الصفحة 26
الصفحة 26
Deepfake detection = اكتشاف التزييف العميق
In the rapidly evolving era of artificial intelligence, addressing the escalating threats of deepfake technology becomes a necessity because of the increasing sophistication of AI algorithms in generating deceptive content, and since it threatens the integrity of information across diverse data. The main objective is to build a sophisticated AI-driven system to detect different types of deepfake in text, audio, and images. In English text deepfake detection, multiple pre-trained tokenizers have been used, but XLNET and BERT stand out with identifying objects outside the dataset with an accuracy of 0.9809 and both have been generalized & trained using LSTM. In Arabic text deepfake detection, Arabert has been trained using LSTM which led with an accuracy of 99.53% by generalizing the model. Both English and Arabic datasets have been generated to enhance the accuracy and effectiveness of the models. Audio deepfake detection has been generalized too, using Random Forest with an accuracy of 98.259%.
Deepfake detection
Recently, various techniques of manipulating the video content have become available to everyone – online, one can find free applications e.g., for face swapping in videos. Such universal accessibility carries a notable risk of flooding online content with false information, affecting not only the greats of this world, but also the whole societies, also the rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. It is therefore necessary to develop a verification tool that will help assess the authenticity of the videos posted on the internet. This project describes the approach of using artificial intelligence solutions to detect doctored videos.
Deepfake detection
The rise of large language models (LLMs) and the increasing sophistication of deepfake images have made detecting synthetic content a pressing challenge. Several approaches have been proposed to tackle this problem, including statistical analysis, and machine learning algorithms. In this project, A novel zero-shot approach is proposed that utilizes the power of LLMs to detect fake text. The pre-trained LLM is fine-tuned to enhance its ability to differentiate real and fake text. The approach uses the LLM to detect text by analyzing the log probabilities of the text. For detecting fake images, computer vision algorithms and neural networks are used to analyze facial features. The facial region is cropped and preprocessed and the neural network identifies patterns indicative of synthetic content.
Deepfake
The technology used to create such digital content has quickly become accessible to the masses, such as “DEEPFAKE.” Deep fakes refer to manipulated videos, or other digital representations produced by sophisticated artificial intelligence, that yields to synthesize a sequence of face images and voices of characters corresponding to their identities, such as voice tone, facial expression, with a good lip synchronization. Therefore, this study is about developing real-time video generation software, which generates a target video from a single input image. Several methods and algorithms have been applied to detect, analyze personalize facial expression, voice and natural head poses to present a life-like image instead of a low quality one.
Deep Statistical Comparison for Meta-heuristic Stochastic Optimization Algorithms
Presents a comprehensive comparison of the performance of stochastic optimization algorithms / Includes an introduction to benchmarking and statistical analysis / Provides a web-based tool for making statistical comparisons of optimization algorithms / Overviews of the current approaches used to analyze algorithm performance in a range of common scenarios, while also addressing issues that are often overlooked. In turn, it shows how these issues can be easily avoided by applying the principles that have produced Deep Statistical Comparison and its variants. The focus is on statistical analyses performed using single-objective and multi-objective optimization data. At the end of the book, examples from a recently developed web-service-based e-learning tool (DSCTool) are presented. The tool provides users with all the functionalities needed to make robust statistical comparison analyses in various statistical scenarios. The book is intended for newcomers to the field and experienced researchers alike. For newcomers, it covers the basics of optimization and statistical analysis, familiarizing them with the subject matter before introducing the Deep Statistical Comparison approach. Experienced researchers can quickly move on to the content on new statistical approaches.
Deep Learning, Machine Learning and IoT in Biomedical and Health Informatics : Techniques and Applications
Examines and demonstrates state-of-the-art approaches for IoT and Machine Learning based biomedical and health related applications. This book aims to provide computational methods for accumulating, updating and changing knowledge in intelligent systems and particularly learning mechanisms that help us to induce knowledge from the data. It is helpful in cases where direct algorithmic solutions are unavailable, there is lack of formal models, or the knowledge about the application domain is inadequately defined. In the future IoT has the impending capability to change the way we work and live. These computing methods also play a significant role in design and optimization in diverse engineering disciplines. With the influence and the development of the IoT concept, the need for AI (artificial intelligence) techniques has become more significant than ever.
Deep learning for computational problems in hardware security : Modeling attacks on strong physically unclonable function circuits
Discusses a broad overview of traditional machine learning methods and state-of-the-art deep learning practices for hardware security applications, in particular the techniques of launching potent "modeling attacks" on Physically Unclonable Function (PUF) circuits, which are promising hardware security primitives. The volume is self-contained and includes a comprehensive background on PUF circuits, and the necessary mathematical foundation of traditional and advanced machine learning techniques such as support vector machines, logistic regression, neural networks, and deep learning. This book can be used as a self-learning resource for researchers and practitioners of hardware security, and will also be suitable for graduate-level courses on hardware security and application of machine learning in hardware security.
Deep learning architecture and application
As one of the fastest-growing topics in machine learning, deep learning algorithms have achieved unprecedented success in recent years. Novel paradigms (such as contrastive learning and few-shot learning) in deep learning and rising neural network architectures (e.g., transformer and masked autoencoder) are dramatically changing the field of data-driven algorithms. More importantly, deep learning models are redefining the next generation of industrial applications spanning image recognition, speech processing, language translation, healthcare, and other sciences. For example, recent advances in deep representation learning are allowing us to learn about protein 3D structures, which sheds new light on fundamental medicine and biology along with potentially bringing in billions of dollars (e.g., in the pharmaceutical market).
Deep learning and computer vision in remote sensing-II
Computer vision (CV) have seen a massive rise in popularity in the remote sensing field over the last few years. This success is mostly due to the effectiveness of deep learning (DL) algorithms. However, remote sensing data acquisition and annotation, as well as information extraction from massive remote sensing data, are still challenging. This reprint collected novel developments in the field of deep learning and computer vision methods for remote sensing. Papers dealing with fundamental theoretical analyses, as well as those demonstrating their application to real-world problems, have been published. With practical examples and real-world case studies, this reprint provides a valuable resource for researchers, professionals, and students seeking to harness the power of deep learning in the field of remote sensing.
Deep learning and computer vision in remote sensing-I
In the last few years, huge amounts of progress have been made regarding remote sensing in the field of computer vision. This success and progress is mostly due to the effectiveness of deep learning (DL) algorithms. In addition, the remote sensing community has shifted its attention to DL, and DL algorithms have been used to achieve significant success in many image analysis tasks. However, with regard to remote sensing, a number of challenges caused by difficulties in data acquisition and annotation have not been fully solved yet. This reprint is a collection of novel developments in the field of remote sensing using computer vision, deep learning, and artificial intelligence. The articles published involve fundamental theoretical analyses as well as those demonstrating their application to real-world problems.
Deep fake detection
Deep learning has been successfully applied to solve various complex problems ranging from big data analytics to computer vision and human-level control. Deep learning advances however have also been employed to create software that can cause threats to privacy, democracy and national security. One of those deep learning-powered applications recently emerged is “deepfake”. Deepfake algorithms can create fake images and videos that humans cannot distinguish them from authentic ones. The proposal of technologies that can automatically detect and assess the integrity of digital visual media is therefore indispensable.
Decision Procedures : An Algorithmic Point of View
Concentrates on decision procedures for first-order theories that are commonly used in automated verification and reasoning, theorem-proving, compiler optimization and operations research.
Datatype-Generic Programming ; International Spring School, SSDGP 2006, Nottingham, UK, April 24-27, 2006, Revised Lectures
A leitmotif in the evolution of programming paradigms has been the level and extent of parametrisation that is facilitated — the so-called genericity of the paradigm. The sorts of parameters that can be envisaged in a programming language range from simple values, like integers and fioating-point numbers, through structured values, types and classes, to kinds (the type of types and/or classes).Datatype-generic programming is about parametrising programsby the structure of the data that they manipulate. To appreciate the importance of data type genericity,one need look no further than the internet. The internet is a massive repository of structured data, but the structure is rarely exploited. For example, compression of data can be much more efiective if its structure is known, but most compression algorithms regard the input data as simply a string of bits, and take no account of its internal organisation. Datatype-generic programming is about exploiting the structure of data when it is relevant and ignoring it when it is not. Programming languages most c- monly used at the present time do not provide efiective mechanisms for do- menting and implementing datatype genericity.
Data-Driven Fault Detection and Reasoning for Industrial Monitoring
Assesses the potential of data-driven methods in industrial process monitoring engineering. The process modeling, fault detection, classification, isolation, and reasoning are studied in detail. These methods can be used to improve the safety and reliability of industrial processes. Fault diagnosis, including fault detection and reasoning, has attracted engineers and scientists from various fields such as control, machinery, mathematics, and automation engineering. Combining the diagnosis algorithms and application cases, this book establishes a basic framework for this topic and implements various statistical analysis methods for process monitoring.
Databases in networked information systems; 4th international workshop, DNIS 2005, Aizu-Wakamatsu, Japan, March 28-30, 2005, Proceedings
This book constitutes the refereed proceedings of the 4th International Workshop on Databases in Networked Information Systems, DNIS 2005, held in Aizu-Wakamatsu, Japan in March 2005. The 17 revised full papers presented together with 8 invited papers were carefully reviewed and selected for inclusion in the book. The papers are organized in topical sections on information interchange and management systems, Web data management systems, networked information systems applications, and networked information systems implementations.
Database Theory – ICDT 2007 ; 11th International Conference, Barcelona, Spain, January 10-12, 2007, Proceedings
The papers are organized in topical sections on information integration and peer to peer, axiomatizations for XML, expressive power of query languages, incompleteness, inconsistency, and uncertainty, XML schemas and typechecking, stream processing and sequential query processing, ranking, XML update and query, as well as query containment.
Database theory - ICDT 2005 ; 10th international conference, Edinburgh, UK, January 5-7, 2005, Proceedings
This volume collects the papers presented at the 10th International Conference on Database Theory, ICDT 2005, held during January 5–7, 2005, in Edinburgh, UK. ICDT (http://alpha.luc.ac.be/~lucp1080/icdt/) has now a long tra- tion of international conferences, providing a biennial scienti?c forum for the communication of high-quality and innovative research results on theoretical - pects of all forms of database systems and database technology. The conference usually takes place in Europe, and has been held in Rome (1986), Bruges (1988), Paris (1990), Berlin (1992), Prague (1995), Delphi (1997), Jerusalem (1999), London (2001), and Siena (2003) so far. ICDT has merged with the Sym- sium on Mathematical Fundamentals of Database Systems (MFDBS), initiated in Dresden in 1987, and continued in Visegrad in 1989 and Rostock in 1991. ICDT had a two-stage submission process. First, 103 abstracts were subm- ted, which were followed a week later by 84 paper submissions. From these 84 submissions, the ICDT Program Committee selected 24 papers for presentation at the conference. Most of these papers were “extended abstracts” and preli- nary reports on work in progress. It is anticipated that most of these papers will appear in a more polished form in scienti?c journals.
Database Systems for Advanced Applications ; Vol. 3882 ; 11th International Conference, DASFAA 2006, Singapore, April 12-15, 2006, Proceedings
This book constitutes the refereed proceedings of the 11th International Conference on Database Systems for Advanced Applications, DASFAA 2006, held in Singapore in April 2006.
Database systems for advanced applications ; Vol. 3453 ; 10th international conference, DASFAA 2005, Beijing, China, April 17-20, 2005, Proceedings
Data Stream Mining and Resource Adaptive Computation.- Purpose Based Access Control for Privacy Protection in Database Systems.- Complex Networks and Network Data Mining.- Bioinformatics.- Indexing DNA Sequences Using q-Grams.- PADS: Protein Structure Alignment Using Directional Shape Signatures.- LinkageTracker: A Discriminative Pattern Tracking Approach to Linkage Disequilibrium Mapping.- Watermarking and Encryption.- Query Optimization in Encrypted Database Systems.- Watermarking Spatial Trajectory Database.- Effective Approaches for Watermarking XML Data.- XML Query Processing.- A Unifying Framework for Merging and Evaluating XML Information.- Efficient Evaluation of Partial Match Queries for XML Documents Using Information Retrieval Techniques.- PathStack: A Holistic Path Join Algorithm for Path Query with Not-Predicates on XML Data.- XML Coding and Metadata Management.- An Improved Prefix Labeling Scheme: A Binary String Approach for Dynamic Ordered XML.- Efficiently Coding and Indexing XML Document.- XQuery-Based TV-Anytime Metadata Management.- Data Mining.- Effective Database Transformation and Efficient Support Computation for Mining Sequential Patterns.
Database Systems for Advanced Applications ; 13th International Conference, DASFAA 2008, New Delhi, India, March 19-21, 2008. Proceedings
This book constitutes the refereed proceedings of the 13th International Conference on Database Systems for Advanced Applications, DASFAA 2008, held in New Delhi, India, in March 2008.
