Backpropagation Through Time Research Articles

Gradient-free training of recurrent neural networks using random perturbations.

Recurrent neural networks (RNNs) hold immense potential for computations due to their Turing completeness and sequential processing capabilities, yet existing methods for their training encounter efficiency challenges. Backpropagation through time (BPTT), the prevailing method, extends the backpropagation (BP) algorithm by unrolling the RNN over time. However, this approach suffers from significant drawbacks, including the need to interleave forward and backward phases and store exact gradient information. Furthermore, BPTT has been shown to struggle to propagate gradient information for long sequences, leading to vanishing gradients. An alternative strategy to using gradient-based methods like BPTT involves stochastically approximating gradients through perturbation-based methods. This learning approach is exceptionally simple, necessitating only forward passes in the network and a global reinforcement signal as feedback. Despite its simplicity, the random nature of its updates typically leads to inefficient optimization, limiting its effectiveness in training neural networks. In this study, we present a new approach to perturbation-based learning in RNNs whose performance is competitive with BPTT, while maintaining the inherent advantages over gradient-based learning. To this end, we extend the recently introduced activity-based node perturbation (ANP) method to operate in the time domain, leading to more efficient learning and generalization. We subsequently conduct a range of experiments to validate our approach. Our results show similar performance, convergence time and scalability when compared to BPTT, strongly outperforming standard node perturbation and weight perturbation methods. These findings suggest that perturbation-based learning methods offer a versatile alternative to gradient-based methods for training RNNs which can be ideally suited for neuromorphic computing applications.

Design of oscillatory neural networks by machine learning.

We demonstrate the utility of machine learning algorithms for the design of oscillatory neural networks (ONNs). After constructing a circuit model of the oscillators in a machine-learning-enabled simulator and performing Backpropagation through time (BPTT) for determining the coupling resistances between the ring oscillators, we demonstrate the design of associative memories and multi-layered ONN classifiers. The machine-learning-designed ONNs show superior performance compared to other design methods (such as Hebbian learning), and they also enable significant simplifications in the circuit topology. We also demonstrate the design of multi-layered ONNs that show superior performance compared to single-layer ones. We argue that machine learning can be a valuable tool to unlock the true computing potential of ONNs hardware.

Latest Technologies on Dataset Distillation: A Survey

Dataset distillation refers to the process of constructing a smaller dataset based on a larger dataset, so that the training model with the smaller dataset can obtain similar results to the larger dataset. In this paper, we first briefly review the basic methods and some recent advances in this field from the perspectives of meta-learning framework and data matching framework, including the backpropagation through time(BPTT), kernel ridge regression(KRR), decoupled techniques, gradient matching(DC), trajectory matching(MTT) and distribution matching(DM). The results of the plug-and-play approach in recent years are then presented. Finally, we discuss possible future developments from the perspectives of data distillation algorithms on large datasets, the relationship between compress ratio and information contained, more tasks and data modalities, and the use of generative models to improve the distillation results of datasets.

A Deep Convolutional Gated Recurrent Unit for CT Image Reconstruction.

Computed tomography (CT) is one of the most important medical imaging technologies in use today. Most commercial CT products use a technique known as the filtered backprojection (FBP) that is fast and can produce decent image quality when an X-ray dose is high. However, the FBP is not good enough on low-dose X-ray CT imaging because the CT image reconstruction problem becomes more stochastic. A more effective reconstruction technique proposed recently and implemented in a limited number of CT commercial products is an iterative reconstruction (IR). The IR technique is based on a Bayesian formulation of the CT image reconstruction problem with an explicit model of the CT scanning, including its stochastic nature, and a prior model that incorporates our knowledge about what a good CT image should look like. However, constructing such prior knowledge is more complicated than it seems. In this article, we propose a novel neural network for CT image reconstruction. The network is based on the IR formulation and constructed with a recurrent neural network (RNN). Specifically, we transform the gated recurrent unit (GRU) into a neural network performing CT image reconstruction. We call it "GRU reconstruction." This neural network conducts concurrent dual-domain learning. Many deep learning (DL)-based methods in medical imaging are single-domain learning, but dual-domain learning performs better because it learns from both the sinogram and the image domain. In addition, we propose backpropagation through stage (BPTS) as a new RNN backpropagation algorithm. It is similar to the backpropagation through time (BPTT) of an RNN; however, it is tailored for iterative optimization. Results from extensive experiments indicate that our proposed method outperforms conventional model-based methods, single-domain DL methods, and state-of-the-art DL techniques in terms of the root mean squared error (RMSE), the peak signal-to-noise ratio (PSNR), and the structure similarity (SSIM) and in terms of visual appearance.

Online Spatio-Temporal Learning in Deep Neural Networks.

Biological neural networks are equipped with an inherent capability to continuously adapt through online learning. This aspect remains in stark contrast to learning with error backpropagation through time (BPTT) that involves offline computation of the gradients due to the need to unroll the network through time. Here, we present an alternative online learning algorithm ic framework for deep recurrent neural networks (RNNs) and spiking neural networks (SNNs), called online spatio-temporal learning (OSTL). It is based on insights from biology and proposes the clear separation of spatial and temporal gradient components. For shallow SNNs, OSTL is gradient equivalent to BPTT enabling for the first time online training of SNNs with BPTT-equivalent gradients. In addition, the proposed formulation unveils a class of SNN architectures trainable online at low time complexity. Moreover, we extend OSTL to a generic form, applicable to a wide range of network architectures, including networks comprising long short-term memory (LSTM) and gated recurrent units (GRUs). We demonstrate the operation of our algorithm ic framework on various tasks from language modeling to speech recognition and obtain results on par with the BPTT baselines.

BP-SRM: A directly training algorithm for spiking neural network constructed by spike response model

Spiking neural networks (SNNs) have attracted widespread attention due to their unique bio-interpretability and low-power properties, but the non-differentiability of discrete spike sequences fired by spiking neurons brings difficulties to the learning of SNNs. Recently, surrogate gradient (SG) and back-propagation through time (BPTT) have provided an excellent idea for training SNNs constructed by leaky integrate-and-fire (LIF) neuron models. The LIF neuron model has been widely used in previous SNNs due to its simplicity and low computational cost, however, this also limits its simulation of biological neuron dynamics, reducing the biological interpretability of SNNs. In this paper, we generalize SG and BPTT to SNNs constructed by spike response model (SRM) and propose the BP-SRM algorithm. Specifically, we address why BPTT succeeded in LIF neurons-based SNNs but failed in SRM neurons-based SNNs in previous researches. Then we establish an iterative form of the SRM neuron model by selecting different state variables. Based on iterable SRM, we get the spatiotemporal dependencies between the state variables of SRM neurons-based SNNs, which allows us to derive the gradient and update weights in SNN by BP-SRM. Then we design temporal channel normalization for BP-SRM and verify the performance of the SNNs on static image dataset, dynamic image dataset and engineering dataset, including Fashion-MNIST, Weather Dataset, N-MNIST, American Sign Language Dataset and bearing fault diagnosis dataset. The experiment results indicate that BP-SRM achieves the state-of-the-art performance of SNNs.

Implementation of recurrent neural network for the forecasting of USD buy rate against IDR

<span lang="EN-US">This study implements a recurrent neural network (RNN) by comparing two RNN network structures, namely Elman and Jordan using the backpropagation through time (BPTT) programming algorithm in the training and forecasting process in foreign exchange forecasting cases. The activation functions used are the linear transfer function, the tan-sigmoid transfer function (Tansig), and the log-sigmoid transfer function (Logsig), which are applied to the hidden and output layers. The application of the activation function results in the log-sigmoid transfer function being the most appropriate activation function for the hidden layer, while the linear transfer function is the most appropriate activation function for the output layer. Based on the results of training and forecasting the USD against IDR currency, the Elman BPTT method is better than the Jordan BPTT method, with the best iteration being the 4000<sup>th</sup> iteration for both. The lowest root mean square error (RMSE) values for training and forecasting produced by Elman BPTT were 0.073477 and 122.15 the following day, while the Jordan backpropagation RNN method yielded 0.130317 and 222.96 also the following day.</span><p> </p>

SATA: Sparsity-Aware Training Accelerator for Spiking Neural Networks

Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent high-sparsity activation. Recently, SNNs with backpropagation through time (BPTT) have achieved a higher accuracy result on image recognition tasks than other SNN training algorithms. Despite the success from the algorithm perspective, prior works neglect the evaluation of the hardware energy overheads of BPTT, due to the lack of a hardware evaluation platform for this SNN training algorithm. Moreover, although SNNs have long been seen as an energy-efficient counterpart of ANNs, a quantitative comparison between the training cost of SNNs and ANNs is missing. To address the aforementioned issues, in this work, we introduce SATA (Sparsity-Aware Training Accelerator), a BPTT-based training accelerator for SNNs. The proposed SATA provides a simple and re-configurable systolic-based accelerator architecture, which makes it easy to analyze the training energy for BPTT-based SNN training algorithms. By utilizing the sparsity, SATA increases its computation energy efficiency by 5.58× compared to the one without using sparsity. Based on SATA, we show quantitative analyses of the energy efficiency of SNN training and make a comparison between the training cost of SNNs and ANNs. The results show that, on Eyeriss-like systolic-based architecture, SNNs consume 1.27× more total energy with considering sparsity (spikes, gradient of firing function, and gradient of membrane potential) when compared to ANNs. We find that such high training energy cost is from time-repetitive convolution operations and data movements during backpropagation. Moreover, to guide the future SNN training algorithm design, we provide several observations on energy efficiency with respect to different SNN-specific training parameters.

Unbiased Spatiotemporal Representation With Uncertainty Control for Person Reidentification

For person re-identification, most current research aims to encode the spatial and temporal information by using convolutional neural networks (CNNs) to extract spatial features and recurrent neural networks (RNNs) or their variations to discover the time dependencies. However, it ignores the effect of the complex background, which leads to a biased spatial representation. Further, it often uses the backpropagation through time (BPTT) to train RNNs. Unfortunately, it is hard to learn the long-term dependency via BPTT due to the gradient vanishing or exploding. The significance of a frame should not be biased by its position in a given sequence. In this paper, a new method is proposed to learn an unbiased semantic representation for video-based person re-identification. To handle the background clutter and occlusion, a two-branch CNN model is used to obtain the enriched representation from both the foreground person and original pedestrian images. Then, an unbiased bidirectional convolutional neural network architecture is developed to learn the unbiased spatial and temporal representation. Experimental results on three public datasets demonstrate the effectiveness of the proposed method.

Batch normalization-free weight-binarized SNN based on hardware-saving IF neuron

Neuromorphic computing realizes low-latency and low-power computing by emulating the neural structure and operation of the human brain, and is considered a key research area for third-generation artificial intelligence. However, current neuromorphic computing faces the problems of huge synaptic memory consumption and complex neuron calculations. This paper proposes a batch normalization (BN)-free weight-binarized SNN based on hardware-saving IF neurons to reduce storage requirements and improve the computational efficiency of neuromorphic computing. Hardware-friendly backpropagation through time (BPTT)-based algorithm and SG function are proposed to calculate the gradients of the “integrate” process and “fire” process of IF neuron, respectively. Weight binarization is carried out during training to reduce storage requirements, and spatio-temporal batch normalization (BN) operations are introduced to ensure high performance. During inference, a simple adaptive-threshold IF neuron model is proposed to achieve the effect equivalent to the computationally expensive spatio-temporal BN operation without any performance loss. The proposed BN-free binarized SNNs based on hardware-saving IF neuron achieves competitive accuracies of 99.36%, 94.79%, 90.39%, and 67.10% on the N-MNIST, DvsGesture, N-TIDIGITS18, and DVS-CIFAR10 datasets, respectively, which are comparable to full-precision SNNs, but the weight sizes are significantly reduced by ∼ 97%. Furthermore, robustness experiments show that the binary SNN is more robust to weight noise than the full-precision SNN. This paper presents an efficient algorithm-hardware co-design paradigm for hardware-friendly and high-performance neuromorphic computing.

Efficient training of spiking neural networks with temporally-truncated local backpropagation through time.

Directly training spiking neural networks (SNNs) has remained challenging due to complex neural dynamics and intrinsic non-differentiability in firing functions. The well-known backpropagation through time (BPTT) algorithm proposed to train SNNs suffers from large memory footprint and prohibits backward and update unlocking, making it impossible to exploit the potential of locally-supervised training methods. This work proposes an efficient and direct training algorithm for SNNs that integrates a locally-supervised training method with a temporally-truncated BPTT algorithm. The proposed algorithm explores both temporal and spatial locality in BPTT and contributes to significant reduction in computational cost including GPU memory utilization, main memory access and arithmetic operations. We thoroughly explore the design space concerning temporal truncation length and local training block size and benchmark their impact on classification accuracy of different networks running different types of tasks. The results reveal that temporal truncation has a negative effect on the accuracy of classifying frame-based datasets, but leads to improvement in accuracy on event-based datasets. In spite of resulting information loss, local training is capable of alleviating overfitting. The combined effect of temporal truncation and local training can lead to the slowdown of accuracy drop and even improvement in accuracy. In addition, training deep SNNs' models such as AlexNet classifying CIFAR10-DVS dataset leads to 7.26% increase in accuracy, 89.94% reduction in GPU memory, 10.79% reduction in memory access, and 99.64% reduction in MAC operations compared to the standard end-to-end BPTT. Thus, the proposed method has shown high potential to enable fast and energy-efficient on-chip training for real-time learning at the edge.

Presynaptic spike-driven plasticity based on eligibility trace for on-chip learning system.

Recurrent spiking neural network (RSNN) performs excellently in spatio-temporal learning with backpropagation through time (BPTT) algorithm. But the requirement of computation and memory in BPTT makes it hard to realize an on-chip learning system based on RSNN. In this paper, we aim to realize a high-efficient RSNN learning system on field programmable gate array (FPGA). A presynaptic spike-driven plasticity architecture based on eligibility trace is implemented to reduce the resource consumption. The RSNN with leaky integrate-and-fire (LIF) and adaptive LIF (ALIF) models is implemented on FPGA based on presynaptic spike-driven architecture. In this architecture, the eligibility trace gated by a learning signal is used to optimize synaptic weights without unfolding the network through time. When a presynaptic spike occurs, the eligibility trace is calculated based on its latest timestamp and drives synapses to update their weights. Only the latest timestamps of presynaptic spikes are required to be stored in buffers to calculate eligibility traces. We show the implementation of this architecture on FPGA and test it with two experiments. With the presynaptic spike-driven architecture, the resource consumptions, including look-up tables (LUTs) and registers, and dynamic power consumption of synaptic modules in the on-chip learning system are greatly reduced. The experiment results and compilation results show that the buffer size of the on-chip learning system is reduced and the RSNNs implemented on FPGA exhibit high efficiency in resources and energy while accurately solving tasks. This study provides a solution to the problem of data congestion in the buffer of large-scale learning systems.

EXODUS: Stable and efficient training of spiking neural networks.

Spiking Neural Networks (SNNs) are gaining significant traction in machine learning tasks where energy-efficiency is of utmost importance. Training such networks using the state-of-the-art back-propagation through time (BPTT) is, however, very time-consuming. Previous work employs an efficient GPU-accelerated backpropagation algorithm called SLAYER, which speeds up training considerably. SLAYER, however, does not take into account the neuron reset mechanism while computing the gradients, which we argue to be the source of numerical instability. To counteract this, SLAYER introduces a gradient scale hyper parameter across layers, which needs manual tuning. In this paper, we modify SLAYER and design an algorithm called EXODUS, that accounts for the neuron reset mechanism and applies the Implicit Function Theorem (IFT) to calculate the correct gradients (equivalent to those computed by BPTT). We furthermore eliminate the need for ad-hoc scaling of gradients, thus, reducing the training complexity tremendously. We demonstrate, via computer simulations, that EXODUS is numerically stable and achieves comparable or better performance than SLAYER especially in various tasks with SNNs that rely on temporal features.

Modulating STDP With Back-Propagated Error Signals to Train SNNs for Audio Classification

Audio classification has many practical applications such as noise pollution detection, wildlife monitoring, speech recognition, and more. For many of these applications, deploying classifiers on low powered devices for persistent deployment is desirable. Artificial neural networks (ANN) have achieved state-of-the-art performance on audio classification tasks; however, it is not always feasible to deploy modern ANNs to embedded devices due to their high power consumption. Biologically inspired spiking neural networks (SNN) have been shown to significantly reduce power consumption during inference when compared with equivalent ANNs, and they have also been theoretically proven to be more computationally powerful than stateless ANNs. This work proposes an audio classification system using SNNs, and a learning algorithm is developed for classification with multilayer SNNs which combines biologically plausible spike-timing-dependent plasticity (STDP) with spatial error backpropagation. By allowing the STDP process to account for both temporal dependencies and the non-differentiable activation function derivative, the proposed learning rule successfully trains multilayer SNNs for the considered classification tasks. Through the STDP process, the proposed learning rule is also capable of online learning; explicit storage of values from previous timesteps is not required, in contrast to the widely adopted backpropagation through time (BPTT) algorithm. The proposed approach approaches the performance of SNNs trained via BPTT on the classification tasks. SNNs trained with the proposed learning rule are evaluated on the Iris Flower dataset, the Real-World Computing Partnership sounds dataset, the Free Spoken Digits Dataset, and the UrbanSound8k dataset.

Toward robust and scalable deep spiking reinforcement learning.

Deep reinforcement learning (DRL) combines reinforcement learning algorithms with deep neural networks (DNNs). Spiking neural networks (SNNs) have been shown to be a biologically plausible and energy efficient alternative to DNNs. Since the introduction of surrogate gradient approaches that allowed to overcome the discontinuity in the spike function, SNNs can now be trained with the backpropagation through time (BPTT) algorithm. While largely explored on supervised learning problems, little work has been done on investigating the use of SNNs as function approximators in DRL. Here we show how SNNs can be applied to different DRL algorithms like Deep Q-Network (DQN) and Twin-Delayed Deep Deteministic Policy Gradient (TD3) for discrete and continuous action space environments, respectively. We found that SNNs are sensitive to the additional hyperparameters introduced by spiking neuron models like current and voltage decay factors, firing thresholds, and that extensive hyperparameter tuning is inevitable. However, we show that increasing the simulation time of SNNs, as well as applying a two-neuron encoding to the input observations helps reduce the sensitivity to the membrane parameters. Furthermore, we show that randomizing the membrane parameters, instead of selecting uniform values for all neurons, has stabilizing effects on the training. We conclude that SNNs can be utilized for learning complex continuous control problems with state-of-the-art DRL algorithms. While the training complexity increases, the resulting SNNs can be directly executed on neuromorphic processors and potentially benefit from their high energy efficiency.

Gradient-Based Neuromorphic Learning on Dynamical RRAM Arrays

We present MEMprop, the adoption of gradient-based learning to train fully memristive spiking neural networks (MSNNs). Our approach harnesses intrinsic device dynamics to trigger naturally arising voltage spikes. These spikes emitted by memristive dynamics are analog in nature, and thus fully differentiable, which eliminates the need for surrogate gradient methods that are prevalent in the spiking neural network (SNN) literature. Memristive neural networks typically either integrate memristors as synapses that map offline-trained networks, or otherwise rely on associative learning mechanisms to train networks of memristive neurons. We instead apply the backpropagation through time (BPTT) training algorithm directly on analog SPICE models of memristive neurons and synapses. Our implementation is fully memristive, in that synaptic weights and spiking neurons are both integrated on resistive RAM (RRAM) arrays without the need for additional circuits to implement spiking dynamics, e.g., analog-to-digital converters (ADCs) or thresholded comparators. As a result, higher-order electrophysical effects are fully exploited to use the state-driven dynamics of memristive neurons at run time. By moving towards non-approximate gradient-based learning, we obtain highly competitive accuracy amongst previously reported lightweight dense fully MSNNs on several benchmarks.

E-prop on SpiNNaker 2: Exploring online learning in spiking RNNs on neuromorphic hardware.

In recent years, the application of deep learning models at the edge has gained attention. Typically, artificial neural networks (ANNs) are trained on graphics processing units (GPUs) and optimized for efficient execution on edge devices. Training ANNs directly at the edge is the next step with many applications such as the adaptation of models to specific situations like changes in environmental settings or optimization for individuals, e.g., optimization for speakers for speech processing. Also, local training can preserve privacy. Over the last few years, many algorithms have been developed to reduce memory footprint and computation. A specific challenge to train recurrent neural networks (RNNs) for processing sequential data is the need for the Back Propagation Through Time (BPTT) algorithm to store the network state of all time steps. This limitation is resolved by the biologically-inspired E-prop approach for training Spiking Recurrent Neural Networks (SRNNs). We implement the E-prop algorithm on a prototype of the SpiNNaker 2 neuromorphic system. A parallelization strategy is developed to split and train networks on the ARM cores of SpiNNaker 2 to make efficient use of both memory and compute resources. We trained an SRNN from scratch on SpiNNaker 2 in real-time on the Google Speech Command dataset for keyword spotting. We achieved an accuracy of 91.12% while requiring only 680 KB of memory for training the network with 25 K weights. Compared to other spiking neural networks with equal or better accuracy, our work is significantly more memory-efficient. In addition, we performed a memory and time profiling of the E-prop algorithm. This is used on the one hand to discuss whether E-prop or BPTT is better suited for training a model at the edge and on the other hand to explore architecture modifications to SpiNNaker 2 to speed up online learning. Finally, energy estimations predict that the SRNN can be trained on SpiNNaker2 with 12 times less energy than using a NVIDIA V100 GPU.

Braille letter reading: A benchmark for spatio-temporal pattern recognition on neuromorphic hardware.

Spatio-temporal pattern recognition is a fundamental ability of the brain which is required for numerous real-world activities. Recent deep learning approaches have reached outstanding accuracies in such tasks, but their implementation on conventional embedded solutions is still very computationally and energy expensive. Tactile sensing in robotic applications is a representative example where real-time processing and energy efficiency are required. Following a brain-inspired computing approach, we propose a new benchmark for spatio-temporal tactile pattern recognition at the edge through Braille letter reading. We recorded a new Braille letters dataset based on the capacitive tactile sensors of the iCub robot's fingertip. We then investigated the importance of spatial and temporal information as well as the impact of event-based encoding on spike-based computation. Afterward, we trained and compared feedforward and recurrent Spiking Neural Networks (SNNs) offline using Backpropagation Through Time (BPTT) with surrogate gradients, then we deployed them on the Intel Loihi neuromorphic chip for fast and efficient inference. We compared our approach to standard classifiers, in particular to the Long Short-Term Memory (LSTM) deployed on the embedded NVIDIA Jetson GPU, in terms of classification accuracy, power, and energy consumption together with computational delay. Our results show that the LSTM reaches ~97% of accuracy, outperforming the recurrent SNN by ~17% when using continuous frame-based data instead of event-based inputs. However, the recurrent SNN on Loihi with event-based inputs is ~500 times more energy-efficient than the LSTM on Jetson, requiring a total power of only ~30 mW. This work proposes a new benchmark for tactile sensing and highlights the challenges and opportunities of event-based encoding, neuromorphic hardware, and spike-based computing for spatio-temporal pattern recognition at the edge.

H2Learn: High-Efficiency Learning Accelerator for High-Accuracy Spiking Neural Networks

Although spiking neural networks (SNNs) take benefits from the bioplausible neural modeling, the low accuracy under the common local synaptic plasticity learning rules limits their application in many practical tasks. Recently, an emerging SNN supervised learning algorithm inspired by backpropagation through time (BPTT) from the domain of artificial neural networks (ANNs) has successfully boosted the accuracy of SNNs, and helped improve the practicability of SNNs. However, current general-purpose processors suffer from low efficiency when performing BPTT for SNNs due to the ANN-tailored optimization. On the other hand, current neuromorphic chips cannot support BPTT because they mainly adopt local synaptic plasticity rules for simplified implementation. In this work, we propose H2Learn, a novel architecture that can achieve high efficiency for BPTT-based SNN learning, which ensures high accuracy of SNNs. At the beginning, we characterized the behaviors of BPTT-based SNN learning. Benefited from the binary spike-based computation in the forward pass and weight update, we first design look-up table (LUT)-based processing elements in the forward engine and weight update engine to make accumulations implicit and to fuse the computations of multiple input points. Second, benefited from the rich sparsity in the backward pass, we design a dual-sparsity-aware backward engine, which exploits both input and output sparsity. Finally, we apply a pipeline optimization between different engines to build an end-to-end solution for the BPTT-based SNN learning. Compared with the modern NVIDIA V100 GPU, H2Learn achieves <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$7.38\times $ </tex-math></inline-formula> area saving, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$5.74-10.20\times $ </tex-math></inline-formula> speedup, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$5.25-7.12\times $ </tex-math></inline-formula> energy saving on several benchmark datasets.

A Privacy-Preserving-Based Secure Framework Using Blockchain-Enabled Deep-Learning in Cooperative Intelligent Transport System

Cooperative Intelligent Transport System (C-ITS) is a promising technology that aims to improve the traditional transport management systems. In C-ITS infrastructure Autonomous Vehicles (AVs) communicate wirelessly with other AVs, Road Side Units (RSUs) and Traffic Command Centres (TCCs) using an open channel Internet. However, the use of the Internet brings inherent vulnerabilities related to privacy (e.g., adversary performing inference and data poisoning attacks), and security (e.g., AVs can be compromised using advanced hacking techniques) issues and prevents the faster realization of C-ITS applications. To address these challenges, this paper presents a privacy-preserving-based secure framework to provide both privacy and security in C-ITS infrastructure. The proposed framework provides two level of security and privacy using blockchain and deep learning modules. First, a blockchain module is designed to securely transmit the C-ITS data between AVs–RSUs-TCCs, and a smart contract-based enhanced Proof of Work (ePoW) technique is designed to verify data integrity and mitigate data poisoning attacks. Second, a deep-learning module is designed that includes Long-Short Term Memory-AutoEncoder (LSTM-AE) technique for encoding C-ITS data into a new format to prevent inference attacks. The encoded data is used by the proposed Attention-based Recurrent Neural Network (A-RNN), for intrusive events recognition in C-ITS infrastructure. The proposed A-RNN is trained using Truncated Backpropagation Through Time (BPTT) algorithm. The framework is further validated and tested using two publicly available ToN-IoT and CICIDS-2017 datasets. The proposed framework is compared with peer privacy-preserving intrusion detection techniques, and the result shows the effectiveness of the proposed framework over several state-of-the-art techniques in both blockchain and non-blockchain systems.