDs, we propose an evolutionary architecture, which can significantly improve both the performance and reliability of SSD-based storage systems compared with the currently prevalent RAID-5 technology [1].
{"title":"Work-in-progress: alert-and-transfer: an evolutionary architecture for ssd-based storage systems","authors":"Yue Zhu, Fei Wu, Qin Xiong, C. Xie","doi":"10.1145/3125502.3125536","DOIUrl":"https://doi.org/10.1145/3125502.3125536","url":null,"abstract":"Over the past few years, NAND flash-based Solid State Drives (SSDs) are progressively replacing Hard Disk Drives (HDDs) in various applications ranging from personal computers to large-scale storage servers, due to their high performance and low power consumption. However, SSDs suffer from limited endurance, which is a major concern for their utilization in the server domain. Based on the unique characteristics of SSDs, we propose an evolutionary architecture, which can significantly improve both the performance and reliability of SSD-based storage systems compared with the currently prevalent RAID-5 technology [1].","PeriodicalId":141215,"journal":{"name":"2017 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122547478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：