Biblio

Next Word Prediction involves guessing the next word which is most likely to come after the current word. The system suggests a few words. A user can choose a word according to their choice from a list of suggested word by system. It increases typing speed and reduces keystrokes of the user. It is also useful for disabled people to enter text slowly and for those who are not good with spellings. Previous studies focused on prediction of the next word in different languages. Some of them are Bangla, Assamese, Ukraine, Kurdish, English, and Hindi. According to Census 2011, 43.63% of the Indian population uses Hindi, the national language of India. In this work, deep learning techniques are proposed to predict the next word in Hindi language. The paper uses Long Short Term Memory and Bidirectional Long Short Term Memory as the base neural network architecture. The model proposed in this work outperformed the existing approaches and achieved the best accuracy among neural network based approaches on IITB English-Hindi parallel corpus.

Keystroke dynamics is one solution to enhance the security of password authentication without adding any disruptive handling for users. Industries are looking for more security without impacting too much user experience. Considered as a friction-less solution, keystroke dynamics is a powerful solution to increase trust during user authentication without adding charge to the user. In this paper, we address the problem of user authentication considering the keystroke dynamics modality. We proposed a new approach based on the conversion of behavioral biometrics data (time series) into a 3D image. This transformation process keeps all the characteristics of the behavioral signal. The time series do not receive any filtering operation with this transformation and the method is bijective. This transformation allows us to train images based on convolutional neural networks. We evaluate the performance of the authentication system in terms of Equal Error Rate (EER) on a significant dataset and we show the efficiency of the proposed approach on a multi-instance system.

On the Internet of Battlefield Things (IoBT), unmanned aerial vehicles (UAVs) provide significant operational advantages. However, the exploitation of the UAV by an untrustworthy entity might lead to security violations or possibly the destruction of crucial IoBT network functionality. The IoBT system has substantial issues related to data tampering and fabrication through illegal access. This paper proposes the use of an intelligent architecture called IoBT-Net, which is built on a convolution neural network (CNN) and connected with blockchain technology, to identify and trace illicit UAV in the IoBT system. Data storage on the blockchain ledger is protected from unauthorized access, data tampering, and invasions. Conveniently, this paper presents a low complexity and robustly performed CNN called LRCANet to estimate AOA for object localization. The proposed LRCANet is efficiently designed with two core modules, called GFPU and stacks, which are cleverly organized with regular and point convolution layers, a max pool layer, and a ReLU layer associated with residual connectivity. Furthermore, the effectiveness of LRCANET is evaluated by various network and array configurations, RMSE, and compared with the accuracy and complexity of the existing state-of-the-art. Additionally, the implementation of tailored drone-based consensus is evaluated in terms of three major classes and compared with the other existing consensus.

In this paper, we established a unified deep learning-based spam filtering method. The proposed method uses the message byte-histograms as a unified representation for all message types (text, images, or any other format). A deep convolutional neural network (CNN) is used to extract high-level features from this representation. A fully connected neural network is used to perform the classification using the extracted CNN features. We validate our method using several open-source text-based and image-based spam datasets.We obtained an accuracy higher than 94% on all datasets.

The new architecture of transformer networks proposed in the work can be used to create an intelligent chat bot that can learn the process of communication and immediately model responses based on what has been said. The essence of the new mechanism is to divide the information flow into two branches containing the history of the dialogue with different levels of granularity. Such a mechanism makes it possible to build and develop the personality of a dialogue agent in the process of dialogue, that is, to accurately imitate the natural behavior of a person. This gives the interlocutor (client) the feeling of talking to a real person. In addition, making modifications to the structure of such a network makes it possible to identify a likely attack using social engineering methods. The results obtained after training the created system showed the fundamental possibility of using a neural network of a new architecture to generate responses close to natural ones. Possible options for using such neural network dialogue agents in various fields, and, in particular, in information security systems, are considered. Possible options for using such neural network dialogue agents in various fields, and, in particular, in information security systems, are considered. The new technology can be used in social engineering attack detection systems, which is a big problem at present. The novelty and prospects of the proposed architecture of the neural network also lies in the possibility of creating on its basis dialogue systems with a high level of biological plausibility.

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code that supports symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development tends to produce DL code that is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, less error-prone imperative DL frameworks encouraging eager execution have emerged at the expense of run-time performance. While hybrid approaches aim for the “best of both worlds,” the challenges in applying them in the real world are largely unknown. We conduct a data-driven analysis of challenges-and resultant bugs-involved in writing reliable yet performant imperative DL code by studying 250 open-source projects, consisting of 19.7 MLOC, along with 470 and 446 manually examined code patches and bug reports, respectively. The results indicate that hybridization: (i) is prone to API misuse, (ii) can result in performance degradation-the opposite of its intention, and (iii) has limited application due to execution mode incompatibility. We put forth several recommendations, best practices, and anti-patterns for effectively hybridizing imperative DL code, potentially benefiting DL practitioners, API designers, tool developers, and educators.

Phishing has become a prominent method of data theft among hackers, and it continues to develop. In recent years, many strategies have been developed to identify phishing website attempts using machine learning particularly. However, the algorithms and classification criteria that have been used are highly different from the real issues and need to be compared. This paper provides a detailed comparison and evaluation of the performance of several machine learning algorithms across multiple datasets. Two phishing website datasets were used for the experiments: the Phishing Websites Dataset from UCI (2016) and the Phishing Websites Dataset from Mendeley (2018). Because these datasets include different types of class labels, the comparison algorithms can be applied in a variety of situations. The tests showed that Random Forest was better than other classification methods, with an accuracy of 88.92% for the UCI dataset and 97.50% for the Mendeley dataset.

Phishing activity is undertaken by the hackers to compromise the computer networks and financial system. A compromised computer system or network provides data and or processing resources to the world of cybercrime. Cybercrimes are projected to cost the world \$6 trillion by 2021, in this context phishing is expected to continue being a growing challenge. Statistics around phishing growth over the last decade support this theory as phishing numbers enjoy almost an exponential growth over the period. Recent reports on the complexity of the phishing show that the fight against phishing URL as a means of building more resilient cyberspace is an evolving challenge. Compounding the problem is the lack of cyber security expertise to handle the expected rise in incidents. Previous research have proposed different methods including neural network, data mining technique, heuristic-based phishing detection technique, machine learning to detect phishing websites. However, recently phishers have started to use more sophisticated techniques to attack the internet users such as VoIP phishing, spear phishing etc. For these modern methods, the traditional ways of phishing detection provide low accuracy. Hence, the requirement arises for the application and development of modern tools and techniques to use as a countermeasure against such phishing attacks. Keeping in view the nature of recent phishing attacks, it is imperative to develop a state-of-the art anti-phishing tool which should be able to predict the phishing attacks before the occurrence of actual phishing incidents. We have designed such a tool that will work efficiently to detect the phishing websites so that a user can understand easily the risk of using of his personal and financial data.

In today’s fast pacing world, cybercrimes have time and again proved to be one of the biggest hindrances in national development. According to recent trends, most of the times the victim’s data is breached by trapping it in a phishing attack. Security and privacy of user’s data has become a matter of tremendous concern. In order to address this problem and to protect the naive user’s data, a tool which may help to identify whether a window executable is malicious or not by doing static analysis on it has been proposed. As well as a comparative study has been performed by implementing different classification models like Logistic Regression, Neural Network, SVM. The static analysis approach used takes into parameters of the executables, analysis of properties obtained from PE Section Headers i.e. API calls. Comparing different model will provide the best model to be used for static malware analysis

With the electric power distribution grid facing ever increasing complexity and new threats from cyber-attacks, situational awareness for system operators is quickly becoming indispensable. Identifying de-energized lines on the distribution system during a SCADA communication failure is a prime example where operators need to act quickly to deal with an emergent loss of service. Loss of cellular towers, poor signal strength, and even cyber-attacks can impact SCADA visibility of line devices on the distribution system. Neural Networks (NNs) provide a unique approach to learn the characteristics of normal system behavior, identify when abnormal conditions occur, and flag these conditions for system operators. This study applies a 24-hour load forecast for distribution line devices given the weather forecast and day of the week, then determines the current state of distribution devices based on changes in SCADA analogs from communicating line devices. A neural network-based algorithm is applied to historical events on Alabama Power's distribution system to identify de-energized sections of line when a significant amount of SCADA information is hidden.

Aiming at the prevention of information security risk in protection and control of smart substation, a multi-level security defense method of substation based on data aggregation and convolution neural network (CNN) is proposed. Firstly, the intelligent electronic device(IED) uses "digital certificate + digital signature" for the first level of identity authentication, and uses UKey identification code for the second level of physical identity authentication; Secondly, the device group of the monitoring layer judges whether the data report is tampered during transmission according to the registration stage and its own ID information, and the device group aggregates the data using the credential information; Finally, the convolution decomposition technology and depth separable technology are combined, and the time factor is introduced to control the degree of data fusion and the number of input channels of the network, so that the network model can learn the original data and fused data at the same time. Simulation results show that the proposed method can effectively save communication overhead, ensure the reliable transmission of messages under normal and abnormal operation, and effectively improve the security defense ability of smart substation.

With the considerable success achieved by modern fuzzing in-frastructures, more crashes are produced than ever before. To dig out the root cause, rapid and faithful crash triage for large numbers of crashes has always been attractive. However, hindered by the practical difficulty of reducing analysis imprecision without compromising efficiency, this goal has not been accomplished. In this paper, we present an end-to-end crash triage solution Default, for accurately and quickly pinpointing unique root cause from large numbers of crashes. In particular, we quantify the “crash relevance” of program entities based on mutual information, which serves as the criterion of unique crash bucketing and allows us to bucket massive crashes without pre-analyzing their root cause. The quantification of “crash relevance” is also used in the shortening of long crashing traces. On this basis, we use the interpretability of neural networks to precisely pinpoint the root cause in the shortened traces by evaluating each basic block's impact on the crash label. Evaluated with 20 programs with 22216 crashes in total, Default demonstrates remarkable accuracy and performance, which is way beyond what the state-of-the-art techniques can achieve: crash de-duplication was achieved at a super-fast processing speed - 0.017 seconds per crashing trace, without missing any unique bugs. After that, it identifies the root cause of 43 unique crashes with no false negatives and an average false positive rate of 9.2%.

Trojan attacks threaten deep neural networks (DNNs) by poisoning them to behave normally on most samples, yet to produce manipulated results for inputs attached with a particular trigger. Several works attempt to detect whether a given DNN has been injected with a specific trigger during the training. In a parallel line of research, the lottery ticket hypothesis reveals the existence of sparse sub-networks which are capable of reaching competitive performance as the dense network after independent training. Connecting these two dots, we investigate the problem of Trojan DNN detection from the brand new lens of sparsity, even when no clean training data is available. Our crucial observation is that the Trojan features are significantly more stable to network pruning than benign features. Leveraging that, we propose a novel Trojan network detection regime: first locating a “winning Trojan lottery ticket” which preserves nearly full Trojan information yet only chance-level performance on clean inputs; then recovering the trigger embedded in this already isolated sub-network. Extensive experiments on various datasets, i.e., CIFAR-10, CIFAR-100, and ImageNet, with different network architectures, i.e., VGG-16, ResNet-18, ResNet-20s, and DenseNet-100 demonstrate the effectiveness of our proposal. Codes are available at https://github.com/VITA-Group/Backdoor-LTH.

Vehicular crowdsensing (VCS) is a subset of crowd-sensing where data collection is outsourced to group vehicles. Here, an entity interested in collecting data from a set of Places of Sensing Interest (PsI), advertises a set of sensing tasks, and the associated rewards. Vehicles attracted by the offered rewards deviate from their ongoing trajectories to visit and collect from one or more PsI. In this win-to-win scenario, vehicles reach their final destination with the extra reward, and the entity obtains the desired samples. Unfortunately, the efficiency of VCS can be undermined by the Sybil attack, in which an attacker can benefit from the injection of false vehicle identities. In this paper, we present a case study and analyze the effects of such an attack. We also propose a defense mechanism based on generative adversarial neural networks (GANs). We discuss GANs' advantages, and drawbacks in the context of VCS, and new trends in GANs' training that make them suitable for VCS.

Physical layer security is an emerging security area to tackle wireless security communications issues and complement conventional encryption-based techniques. Thus, we propose a novel scheme based on swarm intelligence optimization technique and a deep neural network (DNN) for maximizing the secrecy energy efficiency (SEE) in a cooperative relaying underlay cognitive radio- and non-orthogonal multiple access (NOMA) system with a non-linear energy harvesting user which is exposed to multiple eavesdroppers. Satisfactorily, simulation results show that the proposed particle swarm optimization (PSO)-DNN framework achieves close performance to that of the optimal solutions, with a meaningful reduction in computation complexity.

In the computer field, cybersecurity has always been the focus of attention. How to detect malware is one of the focuses and difficulties in network security research effectively. Traditional existing malware detection schemes can be mainly divided into two methods categories: database matching and the machine learning method. With the rise of deep learning, more and more deep learning methods are applied in the field of malware detection. Deeper semantic features can be extracted via deep neural network. The main tasks of this paper are as follows: (1) Using machine learning methods and one-dimensional convolutional neural networks to detect malware (2) Propose a machine The method of combining learning and deep learning is used for detection. Machine learning uses LGBM to obtain an accuracy rate of 67.16%, and one-dimensional CNN obtains an accuracy rate of 72.47%. In (2), LGBM is used to screen the importance of features and then use a one-dimensional convolutional neural network, which helps to further improve the detection result has an accuracy rate of 78.64%.

Recent advancements in Deep Neural Networks (DNNs) have enabled widespread deployment in multiple security-sensitive domains. The need for resource-intensive training and the use of valuable domain-specific training data have made these models the top intellectual property (IP) for model owners. One of the major threats to DNN privacy is model extraction attacks where adversaries attempt to steal sensitive information in DNN models. In this work, we propose an advanced model extraction framework DeepSteal that steals DNN weights remotely for the first time with the aid of a memory side-channel attack. Our proposed DeepSteal comprises two key stages. Firstly, we develop a new weight bit information extraction method, called HammerLeak, through adopting the rowhammer-based fault technique as the information leakage vector. HammerLeak leverages several novel system-level techniques tailored for DNN applications to enable fast and efficient weight stealing. Secondly, we propose a novel substitute model training algorithm with Mean Clustering weight penalty, which leverages the partial leaked bit information effectively and generates a substitute prototype of the target victim model. We evaluate the proposed model extraction framework on three popular image datasets (e.g., CIFAR-10/100/GTSRB) and four DNN architectures (e.g., ResNet-18/34/Wide-ResNetNGG-11). The extracted substitute model has successfully achieved more than 90% test accuracy on deep residual networks for the CIFAR-10 dataset. Moreover, our extracted substitute model could also generate effective adversarial input samples to fool the victim model. Notably, it achieves similar performance (i.e., 1-2% test accuracy under attack) as white-box adversarial input attack (e.g., PGD/Trades).

With the future 6G era, spiking neural networks (SNNs) can be powerful processing tools in various areas due to their strong artificial intelligence (AI) processing capabilities, such as biometric recognition, AI robotics, autonomous drive, and healthcare. However, within Cyber Physical System (CPS), SNNs are surprisingly vulnerable to adversarial examples generated by benign samples with human-imperceptible noise, this will lead to serious consequences such as face recognition anomalies, autonomous drive-out of control, and wrong medical diagnosis. Only by fully understanding the principles of adversarial attacks with adversarial samples can we defend against them. Nowadays, most existing adversarial attacks result in a severe accuracy degradation to trained SNNs. Still, the critical issue is that they only generate adversarial samples by randomly adding, deleting, and flipping spike trains, making them easy to identify by filters, even by human eyes. Besides, the attack performance and speed also can be improved further. Hence, Spike Probabilistic Attack (SPA) is presented in this paper and aims to generate adversarial samples with more minor perturbations, greater model accuracy degradation, and faster iteration. SPA uses Poisson coding to generate spikes as probabilities, directly converting input data into spikes for faster speed and generating uniformly distributed perturbation for better attack performance. Moreover, an objective function is constructed for minor perturbations and keeping attack success rate, which speeds up the convergence by adjusting parameters. Both white-box and black-box settings are conducted to evaluate the merits of SPA. Experimental results show the model's accuracy under white-box attack decreases by 9.2S% 31.1S% better than others, and average success rates are 74.87% under the black-box setting. The experimental results indicate that SPA has better attack performance than other existing attacks in the white-box and better transferability performance in the black-box setting,

The wide application of deep learning techniques is boosting the regulation of deep learning models, especially deep neural networks (DNN), as commercial products. A necessary prerequisite for such regulations is identifying the owner of deep neural networks, which is usually done through the watermark. Current DNN watermarking schemes, particularly white-box ones, are uniformly fragile against a family of functionality equivalence attacks, especially the neuron permutation. This operation can effortlessly invalidate the ownership proof and escape copyright regulations. To enhance the robustness of white-box DNN watermarking schemes, this paper presents a procedure that aligns neurons into the same order as when the watermark is embedded, so the watermark can be correctly recognized. This neuron alignment process significantly facilitates the functionality of established deep neural network watermarking schemes.

Recent works have empirically shown that neural network interpretability is susceptible to malicious manipulations. However, existing attacks against Interpretable Deep Learning Systems (IDLSes) all focus on the white-box setting, which is obviously unpractical in real-world scenarios. In this paper, we make the first attempt to attack IDLSes in the decision-based black-box setting. We propose a new framework called Dual Black-box Adversarial Attack (DBAA) which can generate adversarial examples that are misclassified as the target class, yet have very similar interpretations to their benign cases. We conduct comprehensive experiments on different combinations of classifiers and interpreters to illustrate the effectiveness of DBAA. Empirical results show that in all the cases, DBAA achieves high attack success rates and Intersection over Union (IoU) scores.

XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a single explanation, which fails to account for the diversity of human thoughts and experiences in language. This paper thus addresses this gap, by proposing a generative XAI framework, INTERACTION (explain aNd predicT thEn queRy with contextuAl CondiTional varIational autO-eNcoder). Our novel framework presents explanation in two steps: (step one) Explanation and Label Prediction; and (step two) Diverse Evidence Generation. We conduct intensive experiments with the Transformer architecture on a benchmark dataset, e-SNLI [1]. Our method achieves competitive or better performance against state-of-the-art baseline models on explanation generation (up to 4.7% gain in BLEU) and prediction (up to 4.4% gain in accuracy) in step one; it can also generate multiple diverse explanations in step two.

This work proposed a unified approach to increase the explainability of the predictions made by Convolution Neural Networks (CNNs) on medical images using currently available Explainable Artificial Intelligent (XAI) techniques. This method in-cooperates multiple techniques such as LISA aka Local Interpretable Model Agnostic Explanations (LIME), integrated gradients, Anchors and Shapley Additive Explanations (SHAP) which is Shapley values-based approach to provide explanations for the predictions provided by Blackbox models. This unified method increases the confidence in the black-box model’s decision to be employed in crucial applications under the supervision of human specialists. In this work, a Chest X-ray (CXR) classification model for identifying Covid-19 patients is trained using transfer learning to illustrate the applicability of XAI techniques and the unified method (LISA) to explain model predictions. To derive predictions, an image-net based Inception V2 model is utilized as the transfer learning model.

Security is of importance for communication networks, and many network nodes, like sensors and IoT devices, are resource-constrained. Physical Unclonable Functions (PUFs) leverage physical variations of the integrated circuits to produce responses unique to individual circuits and have the potential for delivering security for low-cost networks. But before a PUF can be adopted for security applications, all security vulnerabilities must be discovered. Recently, a new PUF known as Interpose PUF (IPUF) was proposed, which was tested to be secure against reliability-based modeling attacks and machine learning attacks when the attacked IPUF is of small size. A recent study showed IPUFs succumbed to a divide-and-conquer attack, and the attack method requires the position of the interpose bit known to the attacker, a condition that can be easily obfuscated by using a random interpose position. Thus, large IPUFs may still remain secure against all known modeling attacks if the interpose position is unknown to attackers. In this paper, we present a new modeling attack method of IPUFs using multilayer neural networks, and the attack method requires no knowledge of the interpose position. Our attack was tested on simulated IPUFs and silicon IPUFs implemented on FPGAs, and the results showed that many IPUFs which were resilient against existing attacks cannot withstand our new attack method, revealing a new vulnerability of IPUFs by re-defining the boundary between secure and insecure regions in the IPUF parameter space.

Over past years, the high demand to efficiently process deep learning (DL) models has driven the market of the chip design companies. However, the new Deep Chip architectures, a common term to refer to DL hardware accelerator, have slightly paid attention to the security requirements in quantized neural networks (QNNs), while the black/white -box adversarial attacks can jeopardize the integrity of the inference accelerator. Therefore in this paper, a comprehensive study of the resiliency of QNN topologies to black-box attacks is examined. Herein, different attack scenarios are performed on an FPGA-processor co-design, and the collected results are extensively analyzed to give an estimation of the impact’s degree of different types of attacks on the QNN topology. To be specific, we evaluated the sensitivity of the QNN accelerator to a range number of bit-flip attacks (BFAs) that might occur in the operational lifetime of the device. The BFAs are injected at uniformly distributed times either across the entire QNN or per individual layer during the image classification. The acquired results are utilized to build the entropy-based model that can be leveraged to construct resilient QNN architectures to bit-flip attacks.

Existing works indicate that Spiking Neural Networks (SNNs) are resilient to adversarial attacks by testing against few attack models. This paper studies adversarial attacks on SNNs using additional attack models and shows that SNNs are not inherently robust against many few-pixel L0 black-box attacks. Additionally, a method to defend against such attacks in SNNs is presented. The SNNs and the effects of adversarial attacks are tested on both software simulators as well as on SpiNNaker neuromorphic hardware.