Biblio

"Deepfake" it is an incipiently emerging face video forgery technique predicated on AI technology which is used for creating the fake video. It takes images and video as source and it coalesces these to make a new video using the generative adversarial network and the output is very convincing. This technique is utilized for generating the unauthentic spurious video and it is capable of making it possible to generate an unauthentic spurious video of authentic people verbally expressing and doing things that they never did by swapping the face of the person in the video. Deepfake can create disputes in countries by influencing their election process by defaming the character of the politician. This technique is now being used for character defamation of celebrities and high-profile politician just by swapping the face with someone else. If it is utilized in unethical ways, this could lead to a serious problem. Someone can use this technique for taking revenge from the person by swapping face in video and then posting it to a social media platform. In this paper, working of Deepfake technique along with how it can swap faces with maximum precision in the video has been presented. Further explained are the different ways through which we can identify if the video is generated by Deepfake and its advantages and drawback have been listed.

This work uses adversarial perturbations to enhance deepfake images and fool common deepfake detectors. We created adversarial perturbations using the Fast Gradient Sign Method and the Carlini and Wagner L2 norm attack in both blackbox and whitebox settings. Detectors achieved over 95% accuracy on unperturbed deepfakes, but less than 27% accuracy on perturbed deepfakes. We also explore two improvements to deep-fake detectors: (i) Lipschitz regularization, and (ii) Deep Image Prior (DIP). Lipschitz regularization constrains the gradient of the detector with respect to the input in order to increase robustness to input perturbations. The DIP defense removes perturbations using generative convolutional neural networks in an unsupervised manner. Regularization improved the detection of perturbed deepfakes on average, including a 10% accuracy boost in the blackbox case. The DIP defense achieved 95% accuracy on perturbed deepfakes that fooled the original detector while retaining 98% accuracy in other cases on a 100 image subsample.

Nowadays, people faced an emerging problem of AI-synthesized face swapping videos, widely known as the DeepFakes. This kind of videos can be created to cause threats to privacy, fraudulence and so on. Sometimes good quality DeepFake videos recognition could be hard to distinguish with people eyes. That's why researchers need to develop algorithms to detect them. In this work, we present overview of indicators that can tell us about the fact that face swapping algorithms were used on photos. Main purpose of this paper is to find algorithm or technology that can decide whether photo was changed with DeepFake technology or not with good accuracy.

Video streams acquired from thermal cameras are proven to be beneficial in diverse number of fields including military, healthcare, law enforcement, and security. Despite the hype, thermal imaging is increasingly affected by poor resolution, where it has expensive optical sensors and inability to attain optical precision. In recent years, deep learning based super-resolution algorithms are developed to enhance the video frame resolution at high accuracy. This paper presents a comparative analysis of super resolution (SR) techniques based on deep neural networks (DNN) that are applied on thermal video dataset. SRCNN, EDSR, Auto-encoder, and SRGAN are also discussed and investigated. Further the results on benchmark thermal datasets including FLIR, OSU thermal pedestrian database and OSU color thermal database are evaluated and analyzed. Based on the experimental results, it is concluded that, SRGAN has delivered a superior performance on thermal frames when compared to other techniques and improvements, which has the ability to provide state-of-the art performance in real time operations.

The Automation industries that uses Supervisory Control and Data Acquisition (SCADA) systems are highly vulnerable for Network threats. Systems that are air-gapped and isolated from the internet are highly affected due to insider attacks like Spoofing, DOS and Malware threats that affects confidentiality, integrity and availability of Operational Technology (OT) system elements and degrade its performance even though security measures are taken. In this paper, a behavior-based intrusion prevention system (IPS) is designed for OT networks. The proposed system is implemented on SCADA test bed with two systems replicates automation scenarios in industry. This paper describes 4 main classes of cyber-attacks with their subclasses against SCADA systems and methodology with design of components of IPS system, database creation, Baselines and deployment of system in environment. IPS system identifies not only IT protocols but also Industry Control System (ICS) protocols Modbus and DNP3 with their inside communication fields using deep packet inspection (DPI). The analytical results show 99.89% accuracy on binary classification and 97.95% accuracy on multiclass classification of different attack vectors performed on network with low false positive rate. These results are also validated by actual deployment of IPS in SCADA systems with the prevention of DOS attack.

Recently, the field of adversarial machine learning has been garnering attention by showing that state-of-the-art deep neural networks are vulnerable to adversarial examples, stemming from small perturbations being added to the input image. Adversarial examples are generated by a malicious adversary by obtaining access to the model parameters, such as gradient information, to alter the input or by attacking a substitute model and transferring those malicious examples over to attack the victim model. Specifically, one of these attack algorithms, Robust Physical Perturbations (RP2), generates adversarial images of stop signs with black and white stickers to achieve high targeted misclassification rates against standard-architecture traffic sign classifiers. In this paper, we propose BlurNet, a defense against the RP2 attack. First, we motivate the defense with a frequency analysis of the first layer feature maps of the network on the LISA dataset, which shows that high frequency noise is introduced into the input image by the RP2 algorithm. To remove the high frequency noise, we introduce a depthwise convolution layer of standard blur kernels after the first layer. We perform a blackbox transfer attack to show that low-pass filtering the feature maps is more beneficial than filtering the input. We then present various regularization schemes to incorporate this lowpass filtering behavior into the training regime of the network and perform white-box attacks. We conclude with an adaptive attack evaluation to show that the success rate of the attack drops from 90% to 20% with total variation regularization, one of the proposed defenses.

By analogy to nature, sight is the main integral component of robotic complexes, including unmanned vehicles. In this connection, one of the urgent tasks in the modern development of unmanned vehicles is the solution to the problem of providing security for new advanced systems, algorithms, methods, and principles of space navigation of robots. In the paper, we present an approach to the protection of machine vision systems based on technologies of deep learning. At the heart of the approach lies the “Feature Squeezing” method that works on the phase of model operation. It allows us to detect “adversarial” examples. Considering the urgency and importance of the target process, the features of unmanned vehicle hardware platforms and also the necessity of execution of tasks on detecting of the objects in real-time mode, it was offered to carry out an additional simple computational procedure of localization and classification of required objects in case of crossing a defined in advance threshold of “adversarial” object testing.

Robots are becoming more and more prevalent in many real world scenarios. Housekeeping, medical aid, human assistance are a few common implementations of robots. Military and Security are also major areas where robotics is being researched and implemented. Robots with the purpose of surveillance in war zones and terrorist scenarios need specific functionalities to perform their tasks with precision and efficiency. In this paper, we present a model of Military Surveillance Robot developed using Robot Operating System. The map generation based on Kinect sensor is presented and some test case scenarios are discussed with results.

Intrusion detection system based on representation learning is the main research direction in the field of anomaly detection. Malicious traffic detection system can distinguish normal and malicious traffic by learning representations between normal and malicious traffic. However, under the context of big data, there are many types of malicious traffic, and the features are also changing constantly. It is still a urgent problem to design a detection model that can effectively learn and summarize the feature of normal traffic and accurately identify the features of new kinds of malicious traffic.in this paper, a malicious traffic detection method based on Deep Support Vector Data Description is proposed, which is called Deep - SVDD. We combine convolutional neural network (CNN) with support vector data description, and train the model with normal traffic. The normal traffic features are mapped to high-dimensional space through neural networks, and a compact hypersphere is trained by unsupervised learning, which includes the normal features of the highdimensional space. Malicious traffic fall outside the hypersphere, thus distinguishing between normal and malicious traffic. Experiments show that the model has a high detection rate and a low false alarm rate, and it can effectively identify new malicious traffic.

Since the neural networks are utilized to extract information from an image, Gatys et al. found that they could separate the content and style of images and reconstruct them to another image which called Style Transfer. Moreover, there are many feed-forward neural networks have been suggested to speeding up the original method to make Style Transfer become practical application. However, this takes a price: these feed-forward networks are unchangeable because of their fixed parameters which mean we cannot transfer arbitrary styles but only single one in real-time. Some coordinated approaches have been offered to relieve this dilemma. Such as a style-swap layer and an adaptive normalization layer (AdaIN) and soon. Its worth mentioning that we observed that the AdaIN layer only aligns the means and variance of the content feature maps with those of the style feature maps. Our method is aimed at presenting an operational approach that enables arbitrary style transfer in real-time, reserving more statistical information by histogram matching, providing more reliable texture clarity and more humane user control. We achieve performance more cheerful than existing approaches without adding calculation, complexity. And the speed comparable to the fastest Style Transfer method. Our method provides more flexible user control and trustworthy quality and stability.

These days deep learning is the fastest-growing area in the field of Machine Learning. Convolutional Neural Networks are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this paper, we have focused on the most frequently mentioned problem in the field of machine learning, that is relatively poor generalization abilities. Partial remedies for this are regularization techniques e.g. dropout, batch normalization, weight decay, transfer learning, early stopping and data augmentation. In this paper we have focused on data augmentation. We propose to use a method based on a neural style transfer, which allows to generate new unlabeled images of high perceptual quality that combine the content of a base image with the appearance of another one. In a proposed approach, the newly created images are described with pseudo-labels, and then used as a training dataset. Real, labeled images are divided into the validation and test set. We validated proposed method on a challenging skin lesion classification case study. Four representative neural architectures are examined. Obtained results show the strong potential of the proposed approach.

To preserve anonymity and obfuscate their identity on online platforms users may morph their text and portray themselves as a different gender or demographic. Similarly, a chatbot may need to customize its communication style to improve engagement with its audience. This manner of changing the style of written text has gained significant attention in recent years. Yet these past research works largely cater to the transfer of single style attributes. The disadvantage of focusing on a single style alone is that this often results in target text where other existing style attributes behave unpredictably or are unfairly dominated by the new style. To counteract this behavior, it would be nice to have a style transfer mechanism that can transfer or control multiple styles simultaneously and fairly. Through such an approach, one could obtain obfuscated or written text incorporated with a desired degree of multiple soft styles such as female-quality, politeness, or formalness. To the best of our knowledge this work is the first that shows and attempt to solve the issues related to multiple style transfer. We also demonstrate that the transfer of multiple styles cannot be achieved by sequentially performing multiple single-style transfers. This is because each single style-transfer step often reverses or dominates over the style incorporated by a previous transfer step. We then propose a neural network architecture for fairly transferring multiple style attributes in a given text. We test our architecture on the Yelp dataset to demonstrate our superior performance as compared to existing one-style transfer steps performed in a sequence.

Style transfer is a research hotspot in computer vision. Up to now, it is still a challenge although many researches have been conducted on it for high quality style transfer. In this work, we propose an algorithm named ASTCNN which is a real-time Arbitrary Style Transfer Convolution Neural Network. The ASTCNN consists of two independent encoders and a decoder. The encoders respectively extract style and content features from style and content and the decoder generates the style transferred image images. Experimental results show that ASTCNN achieves higher quality output image than the state-of-the-art style transfer algorithms and the floating point computation of ASTCNN is 23.3% less than theirs.

Re-drawing the image as a certain artistic style is considered to be a complicated task for computer machine. On the contrary, human can easily master the method to compose and describe the style between different images. In the past, many researchers studying on the deep neural networks had found an appropriate representation of the artistic style using perceptual loss and style reconstruction loss. In the previous works, Gatys et al. proposed an artificial system based on convolutional neural networks that creates artistic images of high perceptual quality. Whereas in terms of running speed, it was relatively time-consuming, thus it cannot apply to video style transfer. Recently, a feed-forward CNN approach has shown the potential of fast style transformation, which is an end-to-end system without hundreds of iteration while transferring. We combined the benefits of both approaches, optimized the feed-forward network and defined time loss function to make it possible to implement the style transfer on video in real time. In contrast to the past method, our method runs in real time with higher resolution while creating competitive visually pleasing and temporally consistent experimental results.

Over the years, technology has reformed the perception of the world related to security concerns. To tackle security problems, we proposed a system capable of detecting security alerts. System encompass audio events that occur as an outlier against background of unusual activity. This ambiguous behaviour can be handled by auditory classification. In this paper, we have discussed two techniques of extracting features from sound data including: time-based and signal based features. In first technique, we preserve time-series nature of sound, while in other signal characteristics are focused. Convolution neural network is applied for categorization of sound. Major aim of research is security challenges, so we have generated data related to surveillance in addition to available datasets such as UrbanSound 8k and ESC-50 datasets. We have achieved 94.6% accuracy for proposed methodology based on self-generated dataset. Improved accuracy on locally prepared dataset demonstrates novelty in research.

With the increasing performance of neural networks on many security-critical tasks, the security concerns of machine learning have become increasingly prominent. Recent studies have shown that neural networks are vulnerable to adversarial examples: carefully crafted inputs with negligible perturbations on legitimate samples could mislead a neural network to produce adversary-selected outputs while humans can still correctly classify them. Therefore, we need an additional measurement on the trustworthiness of the results of a machine learning model, especially in adversarial settings. In this paper, we analyse the root cause of adversarial examples, and propose a new property, namely fidelity, of machine learning models to describe the gap between what a model learns and the ground truth learned by humans. One of its benefits is detecting adversarial attacks. We formally define fidelity, and propose a novel approach to quantify it. We evaluate the quantification of fidelity in adversarial settings on two neural networks. The study shows that involving the fidelity enables a neural network system to detect adversarial examples with true positive rate 97.7%, and false positive rate 1.67% on a studied neural network.

Since Gatys et al. proved that the convolution neural network (CNN) can be used to generate new images with artistic styles by separating and recombining the styles and contents of images. Neural Style Transfer has attracted wide attention of computer vision researchers. This paper aims to provide an overview of the style transfer application deep learning network development process, and introduces the classical style migration model, on the basis of the research on the migration of style of the deep learning network for collecting and organizing, and put forward related to gathered during the investigation of the problem solution, finally some classical model in the image style to display and compare the results of migration.

Most of the notable artworks of all time are hand drawn by great artists. But, now with the advancement in image processing and huge computation power, very sophisticated synthesised artworks are being produced. Since mid-1990's, computer graphics engineers have come up with algorithms to produce digital paintings, but the results were not visually appealing. Recently, neural networks have been used to do this task and the results seen are like never before. One such algorithm for this purpose is the neural style transfer algorithm, which imparts the pattern from one image to another, producing marvellous pieces of art. This research paper focuses on the roles of various parameters involved in the neural style transfer algorithm. An extensive analysis of how these parameters influence the output, in terms of time, performance and quality of the style transferred image produced is also shown in the paper. A concrete comparison has been drawn on the basis of different time and performance metrics. Finally, optimal values for these discussed parameters have been suggested.

Mobile expressive rendering gained increasing popularity among users seeking casual creativity by image stylization and supports the development of mobile artists as a new user group. In particular, neural style transfer has advanced as a core technology to emulate characteristics of manifold artistic styles. However, when it comes to creative expression, the technology still faces inherent limitations in providing low-level controls for localized image stylization. This work enhances state-of-the-art neural style transfer techniques by a generalized user interface with interactive tools to facilitate a creative and localized editing process. Thereby, we first propose a problem characterization representing trade-offs between visual quality, run-time performance, and user control. We then present MaeSTrO, a mobile app for orchestration of neural style transfer techniques using iterative, multi-style generative and adaptive neural networks that can be locally controlled by on-screen painting metaphors. At this, first user tests indicate different levels of satisfaction for the implemented techniques and interaction design.

Humans have created many pioneers of art from the beginning of time. There are not many notable achievements by an artificial intelligence to create something visually captivating in the field of art. However, some breakthroughs were made in the past few years by learning the differences between the content and style of an image using convolution neural networks and texture synthesis. But most of the approaches have the limitations on either processing time, choosing a certain style image or altering the weight ratio of style image. Therefore, we are to address these restrictions and provide a system which allows any style image selection with a user defined style weight ratio in minimum time possible.

Malicious scripts are an important computer infection threat vector for computer users. For internet-scale processing, static analysis offers substantial computing efficiencies. We propose the ScriptNet system for neural malicious JavaScript detection which is based on static analysis. We also propose a novel deep learning model, Pre-Informant Learning (PIL), which processes Javascript files as byte sequences. Lower layers capture the sequential nature of these byte sequences while higher layers classify the resulting embedding as malicious or benign. Unlike previously proposed solutions, our model variants are trained in an end-to-end fashion allowing discriminative training even for the sequential processing layers. Evaluating this model on a large corpus of 212,408 JavaScript files indicates that the best performing PIL model offers a 98.10% true positive rate (TPR) for the first 60K byte subsequences and 81.66% for the full-length files, at a false positive rate (FPR) of 0.50%. Both models significantly outperform several baseline models. The best performing PIL model can successfully detect 92.02% of unknown malware samples in a hindsight experiment where the true labels of the malicious JavaScript files were not known when the model was trained.

In view of the problem that the health status and safety monitoring of the traditional intelligent home are mainly dependent on the manual inspection, this paper introduces the intelligent home-based remote monitoring system by introducing the Internet-based Internet of Things technology into the intelligent home condition monitoring and safety assessment. The system's Android remote operation based on the MVP model to develop applications, the use of neural networks to deal with users daily use of operational data to establish the network data model, combined with S3C2440A microcontrollers in the gateway to the embedded Linux to facilitate different intelligent home drivers development. Finally, the power line communication network is used to connect the intelligent electrical appliances to the gateway. By calculating the success rate of the routing nodes, the success rate of the network nodes of 15 intelligent devices is 98.33%. The system can intelligent home many electrical appliances at the same time monitoring, to solve the system data and network congestion caused by the problem can not he security monitoring.

Internet application providers now have more incentive than ever to collect user data, which greatly increases the risk of user privacy violations due to the emerging of deep neural networks. In this paper, we propose TensorClog-a poisoning attack technique that is designed for privacy protection against deep neural networks. TensorClog has three properties with each of them serving a privacy protection purpose: 1) training on TensorClog poisoned data results in lower inference accuracy, reducing the incentive of abusive data collection; 2) training on TensorClog poisoned data converges to a larger loss, which prevents the neural network from learning the privacy; and 3) TensorClog regularizes the perturbation to remain a high structure similarity, so that the poisoning does not affect the actual content in the data. Applying our TensorClog poisoning technique to CIFAR-10 dataset results in an increase in both converged training loss and test error by 300% and 272%, respectively. It manages to maintain data's human perception with a high SSIM index of 0.9905. More experiments including different limited information attack scenarios and a real-world application transferred from pre-trained ImageNet models are presented to further evaluate TensorClog's effectiveness in more complex situations.

With widely applied in various fields, deep learning (DL) is becoming the key driving force in industry. Although it has achieved great success in artificial intelligence tasks, similar to traditional software, it has defects that, once it failed, unpredictable accidents and losses would be caused. In this paper, we propose a test cases generation technique based on an adversarial samples generation algorithm for image classification deep neural networks (DNNs), which can generate a large number of good test cases for the testing of DNNs, especially in case that test cases are insufficient. We briefly introduce our method, and implement the framework. We conduct experiments on some classic DNN models and datasets. We further evaluate the test set by using a coverage metric based on states of the DNN.

In the context of the rapid technological progress, the cyber-threats become a serious challenge that requires immediate and continuous action. As cybercrime poses a permanent and increasing threat, governments, corporate and individual users of the cyber-space are constantly struggling to ensure an acceptable level of security over their assets. Maliciousness on the cyber-space spans identity theft, fraud, and system intrusions. This is due to the benefits of cyberspace-low entry barriers, user anonymity, and spatial and temporal separation between users, make it a fertile field for deception and fraud. Numerous, supervised and unsupervised, techniques have been proposed and used to identify fraudulent transactions and activities that deviate from regular patterns of behaviour. For instance, neural networks and genetic algorithms were used to detect credit card fraud in a dataset covering 13 months and 50 million credit card transactions. Unsupervised methods, such as clustering analysis, have been used to identify financial fraud or to filter fake online product reviews and ratings on e-commerce websites. Blockchain technology has demonstrated its feasibility and relevance in e-commerce. Its use is now being extended to new areas, related to electronic government. The technology appears to be the most appropriate in areas that require storage and processing of large amounts of protected data. The question is what can blockchain technology do and not do to fight malicious online activity?