arXiv subjects

Muhammad Shafique

Publications and source records attributed to Muhammad Shafique.

302 records · Page 17Linked to original sources

arXiv2019

Systimator: A Design Space Exploration Methodology for Systolic Array based CNNs Acceleration on the FPGA-based Edge Nodes

The evolution of IoT based smart applications demand porting of artificial intelligence algorithms to the edge computing devices. CNNs form a large part of these AI algorithms. Systolic array based CNN acceleration is being widely advocated due its ability to allow scalable architectures. However, CNNs are inherently memory and compute intensive algorithms, and hence pose significant challenges to be implemented on the resource-constrained edge computing devices. Memory-constrained low-cost FPGA based devices form a substantial fraction of these edge computing devices. Thus, when porting to such edge-computing devices, the designer is left unguided as to how to select a suitable systolic array configuration that could fit in the available hardware resources. In this paper we propose Systimator, a design space exploration based methodology that provides a set of design points that can be mapped within the memory bounds of the target FPGA device. The methodology is based upon an analytical model that is formulated to estimate the required resources for systolic arrays, assuming multiple data reuse patterns. The methodology further provides the performance estimates for each of the candidate design points. We show that Systimator provides an in-depth analysis of resource-requirement of systolic array based CNNs. We provide our resource estimation results for porting of convolutional layers of TINY YOLO, a CNN based object detector, on a Xilinx ARTIX 7 FPGA.

cs.DC↗

arXiv2019

XBioSiP: A Methodology for Approximate Bio-Signal Processing at the Edge

Bio-signals exhibit high redundancy, and the algorithms for their processing are inherently error resilient. This property can be leveraged to improve the energy-efficiency of IoT-Edge (wearables) through the emerging trend of approximate computing. This paper presents XBioSiP, a novel methodology for approximate bio-signal processing that employs two quality evaluation stages, during the pre-processing and bio-signal processing stages, to determine the approximation parameters. It thereby achieves high energy savings while satisfying the user-determined quality constraint. Our methodology achieves, up to 19x and 22x reduction in the energy consumption of a QRS peak detection algorithm for 0% and <1% loss in peak detection accuracy, respectively.

eess.SP↗

arXiv2019

RED-Attack: Resource Efficient Decision based Attack for Machine Learning

Due to data dependency and model leakage properties, Deep Neural Networks (DNNs) exhibit several security vulnerabilities. Several security attacks exploited them but most of them require the output probability vector. These attacks can be mitigated by concealing the output probability vector. To address this limitation, decision-based attacks have been proposed which can estimate the model but they require several thousand queries to generate a single untargeted attack image. However, in real-time attacks, resources and attack time are very crucial parameters. Therefore, in resource-constrained systems, e.g., autonomous vehicles where an untargeted attack can have a catastrophic effect, these attacks may not work efficiently. To address this limitation, we propose a resource efficient decision-based methodology which generates the imperceptible attack, i.e., the RED-Attack, for a given black-box model. The proposed methodology follows two main steps to generate the imperceptible attack, i.e., classification boundary estimation and adversarial noise optimization. Firstly, we propose a half-interval search-based algorithm for estimating a sample on the classification boundary using a target image and a randomly selected image from another class. Secondly, we propose an optimization algorithm which first, introduces a small perturbation in some randomly selected pixels of the estimated sample. Then to ensure imperceptibility, it optimizes the distance between the perturbed and target samples. For illustration, we evaluate it for CFAR-10 and German Traffic Sign Recognition (GTSR) using state-of-the-art networks.

cs.CR↗

arXiv2018

ApproxCS: Near-Sensor Approximate Compressed Sensing for IoT-Healthcare Systems

Internet of Things (IoTs) is an emerging trend that has enabled an upgrade in the design of wearable healthcare monitoring systems through the (integrated) edge, fog, and cloud computing paradigm. Energy efficiency is one of the most important design metrics in such IoT-healthcare systems especially, for the edge and fog nodes. Due to the sensing noise and inherent redundancy in the input data, even the most safety-critical biomedical applications can sometimes afford a slight degradation in the output quality. Hence, such inherent error tolerance in the bio-signals can be exploited to achieve high energy savings through the emerging trends like, the Approximate Computing which is applicable at both software and hardware levels. In this paper, we propose to leverage the approximate computing in digital Compressed Sensing (CS), through low-power approximate adders (LPAA) in an accurate Bernoulli sensing-based CS acquisition (BCS). We demonstrate that approximations can indeed be safely employed in IoT healthcare without affecting the detection of critical events in the biomedical signals. Towards this, we explored the trade-of between energy efficiency and output quality using the state-of-the-art lp2d RLS reconstruction algorithm. The proposed framework is validated with the MIT-BIH Arrhythmia database. Our results demonstrated approximately 59% energy savings as compared to the accurate design.

eess.SP↗

arXiv2018

A Roadmap Towards Resilient Internet of Things for Cyber-Physical Systems

The Internet of Things (IoT) is a ubiquitous system connecting many different devices - the things - which can be accessed from the distance. The cyber-physical systems (CPS) monitor and control the things from the distance. As a result, the concepts of dependability and security get deeply intertwined. The increasing level of dynamicity, heterogeneity, and complexity adds to the system's vulnerability, and challenges its ability to react to faults. This paper summarizes state-of-the-art of existing work on anomaly detection, fault-tolerance and self-healing, and adds a number of other methods applicable to achieve resilience in an IoT. We particularly focus on non-intrusive methods ensuring data integrity in the network. Furthermore, this paper presents the main challenges in building a resilient IoT for CPS which is crucial in the era of smart CPS with enhanced connectivity (an excellent example of such a system is connected autonomous vehicles). It further summarizes our solutions, work-in-progress and future work to this topic to enable "Trustworthy IoT for CPS". Finally, this framework is illustrated on a selected use case: A smart sensor infrastructure in the transport domain.

cs.ET↗

arXiv2018

TrojanZero: Switching Activity-Aware Design of Undetectable Hardware Trojans with Zero Power and Area Footprint

Conventional Hardware Trojan (HT) detection techniques are based on the validation of integrated circuits to determine changes in their functionality, and on non-invasive side-channel analysis to identify the variations in their physical parameters. In particular, almost all the proposed side-channel power-based detection techniques presume that HTs are detectable because they only add gates to the original circuit with a noticeable increase in power consumption. This paper demonstrates how undetectable HTs can be realized with zero impact on the power and area footprint of the original circuit. Towards this, we propose a novel concept of TrojanZero and a systematic methodology for designing undetectable HTs in the circuits, which conceals their existence by gate-level modifications. The crux is to salvage the cost of the HT from the original circuit without being detected using standard testing techniques. Our methodology leverages the knowledge of transition probabilities of the circuit nodes to identify and safely remove expendable gates, and embeds malicious circuitry at the appropriate locations with zero power and area overheads when compared to the original circuit. We synthesize these designs and then embed in multiple ISCAS85 benchmarks using a 65nm technology library, and perform a comprehensive power and area characterization. Our experimental results demonstrate that the proposed TrojanZero designs are undetectable by the state-of-the-art power-based detection methods.

cs.CR↗

arXiv2018

Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference

The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the enormous amount of data. Although ML-based solutions address the efficient computing requirements of big data, they introduce (new) security vulnerabilities into the systems, which cannot be addressed by traditional monitoring-based security measures. Therefore, this paper first presents a brief overview of various security threats in machine learning, their respective threat models and associated research challenges to develop robust security measures. To illustrate the security vulnerabilities of ML during training, inferencing and hardware implementation, we demonstrate some key security threats on ML using LeNet and VGGNet for MNIST and German Traffic Sign Recognition Benchmarks (GTSRB), respectively. Moreover, based on the security analysis of ML-training, we also propose an attack that has a very less impact on the inference accuracy. Towards the end, we highlight the associated research challenges in developing security measures and provide a brief overview of the techniques used to mitigate such security threats.

cs.LG↗

arXiv2018

FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning

Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversarial examples, and network manipulation (through the addition of malicious nodes) has, however, put the spotlight squarely on the lack of security in DNN-based ML systems. In particular, malicious actors can use these well-known attacks to cause random/targeted misclassification, or cause a change in the prediction confidence, by only slightly but systematically manipulating the environmental parameters, inference data, or the data acquisition block. Most of the prior adversarial attacks have, however, not accounted for the pre-processing noise filters commonly integrated with the ML-inference module. Our contribution in this work is to show that this is a major omission since these noise filters can render ineffective the majority of the existing attacks, which rely essentially on introducing adversarial noise. Apart from this, we also extend the state of the art by proposing a novel pre-processing noise Filter-aware Adversarial ML attack called FAdeML. To demonstrate the effectiveness of the proposed methodology, we generate an adversarial attack image by exploiting the "VGGNet" DNN trained for the "German Traffic Sign Recognition Benchmarks (GTSRB" dataset, which despite having no visual noise, can cause a classifier to misclassify even in the presence of pre-processing noise filters.

cs.LG↗

arXiv2018

CapsAcc: An Efficient Hardware Accelerator for CapsuleNets with Data Reuse

Deep Neural Networks (DNNs) have been widely deployed for many Machine Learning applications. Recently, CapsuleNets have overtaken traditional DNNs, because of their improved generalization ability due to the multi-dimensional capsules, in contrast to the single-dimensional neurons. Consequently, CapsuleNets also require extremely intense matrix computations, making it a gigantic challenge to achieve high performance. In this paper, we propose CapsAcc, the first specialized CMOS-based hardware architecture to perform CapsuleNets inference with high performance and energy efficiency. State-of-the-art convolutional DNN accelerators would not work efficiently for CapsuleNets, as their designs do not account for key operations involved in CapsuleNets, like squashing and dynamic routing, as well as multi-dimensional matrix processing. Our CapsAcc architecture targets this problem and achieves significant improvements, when compared to an optimized GPU implementation. Our architecture exploits the massive parallelism by flexibly feeding the data to a specialized systolic array according to the operations required in different layers. It also avoids extensive load and store operations on the on-chip memory, by reusing the data when possible. We further optimize the routing algorithm to reduce the computations needed at this stage. We synthesized the complete CapsAcc architecture in a 32nm CMOS technology using Synopsys design tools, and evaluated it for the MNIST benchmark (as also done by the original CapsuleNet paper) to ensure consistent and fair comparisons. This work enables highly-efficient CapsuleNets inference on embedded platforms.

cs.DC↗

arXiv2018

MPNA: A Massively-Parallel Neural Array Accelerator with Dataflow Optimization for Convolutional Neural Networks

The state-of-the-art accelerators for Convolutional Neural Networks (CNNs) typically focus on accelerating only the convolutional layers, but do not prioritize the fully-connected layers much. Hence, they lack a synergistic optimization of the hardware architecture and diverse dataflows for the complete CNN design, which can provide a higher potential for performance/energy efficiency. Towards this, we propose a novel Massively-Parallel Neural Array (MPNA) accelerator that integrates two heterogeneous systolic arrays and respective highly-optimized dataflow patterns to jointly accelerate both the convolutional (CONV) and the fully-connected (FC) layers. Besides fully-exploiting the available off-chip memory bandwidth, these optimized dataflows enable high data-reuse of all the data types (i.e., weights, input and output activations), and thereby enable our MPNA to achieve high energy savings. We synthesized our MPNA architecture using the ASIC design flow for a 28nm technology, and performed functional and timing validation using multiple real-world complex CNNs. MPNA achieves 149.7GOPS/W at 280MHz and consumes 239mW. Experimental results show that our MPNA architecture provides 1.7x overall performance improvement compared to state-of-the-art accelerator, and 51% energy saving compared to the baseline architecture.

cs.DC↗

arXiv2018

A Methodology for Automatic Selection of Activation Functions to Design Hybrid Deep Neural Networks

Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear counterparts. However, selecting an appropriate activation function is a challenging problem, as it affects the accuracy and the complexity of the given DNN. In this paper, we propose a novel methodology to automatically select the best-possible activation function for each layer of a given DNN, such that the overall DNN accuracy, compared to considering only one type of activation function for the whole DNN, is improved. However, an associated scientific challenge in exploring all the different configurations of activation functions would be time and resource-consuming. Towards this, our methodology identifies the Evaluation Points during learning to evaluate the accuracy in an intermediate step of training and to perform early termination by checking the accuracy gradient of the learning curve. This helps in significantly reducing the exploration time during training. Moreover, our methodology selects, for each layer, the dropout rate that optimizes the accuracy. Experiments show that we are able to achieve on average 7% to 15% Relative Error Reduction on MNIST, CIFAR-10 and CIFAR-100 benchmarks, with limited performance and power penalty on GPUs.

cs.NE↗

arXiv2017

Eliminating Tight Coupling using Subscriptions Subgrouping in Structured Overlays

Advertisements and subscriptions are tightly coupled to generate publication routing paths in content--based publish/subscribe systems. Tight coupling requires instantaneous updates in routing tables to generate alternative paths which prevents offering scalable and robust dynamic routing in cyclic overlays when link congestion is detected. We propose, OctopiA, first distributed publish/subscribe system for content--based inter--cluster dynamic routing using purpose--built structured cyclic overlays. OctopiA uses a novel concept of subscription subgrouping, which divides subscriptions into disjoint sets called subscription subgroups. The purpose--built structured cyclic overlay is divided into identical clusters where subscriptions in each subgroup are broadcast to an exclusive cluster. Our advertisement and subscription forwarding algorithms use subscription subgrouping to eliminate tight coupling to offer inter--cluster dynamic routing without requiring updates in routing tables. Experiments on a cluster testbed with real world data show that OctopiA reduces the number of saved advertisements in routing tables by 93%, subscription broadcast delay by 33%, static and dynamic publication delivery delays by 25% and 54%, respectively.

cs.DC↗

arXiv2017

Content-based Dynaic Routing in Structured Overlays Networks

Acyclic overlays used for broker-based publish/subscribe systems provide unique paths for content-based routing from a publisher to interested subscribers. Cyclic overlays may provide multiple paths, however, the subscription broadcast process generates one content-based routing path per subscription. This poses serious challenges in offering dynamic routing of notifications when congestion is detected because instantaneous updates in routing tables are required to generate alternative routing paths. This paper introduces the first subscription-based publish/subscribe system, OctopiS, which offers inter-cluster dynamic routing when congestion in the output queues is detected. OctopiS is based on a formally defined Structured Cyclic Overlay Topology (SCOT). SCOT is divided into homogeneous clusters where each cluster has equal number of brokers and connects to other clusters through multiple inter-cluster overlay links. These links are used to provide parallel routing paths between publishers and subscribers connected to brokers in different clusters. While aiming at deployment at data center networks, OctopiS generates subscription-trees of shortest lengths used by Static Notification Routing (SNR) algorithm. Dynamic Notification Routing (DNR) algorithm uses a bit-vector mechanism to exploit the structuredness of a clustered SCOT to offer inter-cluster dynamic routing without making updates in routing tables and minimizing load on overwhelmed brokers and congested links. Experiments on a cluster testbed with real world data show that OctopiS is scalable and reduces the number of inter-broker messages in subscription delivery by 89%, subscription delay by 77%, end-to-end notification delay in static and dynamic routing by 47% and 58% respectively, and the lengths of output queues of brokers in dynamic routing paths by 59%.

cs.DC↗

arXiv2016

Adaptive Content-based Routing using Subscription Subgrouping in Structured Overlays

Cyclic or general overlays may provide multiple paths between publishers and subscribers. However, an advertisement tree and a matching subscription activates only one path for notifications routing in publish/subscribe systems. This poses serious challenges in handling network conditions like congestion, and link or broker failures. Further, content-based dynamic routing of notifications requires instantaneous updates in routing paths, which is not a scalable option. This paper introduces a clustering approach with a bit-vector technique for inter-cluster dynamic routing of notifications in a structured cyclic topology that provides multiple paths between publishers and interested subscribers. The advertisement forwarding process exploits the structured nature of the overlay topology to generate advertisement trees of length 1 without generating duplicate messages in the advertisement forwarding process. Issued subscriptions are divided into multiple disjoint subgropus, where each subscription is broadcast to a cluster, which is a limited part of the structured cyclic overlay network. We implemented novel static and intra-cluster dynamic routing algorithms in the proposed overlay topology for our advertisement-based publish/subscribe system, called OctopiA. We also performed a pragmatic comparison of our two algorithms with the state-of-the-art. Experiments on a cluster testbed show that our approach generates fewer inter-broker messages, and is scalable.

cs.DC↗