Biblio

In this decade, digital transactions have risen exponentially demanding more reliable and secure authentication systems. CAPTCHA (Completely Automated Public Turing Test to tell Computers and Humans Apart) system plays a major role in these systems. These CAPTCHAs are available in character sequence, picture-based, and audio-based formats. It is very essential that these CAPTCHAs should be able to differentiate a computer program from a human precisely. This work tests the strength of text-based CAPTCHAs by breaking them using an algorithm built on CNN (Convolution Neural Network) and RNN (Recurrent Neural Network). The algorithm is designed in such a way as an attempt to break the security features designers have included in the CAPTCHAs to make them hard to be cracked by machines. This algorithm is tested against the synthetic dataset generated in accordance with the schemes used in popular websites. The experiment results exhibit that the model has shown a considerable performance against both the synthetic and real-world CAPTCHAs.

Visual Question Answering or VQA is a technique used in diverse domains ranging from simple visual questions and answers on short videos to security. Here in this paper, we talk about the video captcha that will be deployed for user authentication. Randomly any short video of length 10 to 20 seconds will be displayed and automated questions and answers will be generated by the system using AI and ML. Automated Programs have maliciously affected gateways such as login, registering etc. Therefore, in today's environment it is necessary to deploy such security programs that can recognize the objects in a video and generate automated MCQs real time that can be of context like the object movements, color, background etc. The features in the video highlighted will be recorded for generating MCQs based on the short videos. These videos can be random in nature. They can be taken from any official websites or even from your own local computer with prior permission from the user. The format of the video must be kept as constant every time and must be cross checked before flashing it to the user. Once our system identifies the captcha and determines the authenticity of a user, the other website in which the user wants to login, can skip the step of captcha verification as it will be done by our system. A session will be maintained for the user, eliminating the hassle of authenticating themselves again and again for no reason. Once the video will be flashed for an IP address and if the answers marked by the user for the current video captcha are correct, we will add the information like the IP address, the video and the questions in our database to avoid repeating the same captcha for the same IP address. In this paper, we proposed the methodology of execution of the aforementioned and will discuss the benefits and limitations of video captcha along with the visual questions and answering.

CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) is an important security technique designed to deter bots from abusing software systems, which has broader applications in cyberspace. CAPTCHAs come in a variety of forms, including the deciphering of obfuscated text, transcribing of audio messages, and tracking mouse movement, among others. This paper focuses on using deep learning techniques to recognize text-based CAPTCHAs. In particular, our work focuses on generating training datasets using different CAPTCHA schemes, along with a pre-processing technique allowing for character-based recognition. We have encapsulated the CRABI (CAPTCHA Recognition with Attached Binary Images) framework to give an image multiple labels for improvement in feature extraction. Using real-world datasets, performance evaluations are conducted to validate the efficacy of our proposed approach on several neural network architectures (e.g., custom CNN architecture, VGG16, ResNet50, and MobileNet). The experimental results confirm that over 90% accuracy can be achieved on most models.

Blind identification of channel codes is crucial in intelligent communication and non-cooperative signal processing, and it plays a significant role in wireless physical layer security, information interception, and information confrontation. Previous researches show a high computation complexity by manual feature extractions, in addition, problems of indisposed accuracy and poor robustness are to be resolved in a low signal-to-noise ratio (SNR). For solving these difficulties, based on deep residual shrinkage network (DRSN), this paper proposes a novel recognizer by deep learning technologies to blindly distinguish the type and the parameter of channel codes without any prior knowledge or channel state, furthermore, feature extractions by the neural network from codewords can avoid intricate calculations. We evaluated the performance of this recognizer in AWGN, single-path fading, and multi-path fading channels, the results of the experiments showed that the method we proposed worked well. It could achieve over 85 % of recognition accuracy for channel codes in AWGN channels when SNR is not lower than 4dB, and provide an improvement of more than 5% over the previous research in recognition accuracy, which proves the validation of the proposed method.

Explainable Artificial Intelligence (XAI) research focuses on effective explanation techniques to understand and build AI models with trust, reliability, safety, and fairness. Feature importance explanation summarizes feature contributions for end-users to make model decisions. However, XAI methods may produce varied summaries that lead to further analysis to evaluate the consistency across multiple XAI methods on the same model and data set. This paper defines metrics to measure the consistency of feature contribution explanation summaries under feature importance order and saliency map. Driven by these consistency metrics, we develop an XAI process oriented on the XAI criterion of feature importance, which performs a systematical selection of XAI techniques and evaluation of explanation consistency. We demonstrate the process development involving twelve XAI methods on three topics, including a search ranking system, code vulnerability detection and image classification. Our contribution is a practical and systematic process with defined consistency metrics to produce rigorous feature contribution explanations.

The Internet of Vehicles (IoVs) performs the rapid expansion of connected devices. This massive number of devices is constantly generating a massive and near-real-time data stream for numerous applications, which is known as big data. Analyzing such big data to find, predict, and control decisions is a critical solution for IoVs to enhance service quality and experience. Thus, the main goal of this paper is to study the impact of big data analytics on traffic prediction in IoVs. In which we have used big data analytics steps to predict the traffic flow, and based on different deep neural models such as LSTM, CNN-LSTM, and GRU. The models are validated using evaluation metrics, MAE, MSE, RMSE, and R2. Hence, a case study based on a real-world road is used to implement and test the efficiency of the traffic prediction models.

In order to gain more benefits from big data, they must be shared, published, analyzed and processed without having any harm or facing any violation and finally get better values from these analytics. The literature reports that this analytics brings an issue of privacy violations. This issue is also protected by law and bring fines to the companies, institutions or individuals. As a result, data collectors avoid to publish or share their big data due to these concerns. In order to obtain plausible solutions, there are a number of techniques to reduce privacy risks and to enable publishing big data while preserving privacy at the same time. These are known as privacy-preserving big data publishing (PPBDP) models. This study presents the privacy problem in big data, evaluates big data components from privacy perspective, privacy risks and protection methods in big data publishing, and reviews existing privacy-preserving big data publishing approaches and anonymization methods in literature. The results were finally evaluated and discussed, and new suggestions were presented.

Smart phones have become the preferred way for Chinese Internet users currently. The mobile phone traffic is large from the operating system. These traffic is mainly generated by the services. In the context of the universal encryption of the traffic, classification identification of mobile encryption services can effectively reduce the difficulty of analytical difficulty due to mobile terminals and operating system diversity, and can more accurately identify user access targets, and then enhance service quality and network security management. The existing mobile encryption service classification methods have two shortcomings in feature selection: First, the DL model is used as a black box, and the features of large dimensions are not distinguished as input of classification model, which resulting in sharp increase in calculation complexity, and the actual application is limited. Second, the existing feature selection method is insufficient to use the time and space associated information of traffic, resulting in less robustness and low accuracy of the classification. In this paper, we propose a feature enhancement method based on adjacent flow contextual features and evaluate the Apple encryption service traffic collected from the real world. Based on 5 DL classification models, the refined classification accuracy of Apple services is significantly improved. Our work can provide an effective solution for the fine management of mobile encryption services.

Most existing deep neural networks (DNNs) are inexplicable and fragile, which can be easily deceived by carefully designed adversarial example with tiny undetectable noise. This allows attackers to cause serious consequences in many DNN-assisted scenarios without human perception. In the field of speaker recognition, the attack for speaker recognition system has been relatively mature. Most works focus on white-box attacks that assume the information of the DNN is obtainable, and only a few works study gray-box attacks. In this paper, we study blackbox attacks on the speaker recognition system, which can be applied in the real world since we do not need to know the system information. By combining the idea of transferable attack and query attack, our proposed method NMI-FGSM-Tri can achieve the targeted goal by misleading the system to recognize any audio as a registered person. Specifically, our method combines the Nesterov accelerated gradient (NAG), the ensemble attack and the restart trigger to design an attack method that generates the adversarial audios with good performance to attack blackbox DNNs. The experimental results show that the effect of the proposed method is superior to the extant methods, and the attack success rate can reach as high as 94.8% even if only one query is allowed.

Adversarial attacks have recently been proposed to scrutinize the security of deep neural networks. Most blackbox adversarial attacks, which have partial access to the target through queries, are target-specific; e.g., they require a well-trained surrogate that accurately mimics a given target. In contrast, target-agnostic black-box attacks are developed to attack any target; e.g., they learn a generalized surrogate that can adapt to any target via fine-tuning on samples queried from the target. Despite their success, current state-of-the-art target-agnostic attacks require tremendous fine-tuning steps and consequently an immense number of queries to the target to generate successful attacks. The high query complexity of these attacks makes them easily detectable and thus defendable. We propose a novel query-efficient target-agnostic attack that trains a generalized surrogate network to output the adversarial directions iv.r.t. the inputs and equip it with an effective fine-tuning strategy that only fine-tunes the surrogate when it fails to provide useful directions to generate the attacks. Particularly, we show that to effectively adapt to any target and generate successful attacks, it is sufficient to fine-tune the surrogate with informative samples that help the surrogate get out of the failure mode with additional information on the target’s local behavior. Extensive experiments on CIFAR10 and CIFAR-100 datasets demonstrate that the proposed target-agnostic approach can generate highly successful attacks for any target network with very few fine-tuning steps and thus significantly smaller number of queries (reduced by several order of magnitudes) compared to the state-of-the-art baselines.

Black-box adversarial attack has aroused much research attention for its difficulty on nearly no available information of the attacked model and the additional constraint on the query budget. A common way to improve attack efficiency is to transfer the gradient information of a white-box substitute model trained on an extra dataset. In this paper, we deal with a more practical setting where a pre-trained white-box model with network parameters is provided without extra training data. To solve the model mismatch problem between the white-box and black-box models, we propose a novel algorithm EigenBA by systematically integrating gradient-based white-box method and zeroth-order optimization in black-box methods. We theoretically show the optimal directions of perturbations for each step are closely related to the right singular vectors of the Jacobian matrix of the pretrained white-box model. Extensive experiments on ImageNet, CIFAR-10 and WebVision show that EigenBA can consistently and significantly outperform state-of-the-art baselines in terms of success rate and attack efficiency.

In recent years, radar automatic target recognition (RATR) technology based on high-resolution range profile (HRRP) has received extensive attention in various fields. However, insufficient data on non-cooperative targets seriously affects recognition performance of this technique. For HRRP target recognition under few-shot condition, we proposed a novel gaussian deep belief network based on model-agnostic meta-learning (GDBN-MAML). In the proposed method, GDBN allowed real-value data to be transmitted over the entire network, which effectively avoided feature loss due to binarization requirements of conventional deep belief network (DBN) for data. In addition, we optimized the initial parameters of GDBN by multi-task learning based on MAML. In this way, the number of training samples required by the model for new recognition tasks could be reduced. We applied the proposed method to the HRRP recognition experiments of 3 types of 3D simulated aircraft models. The experimental results showed that the proposed method had higher recognition accuracy and generalization performance under few-shot condition compared with conventional deep learning methods.

In view of the characteristics that rolling bearing is prone to failure under actual working conditions, and it is difficult to classify the fault category and fault degree, the deep belief network is introduced to diagnose the rolling bearing fault. Firstly, principal component analysis is used to reduce the dimension of original input data and delete redundant input information. Then, the dimension reduced data are input into the deep belief network to extract the low dimensional fault feature representation, and the extracted features are input into the classifier for rolling bearing fault pattern recognition. Finally, the diagnosis effect of the proposed network is compared with the existing common shallow neural network. The simulation experiment is carried out through the bearing data in the United States.

Terrorism, and radicalization are major economic, political, and social issues faced by the world in today's era. The challenges that governments and citizens face in combating terrorism are growing by the day. Artificial intelligence, including machine learning and deep learning, has shown promising results in predicting terrorist attacks. In this paper, we attempted to build a machine learning model to predict terror activities using a global terrorism database in both relational and graphical forms. Using the Neo4j Sandbox, you can create a graph database from a relational database. We used the node2vec algorithm from Neo4j Sandbox's graph data science library to convert the high-dimensional graph to a low-dimensional vector form. In order to predict terror activities, seven machine learning models were used, and the performance parameters that were calculated were accuracy, precision, recall, and F1 score. According to our findings, the Logistic Regression model was the best performing model which was able to classify the dataset with an accuracy of 0.90, recall of 0.94 precision of 0.93, and an F1 score of 0.93.

A recommender system is a filtering application based on personalized information from acquired big data to predict a user's preference. Traditional recommender systems primarily rely on keywords or scene patterns. Users' subjective emotion data are rarely utilized for preference prediction. Novel Brain Computer Interfaces hold incredible promise and potential for intelligent applications that rely on collected user data like a recommender system. This paper describes a deep learning method that uses Brain Computer Interfaces (BCI) based neural measures to predict a user's preference on short music videos. Our models are employed on both population-wide and individualized preference predictions. The recognition method is based on dynamic histogram measurement and deep neural network for distinctive feature extraction and improved classification. Our models achieve 97.21%, 94.72%, 94.86%, and 96.34% classification accuracy on two-class, three-class, four-class, and nine-class individualized predictions. The findings provide evidence that a personalized recommender system on an implicit BCI has the potential to succeed.

Ubiquitous environment embedded with artificial intelligent consist of heterogenous smart devices communicating each other in several context for the computation of requirements. In such environment the trust among the smart users have taken as the challenge to provide the secure environment during the communication in the ubiquitous region. To provide the secure trusted environment for the users of ubiquitous system proposed approach aims to extract behavior of smart invisible entities by retrieving their behavior of communication in the network and applying the recommendation-based filters using Deep learning (RBF-DL). The proposed model adopts deep learning-based classifier to classify the unfair recommendation with fair ones to have a trustworthy ubiquitous system. The capability of proposed model is analyzed and validated by considering different attacks and additional feature of instances in comparison with generic recommendation systems.

Trip planning, which targets at planning a trip consisting of several ordered Points of Interest (POIs) under user-provided constraints, has long been treated as an important application for location-based services. The goal of trip planning is to maximize the chance that the users will follow the planned trip while it is difficult to directly quantify and optimize the chance. Conventional methods either leverage statistical analysis to rank POIs to form a trip or generate trips following pre-defined objectives based on constraint programming to bypass such a problem. However, these methods may fail to reflect the complex latent patterns hidden in the human mobility data. On the other hand, though there are a few deep learning-based trip recommendation methods, these methods still cannot handle the time budget constraint so far. To this end, we propose a TIme-aware Neural Trip Planning (TINT) framework to tackle the above challenges. First of all, we devise a novel attention-based encoder-decoder trip generator that can learn the correlations among POIs and generate trips under given constraints. Then, we propose a specially-designed reinforcement learning (RL) paradigm to directly optimize the objective to obtain an optimal trip generator. For this purpose, we introduce a discriminator, which distinguishes the generated trips from real-life trips taken by users, to provide reward signals to optimize the generator. Subsequently, to ensure the feedback from the discriminator is always instructive, we integrate an adversarial learning strategy into the RL paradigm to update the trip generator and the discriminator alternately. Moreover, we devise a novel pre-training schema to speed up the convergence for an efficient training process. Extensive experiments on four real-world datasets validate the effectiveness and efficiency of our framework, which shows that TINT could remarkably outperform the state-of-the-art baselines within short response time.

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.

IoBTs must feature collaborative, context-aware, multi-modal fusion for real-time, robust decision-making in adversarial environments. The integration of machine learning (ML) models into IoBTs has been successful at solving these problems at a small scale (e.g., AiTR), but state-of-the-art ML models grow exponentially with increasing temporal and spatial scale of modeled phenomena, and can thus become brittle, untrustworthy, and vulnerable when interpreting large-scale tactical edge data. To address this challenge, we need to develop principles and methodologies for uncertainty-quantified neuro-symbolic ML, where learning and inference exploit symbolic knowledge and reasoning, in addition to, multi-modal and multi-vantage sensor data. The approach features integrated neuro-symbolic inference, where symbolic context is used by deep learning, and deep learning models provide atomic concepts for symbolic reasoning. The incorporation of high-level symbolic reasoning improves data efficiency during training and makes inference more robust, interpretable, and resource-efficient. In this paper, we identify the key challenges in developing context-aware collaborative neuro-symbolic inference in IoBTs and review some recent progress in addressing these gaps.

State of the art Artificial Intelligence Assurance (AIA) methods validate AI systems based on predefined goals and standards, are applied within a given domain, and are designed for a specific AI algorithm. Existing works do not provide information on assuring subjective AI goals such as fairness and trustworthiness. Other assurance goals are frequently required in an intelligent deployment, including explainability, safety, and security. Accordingly, issues such as value loading, generalization, context, and scalability arise; however, achieving multiple assurance goals without major trade-offs is generally deemed an unattainable task. In this manuscript, we present two AIA pipelines that are model-agnostic, independent of the domain (such as: healthcare, energy, banking), and provide scores for AIA goals including explainability, safety, and security. The two pipelines: Adversarial Logging Scoring Pipeline (ALSP) and Requirements Feedback Scoring Pipeline (RFSP) are scalable and tested with multiple use cases, such as a water distribution network and a telecommunications network, to illustrate their benefits. ALSP optimizes models using a game theory approach and it also logs and scores the actions of an AI model to detect adversarial inputs, and assures the datasets used for training. RFSP identifies the best hyper-parameters using a Bayesian approach and provides assurance scores for subjective goals such as ethical AI using user inputs and statistical assurance measures. Each pipeline has three algorithms that enforce the final assurance scores and other outcomes. Unlike ALSP (which is a parallel process), RFSP is user-driven and its actions are sequential. Data are collected for experimentation; the results of both pipelines are presented and contrasted.

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 ongoing COVID-19 virus pandemic has resulted in a global tragedy due to its lethal spread. The population's vulnerability grows as a result of a lack of effective helping agents and vaccines against the virus. The spread of viruses can be mitigated by minimizing close connections between people. Social distancing is a critical containment tool for COVID-19 prevention. In this paper, the social distancing violations that are being made by the people when they are in public places are detected. As per CDC (Centers for Disease Control and Prevention) minimum distance that should be maintained by people is 2-3 meters to prevent the spread of COVID- 19, the proposed tool will be used to detect the people who are maintaining less than 2-3 meters of distance between themselves and record them as a violation. As a result, the goal of this work is to develop a deep learning-based system for object detection and tracking models in social distancing detection. For object detection models, You Only Look Once, Version 3 (YOLO v3) is used in conjunction with deep sort algorithms to balance speed and accuracy. To recognize persons in video segments, the approach applies the YOLOv3 object recognition paradigm. An efficient computer vision-based approach centered on legitimate continuous tracking of individuals is presented to determine supportive social distancing in public locations by creating a model to generate a supportive climate that contributes to public safety and detect violations through camera.

The dynamic state of networks presents a challenge for the deployment of distributed applications and protocols. Ad-hoc schedules in the updating phase might lead to a lot of ambiguity and issues. By separating the control and data planes and centralizing control, Software Defined Networking (SDN) offers novel opportunities and remedies for these issues. However, software-based centralized architecture for distributed environments introduces significant challenges. Security is a main and crucial issue in SDN. This paper presents a deep study of the state-of-the-art of security challenges and solutions for the SDN paradigm. The conducted study helped us to propose a dynamic approach to efficiently detect different security violations and incidents caused by network updates including forwarding loop, forwarding black hole, link congestion, network policy violation, etc. Our solution relies on an intelligent approach based on the use of Machine Learning and Artificial Intelligence Algorithms.

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.

In this paper, the malicious code is run in the sandbox in a safe and controllable environment, the API sequence is deduplicated by the idea of the longest common subsequence, and the CNN and Bi-LSTM are integrated to process and analyze the API sequence. Compared with the method, the method using deep learning can have higher accuracy and work efficiency.