Zainab Alibhai, Taylor Burreson, Matthew Stiller, Ishfaq Ahmad, M. Huber, Addison Clark
{"title":"A Human-Computer Interface For Smart Wheelchair Control Using Forearm EMG Signals","authors":"Zainab Alibhai, Taylor Burreson, Matthew Stiller, Ishfaq Ahmad, M. Huber, Addison Clark","doi":"10.1109/ICDIS50059.2020.00011","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00011","url":null,"abstract":"With the increase in the aging population and people with disabilities, caused by heredity, disease, or injury, the demand for assistive devices is growing. Considerable research has been devoted in recent times on developing assistive technologies based on mobile robots to create what is now known as “smart wheelchairs.” One of the main challenges is how the user interfaces with the smart wheelchair for its smooth control. These smart wheelchairs typically consist of a powered commodity wheelchair, a computer, and a network of sensors. The common interface of a joy stick is problematic because it requires certain motor skills, which may be lacking in elderly and in people with disabilities. We have been developing a new smart wheelchair that comprises of a standard power wheelchair as the testbed, a joystick interface for manual control, an on-board computer, a laser scanner, and an EMG signal reading device. Its goal is to offer the elderly and the physically handicapped, concentrating on the portion who have sufficient motor control skills in their forearm, another way to control a power wheelchair without the means of a joystick. This paper focuses on efficiently using electromyography (EMG) to measure and utilize muscle signals for control of the wheelchair. The proposed system aims to help the user navigate within their environment, indoor or outdoor, as well as provide a capable HMI. The paper focuses on the growth of a user-friendly HCI in its application of making customizable mobilization for users on any commercial powered wheelchair. The simulation results show the potential of the system’s capabilities to recognize EMG-based signals for better mobility in an indoor, open office environment.","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122650042","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}
{"title":"Evaluation of CentOS performance under IoT based DDoS Security Attacks","authors":"William Robert Rivas, Sanjeev Kumar","doi":"10.1109/ICDIS50059.2020.00015","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00015","url":null,"abstract":"The increasing interest in ‘always-connected’ devices and the Internet of Things (IoT) technologies have led to many electronic devices with Internet connectivity becoming omnipresent in modern households and workplaces. Consequently, this increase has also led to an increase in vulnerable IoT devices, ripe for being hijacked by a malicious third party. Distributed Denial of Service (DDoS) attacks have consistently been an issue since the birth of the Internet. With the large number of IoT devices available today, the strength and intensity of these attacks continue to grow. Not all devices are created equal in terms of vulnerabilities that may exist with them. Many harbor flaws that allow them to be used as a bot by an external malicious host without the knowledge of the owner. Myriad of such devices can be used in a network of zombie machines (botnet) meant to carry out an attack. These botnets are used to flood a victim system with information aimed at consuming large amounts of resources, such as memory or processing power. In this paper, we evaluated the performance of CentOS 15 operating system under four popular DDoS attack scenarios in a controlled experimental environment.","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"164 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123291863","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}
Suhail Basalama, Atiyehsadat Panahi, Ange-Thierry Ishimwe, David Andrews
{"title":"SPAR-2: A SIMD Processor Array for Machine Learning in IoT Devices","authors":"Suhail Basalama, Atiyehsadat Panahi, Ange-Thierry Ishimwe, David Andrews","doi":"10.1109/ICDIS50059.2020.00025","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00025","url":null,"abstract":"In this paper, SPAR-2, a SIMD processor array for migrating machine learning applications into FPGA IoT edge devices is presented. SPAR-2 is a second-generation processorin/ near-memory architecture developed as a programmable overlay for modern FPGAs. In contrast to point designs, SPAR-2 can be programmed to implement different classes of machine learning algorithms. The overlay architecture is based on Processor-In-Memory (PIM) tiles, which integrate bit-serial ALUs with distributed Block RAMs (BRAMs). Forming PIM tiles increases the size of the multiply-accumulate array and on-chip storage capacity. User-visible inference latencies are reduced by exploiting concurrent accesses to weights and partial results stored throughout the distributed BRAMs. The sizing and performance analysis of SPAR-2 running a standard Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN) model is provided. Results show that our approach enables packing up to 16,384 processing elements in a Virtex-7 FPGA. Runtime performance comparisons show that SPAR-2 achieves up to 24.51x speedup compared to a High-Level Synthesis (HLS) equivalent design and 1.75x speedup over a previous custom-tuned design.","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129067302","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}
{"title":"Load-balancing of computing resources in vehicular fog computing","authors":"A. Hameed, K. Munir, Saif ul Islam, I. Ahmad","doi":"10.1109/ICDIS50059.2020.00020","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00020","url":null,"abstract":"The fog paradigm has the potential to efficiently address the time constraints of real-time critical applications by providing cloud-like services closer to the Internet of Things (IoT) devices. In this context, an emerging application is a cluster of auto-driven vehicles that are networked and can process the requests of IoT devices attached to the vehicles. With the ability to collectively provide abundant computing power as well as communication and storage resources, the cluster of vehicles can be viewed as a pool of fog devices. In order to utilize such resources, we devise a mechanism that provides load-balancing among the vehicular devices despite their mobility. The proposed mechanism functions in two ways: clustering among mobile fog devices and capacity-based load-balancing among clusters. The clustering algorithm efficiently builds clusters, allowing the selection of a cluster head based on the fog mobility factor. In addition to reducing congestion in the network, the proposed capacity-based load-balancing algorithm efficiently balances the load within a cluster as well as among the clusters of vehicles. Simulations conducted on NS2 demonstrate the efficiency of the proposed scheme in terms of end-to-end delay and packet delivery ratio (PDR).","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121909812","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}
Ishfaq Ahmad, Addison Clark, Muhammad Ali, David Ferris, Alexander J. Aved
{"title":"Identifying Optimal Attacks for Infrastructure Networks with failure Propagation","authors":"Ishfaq Ahmad, Addison Clark, Muhammad Ali, David Ferris, Alexander J. Aved","doi":"10.1109/ICDIS50059.2020.00017","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00017","url":null,"abstract":"Most critical infrastructures can be represented as directed graphs in which the nodes denote the operational entities and the arcs denote the dependencies of one entity upon others. A rational adversary that plans to harm the system would aim to use the minimum amount of effort to cause the maximum amount of damage. Therefore, attacking the most critical nodes of the graph would be the most rational strategy of an attacker. In contrast, the system’s operator might be able to minimize the damage if they are able to defend these critical nodes. Hence, it is strategically important for both the attacker and the defender to identify these critical nodes, but this corresponds to a complex optimization problem. This paper presents a problem formulation and then a solution for computing the optimal cost attack that takes failure propagation into consideration. Given a graph representing one or multiple infrastructures and the attack costs of each node, the proposed method computes the optimal attack that a rational attacker is likely to make. Our problem model has the goal of maximizing the damage for a given attack budget. Our technique relies on integer-linear programming to obtain the solution, given our objective function and sets of constraints for each of the specified goals. As shown by the experimental results, using a wide range of graphs, the proposed solution is very fast in terms of the runtime complexity.","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129537776","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}
C. Lipps, Sachinkumar Bavikatti Mallikarjun, Matthias Strufe, Christopher Heinz, C. Grimm, H. Schotten
{"title":"Keep Private Networks Private: Secure Channel-PUFs, and Physical Layer Security by Linear Regression Enhanced Channel Profiles","authors":"C. Lipps, Sachinkumar Bavikatti Mallikarjun, Matthias Strufe, Christopher Heinz, C. Grimm, H. Schotten","doi":"10.1109/ICDIS50059.2020.00019","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00019","url":null,"abstract":"In the context of a rapidly changing and increasingly complex (industrial) production landscape, securing the (communication) infrastructure is becoming an ever more important but also more challenging task - accompanied by the application of radio communication. A worthwhile and promising approach to overcome the arising attack vectors, and to keep private networks private, are Physical Layer Security (PhySec) implementations. The paper focuses on the transfer of the IEEE802.11 (WLAN) PhySec - Secret Key Generation (SKG) algorithms to Next Generation Mobile Networks (NGMNs), as they are the driving forces and key enabler of future industrial networks. Based on a real world Long Term Evolution (LTE) testbed, improvements of the SKG algorithms are validated. The paper presents and evaluates significant improvements in the establishment of channel profiles, whereby especially the Bit Disagreement Rate (BDR) can be improved substantially. The combination of the Discrete Cosine Transformation (DCT) and the supervised Machine Learning (ML) algorithm - Linear Regression (LR) – provides outstanding results, which can be used beyond the SKG application. The evaluation also emphasizes the appropriateness of PhySec for securing private networks.","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116010694","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}
{"title":"A Dynamic Multi-Threaded Queuing Mechanism for Reducing the Inter-Process Communication Latency on Multi-Core Chips","authors":"Rohitshankar Mishra, I. Ahmad, Akshaya Sharma","doi":"10.1109/ICDIS50059.2020.00008","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00008","url":null,"abstract":"Reducing latency in inter-process/inter-thread communication is one of the key challenges in parallel and distributed computing. This is because as the number of threads in an application increases, the communication overhead also increases. Moreover, the presence of background load further increases the latency. Reducing communication latency can have a significant impact on multi-threaded application performance in multi-core environments. In a wide-range of applications that utilize queueing mechanism, inter-process/ inter-thread communication typically involves enqueuing and dequeuing. This paper presents a queueing techniques called eLCRQ, which is a lock-free block-when-necessary multi-producer multi-consumer (MPMC) FIFO queue. It is designed for scenarios where the queue can randomly and frequently become empty during runtime. By combining lock-free performance with blocking resource efficiency, it delivers improved performance. Specifically, it results in a 1.7X reduction in latency and a 2.3X reduction in CPU usage when compared to existing message-passing mechanisms including PIPE and Sockets while running on multi-core Linux based systems. The proposed scheme also provides a 3.4X decrease in CPU usage while maintaining comparable latency when compared to other (MPMC) lock-free queues in low load scenarios. Our work is based on open-source Linux and support libraries.","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128056261","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}
Cameron Dignan, Eliud Perez, Ishfaq Ahmad, M. Huber, Addison Clark
{"title":"Improving Sign Language Recognition by Combining Hardware and Software Techniques","authors":"Cameron Dignan, Eliud Perez, Ishfaq Ahmad, M. Huber, Addison Clark","doi":"10.1109/ICDIS50059.2020.00018","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00018","url":null,"abstract":"People with hearing and speaking disabilities often have trouble communicating with the general population. They can often communicate amongst themselves, and, perhaps, with close family members and friends, if they have knowledge of a sign language. That being said, there has yet to be a widespread adoption of sign language by the general population. To remedy this problem, there is an increasing interest in developing hardware and software techniques for sign language gesture recognition, but there is a serious lack of technologies that fuse hardware and software. This paper proposes a techniques that aims to improve the accuracy of a software-based gesture recognition system by incorporating the Myo Armband, developed by Thalmic Labs. In our prototype, we train the software-based module using the Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) methods, and train the Myo-based module using the Support Vector Machine method. A dataset of nine gestures was used, with each repeated five times for a total of 45 trials for both the software-based and hardware-based modules. The Myo-based module achieved an accuracy of 49% while the software-based module had an accuracy of 89%; the results were then combined.","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114746928","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}
Jonas Herskind Sejr, A. Zimek, Peter Schneider-Kamp
{"title":"Explainable Detection of Zero Day Web Attacks","authors":"Jonas Herskind Sejr, A. Zimek, Peter Schneider-Kamp","doi":"10.1109/ICDIS50059.2020.00016","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00016","url":null,"abstract":"The detection of malicious HTTP(S) requests is a pressing concern in cyber security, in particular given the proliferation of HTTP-based (micro-)service architectures. In addition to rule-based systems for known attacks, anomaly detection has been shown to be a promising approach for unknown (zero-day) attacks. This article extends existing work by integrating outlier explanations for individual requests into an end-to-end pipeline. These end-to-end explanations reflect the internal working of the pipeline. Empirically, we show that found explanations coincide with manually labelled explanations for identified outliers, allowing security professionals to quickly identify and understand malicious requests.","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132038288","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}
{"title":"Ensemble Learning for Detecting Attacks and Anomalies in IoT Smart Home","authors":"Shivanjali Khare, Michael W. Totaro","doi":"10.1109/ICDIS50059.2020.00014","DOIUrl":"https://doi.org/10.1109/ICDIS50059.2020.00014","url":null,"abstract":"The expansion of the Internet of Things (IoT) has also given rise to an increasing number of destructive attacks that pose severe threats to exposed IoT devices. As such, IoT technologies involve a number of privacy and security challenges. Anomalies in the IoT environment often lead to unexpected disruptions or sensor failures in a machine, and may facilitate opportunities of intrusion by an attacker. Thus, it is crucial to observe the unexpected events from sensor signals. In this paper, the performance of an ensemble machine learning model is compared against the traditional learning approach for attack and anomaly detection in a smart home IoT environment on a categorical DS2oS traffic traces dataset. After training each model with the training dataset, we combine the best models using the AdaBoost ensemble learning approach in order to obtain optimized results for anomaly detection. This paper discusses various evaluation models and metrics, along with a clear description of training process. We also compare our results with other similar existing models. Finally, we discuss challenges and future work.","PeriodicalId":406260,"journal":{"name":"2020 3rd International Conference on Data Intelligence and Security (ICDIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129936338","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}