DOCSLIB.ORG

Planning Resiliency Shaping the Future I Am No Longer Myself

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Planning Resiliency Shaping the Future I Am No Longer Myself Planning resiliency Shaping the future I am no longer myself INTERNATIONAL DAY FOR THE ELIMINATION OF VIOLENCE AGAINST WOMEN 25 NOVEMBER 2019 The actress Melania Dalla Costa and the photographer Dimitri Dimitracacos joined UNICRI in the development of the campaign for the elimination of violence against women. The campaign is a tribute to the victims and it describes the painful process that leads to the destruction of an identity. An identity that can reborn through the strength that only solidarity and help can generate. The campaign is also launching a strong message to violent people: their abuses are a form of weakness, a denial of our human nature. Planning resiliency Shaping the future Confusion of goals and perfection of means seems, in my opinion, to characterize our age Albert Einstein Editorial Board Editor in Chief Graphic and layout UNICRI Marina Mazzini Antonella Bologna Bettina Tucci Bartsiotas Marina Mazzini Editorial Team Cover design Leif Villadsen Merwan Benamor Beniamino Garrone Fabrizio De Rosa Max-Planck Institute Robin Hughes Website designer Hans-Jörg Albrecht Jinyi Li Davide Dal Farra Ulrike Auerbach Marina Mazzini Michael Kilchling Ghent University Tom Vander Beken Jelle Janssens Noel Klima Disclaimer The views expressed are those of the authors and do not necessarily reflect the views and po- sitions of the United Nations. Authors are not responsible for the use that might be made of the information contained in this publication. Contents of the publication may be quoted or reproduced, provided that the source of information is acknowledged. The designations employed and the presentation of the material in this publication do not imply the expression of any opinion whatsoever on the part of the Secretariat of the United Nations and UNICRI, concerning the legal status of any country, territory, city or area or of its authorities, or concerning the delimitation of its frontiers or boundaries. The mention of specific institutions, companies or of certain manufacturers’ products does not imply that they are endorsed or recommended by the Secretariat of the United Nations or UNICRI in preference to others of a similar nature that are not mentioned. DITORIAL BUILD RESILIENCE: getting ready to bounce back by Bettina Tucci Bartsiotas Director a.i. of UNICRI The development of modern technologies along with the acceleration of globaliza- tion and increasing inequalities are generating new paradigms and unpredictable risks. This has huge impact on populations all over the world. Today, millions of peo- ple are coping with crises stemming from climate change, violent extremism, organ- ized crime, and a general lack of vision on how to develop sustainable responses. Threats, uncertainties and socioeconomic disparities, and the need for new effective and innovative approaches are symbiotic in every corner of the world. Over the recent years, the word “resilience” is occupying the vocabulary of the global community. Why? It appears that we have entered a phase where we must cope with problems and adversities that we failed to anticipate and address from the very beginning. The word resiliency per se represents an admission of the need to survive and adapt to a variety of exponential changes that find us unprepared. “Resilience is an individual’s ability to generate biological, psychological and so- cial factors to resist, adapt and strengthen itself, when faced with an environment of risk, generating individual, social and moral success.”1 Resilience expresses the abilities of people, communities and systems to deal with challenges or crises. In the field of crime and justice, developing resilience within and among insti- tutions, social systems, communities and individuals requires a thorough knowl- edge of its causes and the possible ways to prevent escalation. This issue of F3 includes articles describing different areas where resilience should be built. They offer a variety of perspectives, illustrating the necessity of enhancing resilience in institutions, systems and societies to achieve human rights for all, prevent and counter violent extremism and mitigate risks and re- spond to threats. The articles of this issue are closely connected to the Sustain- able Development Goal 16 of the United Nations 2030 Agenda, which aims to promote peaceful and inclusive societies, provide access to justice and strength- 1 Colchado, Oscar Chapital. (2018). “Resiliencia: Una propuesta de concepto y de etapas de desarrol- lo.” Instituto Nacional para la Evaluación de la Educación. https://www.academia.edu/38119923/ Resiliencia_Una_propuesta_de_concepto_y_de_etapas_de_desarrollo iii DITORIAL en institutions and accountability. In addition, Goals 4, 5, 9, 10, 11, 12, 14 are also referred in these articles, embodying the connections between resilience and ed- ucation, gender equality, online security, youth empowerment, community poli- cies, environmental crimes and so on. The importance of building collective resilience cannot be ignored. For example, once a crime is committed, a criminal justice institution focusing on both the pro- cesses of desistance and recovery, and the harm endured by both victims and per- petrators, helps ensure true justice. When confronted with challenges and crises, countries with enhanced international cooperation and harmonized legal frame- works to the relevant conventions and treaties have shown to be more resilient. Enhancing community resilience facilitates the promotion of social justice, de- velopment and the protection of vulnerable groups. Collaborative communities can play a significant role in shaping the future of young people, their ability to find a role in the society through education and skills development. Building resilience at the individual level helps people better tackle current and potential crises, for instance, taking personal actions to guarantee their online privacy as well as recognizing sensitive and violent information in social media and the In- ternet to deal with cybercrime or cyber violence. We are standing at a crossroad, and resilience helps guide us to a positive direc- tion. To achieve a world of respect for dignity and diversity, the rule of law, justice and development, all sides must act together and make collaborative efforts to implement comprehensive responses. Building resilient societies give us the possibility of reshaping a resilient world. As a central and transformative guide of the 2030 Agenda and its SDGs, the prom- ise “Leaving no one behind” still faces challenges and threats stemming from inequalities and vulnerabilities. Recent days have witnessed a wave of demon- strations around the world, from the Middle East to Latin America and the Carib- bean… from Europe to Africa and Asia. Behind those protests in cities across the world, there are economic issues relating to systems and political demands com- ing from people. António Guterres, Secretary-General of the United Nations said: “The global wave of demonstrations we are witnessing shows a growing lack of trust between people and political establishments. People are hurting and want to be heard. We must listen to the real problems of real people, and work to restore the social contract.”2 2 https://twitter.com/antonioguterres/status/1187794920846876672?lang=en iv DITORIAL Researchers identified resilience as a process, not a trait. From the lessons learned all along this adaptation process, we may extrapolate the answers we need to use the gov- ernance tools, knowledge and cooperation mechanisms to eradicate the problems we are facing. Instead of limits itself to building resilience, a real advanced society should be able to prevent crises before it is too late and before an adaptation is needed. A real advanced society requires focus pertaining to the commitment of doing what is possible before a situation gets to the point of crisis and should be able to expand its advances. One day we will achieve a world where no one is left behind; the hope is that this world will have created the conditions for true sustainability. Charles Darwin said that “It is not the most intellectual or the strongest of species that survives; but the species that survives is the one that is able to adapt to and adjust best to the changing environment in which it finds itself.” Compared to the past, changes are occurring at an exponential rate that obliges us to develop the capacity to antici- pate and mitigate negative consequences. We want the change to continue for the best of humankind, minimizing uncertainty, fear, pressure and lack of vision. We need to develop the tools and resources to build resilience. The only vision that can lead humankind is the one the United Nations has of- fered since its very creation, almost 75 years ago. The Charter of the United Na- tions includes the antidotes to address our current problems. We just need the political will to implement a concept of global solidarity. I hope we will reach the day when we replace resiliency with global solidarity to be one step ahead of the challenges of our global village. v CONT NTS Women and prevention of violent extremism: 1 does it work – and if so, how? by Edit Schlaffer Community resilience: insights from UNICRI 8 experience in the Sahel-Maghreb by Danielle Hull, Tamara Nešković, Manuela Brunero No one is left behind in the fight of the EU 12 against violent extremism by Deborah Phares Youth engagement and resilience against 18 violent extremism in the Sahel How to train professionals for managing the 22 contradictions of a multiethnic
Load more

Recommended publications
  • Xinggan for Person Image Generation
    XingGAN for Person Image Generation Hao Tang1;2, Song Bai2, Li Zhang2, Philip H.S. Torr2, and Nicu Sebe1;3 1University of Trento ([email protected]) 2University of Oxford 3Huawei Research Ireland Abstract. We propose a novel Generative Adversarial Network (Xing- GAN or CrossingGAN) for person image generation tasks, i.e., translat- ing the pose of a given person to a desired one. The proposed Xing gener- ator consists of two generation branches that model the person's appear- ance and shape information, respectively. Moreover, we propose two novel blocks to effectively transfer and update the person's shape and appear- ance embeddings in a crossing way to mutually improve each other, which has not been considered by any other existing GAN-based image genera- tion work. Extensive experiments on two challenging datasets, i.e., Market- 1501 and DeepFashion, demonstrate that the proposed XingGAN ad- vances the state-of-the-art performance both in terms of objective quan- titative scores and subjective visual realness. The source code and trained models are available at https://github.com/Ha0Tang/XingGAN. Keywords: Generative Adversarial Networks (GANs), Person Image Generation, Appearance Cues, Shape Cues 1 Introduction The problem of person image generation aims to generate photo-realistic per- son images conditioned on an input person image and several desired poses. This task has a wide range of applications such as person image/video genera- tion [41,9,2,11,19] and person re-identification [45,28]. Exiting methods such as [21,22,31,45,35] have achieved promising performance on this challenging task.
    [Show full text]
  • Video and Audio Deepfakes: What Lawyers Need to Know by Sharon D
    Video and Audio Deepfakes: What Lawyers Need to Know by Sharon D. Nelson, Esq., and John W. Simek © 2020 Sensei Enterprises, Inc. If some nefarious person has decent photos of your face, you too (like so many unfortunate Hollywood celebrities) could appear to be the star of a pornographic video. If someone has recordings of your voice (from your website videos, CLEs you have presented, speeches you’ve given, etc.), they can do a remarkably good job of simulating your spoken words and, just as an example, call your office manager and authorize a wire transfer – something the office manager may be willing to do because of “recognizing” your voice. Unnerving? Yes, but it is the reality of today. And if you don’t believe how “white hot” deepfakes are, just put a Google alert on that word and you’ll be amazed at the volume of daily results. Political and Legal Implications We have already seen deepfakes used in the political area (the “drunk” Nancy Pelosi deepfake, a reference to which was tweeted by the president), and many commentators worry that deepfake videos will ramp up for the 2020 election. Some of them, including the Pelosi video, are referred to as “cheapfakes” because they are so poorly done (basically running the video at 75 percent speed to simulate drunkenness), but that really doesn’t matter if large numbers of voters believe it’s real. And the days when you could tell a deepfake video by the fact that the person didn’t blink are rapidly vanishing as the algorithms have gotten smarter.
    [Show full text]
  • Neural Rendering and Reenactment of Human Actor Videos
    Neural Rendering and Reenactment of Human Actor Videos LINGJIE LIU, University of Hong Kong, Max Planck Institute for Informatics WEIPENG XU, Max Planck Institute for Informatics MICHAEL ZOLLHÖFER, Stanford University, Max Planck Institute for Informatics HYEONGWOO KIM, FLORIAN BERNARD, and MARC HABERMANN, Max Planck Institute for Informatics WENPING WANG, University of Hong Kong CHRISTIAN THEOBALT, Max Planck Institute for Informatics (real) Driving motion (synth.) Output Fig. 1. We propose a novel learning-based approach for the animation and reenactment of human actor videos. The top row shows some frames of the video from which the source motion is extracted, and the bottom row shows the corresponding synthesized target person imagery reenacting the source motion. We propose a method for generating video-realistic animations of real hu- images are then used to train a conditional generative adversarial network mans under user control. In contrast to conventional human character render- that translates synthetic images of the 3D model into realistic imagery of ing, we do not require the availability of a production-quality photo-realistic the human. We evaluate our method for the reenactment of another person 3D model of the human, but instead rely on a video sequence in conjunction that is tracked in order to obtain the motion data, and show video results with a (medium-quality) controllable 3D template model of the person. With generated from artist-designed skeleton motion. Our results outperform the that, our approach significantly reduces production cost compared to conven- state-of-the-art in learning-based human image synthesis. tional rendering approaches based on production-quality 3D models, and can CCS Concepts: • Computing methodologies → Computer graphics; also be used to realistically edit existing videos.
    [Show full text]
  • Complement the Broken Pose in Human Image Synthesis
    Focus and retain: Complement the Broken Pose in Human Image Synthesis Pu Ge†, Qiushi Huang†, Wei Xiang‡, Xue Jing, Yule Li, Yiyong Li, Zhun Sun Bigo Technology PTE. LTD, Singapore {gepu,huangqiushi,xiangwei1}@bigo.sg Abstract Given a target pose, how to generate an image of a spe- cific style with that target pose remains an ill-posed and thus complicated problem. Most recent works treat the human pose synthesis tasks as an image spatial transformation prob- lem using flow warping techniques. However, we observe that, due to the inherent ill-posed nature of many compli- cated human poses, former methods fail to generate body parts. To tackle this problem, we propose a feature-level flow attention module and an Enhancer Network. The flow attention module produces a flow attention mask to guide the combination of the flow-warped features and the structural pose features. Then, we apply the Enhancer Network to re- fine the coarse image by injecting the pose information. We present our experimental evaluation both qualitatively and quantitatively on DeepFashion, Market-1501, and Youtube dance datasets. Quantitative results show that our method has 12.995 FID at DeepFashion, 25.459 FID at Market-1501, 14.516 FID at Youtube dance datasets, which outperforms some state-of-the-arts including Guide-Pixe2Pixe, Global- Flow-Local-Attn, and CocosNet. 1. Introduction Figure 1: (a) The inputs of the task: a reference image with a target pose. (b) The outputs of the task: a generated human in Conditional image generation and synthesis becomes a the target pose. From left to right: the ground truth, results popular computer vision task recent years [29].
    [Show full text]
  • Unpaired Pose Guided Human Image Generation
    Research Collection Conference Paper Unpaired Pose Guided Human Image Generation Author(s): Chen, Xu; Song, Jie; Hilliges, Otmar Publication Date: 2019 Permanent Link: https://doi.org/10.3929/ethz-b-000396290 Rights / License: In Copyright - Non-Commercial Use Permitted This page was generated automatically upon download from the ETH Zurich Research Collection. For more information please consult the Terms of use. ETH Library Unpaired Pose Guided Human Image Generation Xu Chen Jie Song Otmar Hilliges AIT Lab, ETH Zurich {xuchen,jsong,otmarh}@inf.ethz.ch Abstract This paper studies the task of full generative modelling of realistic images of humans, guided only by coarse sketch of the pose, while providing control over the specific instance or type of outfit worn by the user. This is a difficult prob- lem because input and output domain are very different and direct image-to-image translation becomes infeasible. We propose an end-to-end trainable network under the gener- ative adversarial framework, that provides detailed control over the final appearance while not requiring paired train- ing data and hence allows us to forgo the challenging prob- lem of fitting 3D poses to 2D images. The model allows to generate novel samples conditioned on either an image taken from the target domain or a class label indicating the style of clothing (e.g., t-shirt). We thoroughly evaluate the architecture and the contributions of the individual compo- nents experimentally. Finally, we show in a large scale per- ceptual study that our approach can generate realistic look- Figure 1: Generating humans in clothing: Our network ing images and that participants struggle in detecting fake takes a pose sketch as input and generates realistic images, images versus real samples, especially if faces are blurred.
    [Show full text]
  • Generative Adversarial Networks in Human Emotion Synthesis: a Review
    Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000. Digital Object Identifier 10.1109/ACCESS.2017.DOI Generative Adversarial Networks in Human Emotion Synthesis: A Review NOUSHIN HAJAROLASVADI1, MIGUEL ARJONA RAMÍREZ2, (Senior Member, IEEE), WESLEY BECCARO2, and HASAN DEMIREL.1, (Senior Member, IEEE) 1Eastern Mediterranean University, Electrical and Electronic Engineering Department, Gazimagusa, 10 Via Mersin, Turkey 2University of São Paulo, Escola Politécnica, Department of Electronic Systems Engineering, São Paulo, Brazil Corresponding author: Miguel Arjona Ramírez (e-mail: [email protected]). ABSTRACT Deep generative models have become an emerging topic in various research areas like computer vision and signal processing. These models allow synthesizing realistic data samples that are of great value for both academic and industrial communities Affective computing, a topic of a broad interest in computer vision society, has been no exception and has benefited from this powerful approach. In fact, affective computing observed a rapid derivation of generative models during the last two decades. Applications of such models include but are not limited to emotion recognition and classification, unimodal emotion synthesis, and cross-modal emotion synthesis. As a result, we conducted a comprehensive survey of recent advances in human emotion synthesis by studying available databases, advantages, and disadvantages of the generative models along with the related training strategies considering two principal human communication modalities, namely audio and video. In this context, facial expression synthesis, speech emotion synthesis, and the audio-visual (cross-modal) emotion synthesis are reviewed extensively under different application scenarios. Gradually, we discuss open research problems to push the boundaries of this research area for future works.
    [Show full text]
  • Successive Image Generation from a Single Sentence Amogh Parab1, Ananya Malik1, Arish Damania1, Arnav Parekhji1, and Pranit Bari1
    ITM Web of Conferences 40, 03017 (2021) https://doi.org/10.1051/itmconf/20214003017 ICACC-2021 Successive Image Generation from a Single Sentence Amogh Parab1, Ananya Malik1, Arish Damania1, Arnav Parekhji1, and Pranit Bari1 1 Dwarkadas J. Sanghvi College of Engineering, Mumbai, India Abstract - Through various examples in history such as the early man’s carving on caves, dependence on diagrammatic representations, the immense popularity of comic books we have seen that vision has a higher reach in communication than written words. In this paper, we analyse and propose a new task of transfer of information from text to image synthesis. Through this paper we aim to generate a story from a single sentence and convert our generated story into a sequence of images. We plan to use state of the art technology to implement this task. With the advent of Generative Adversarial Networks text to image synthesis have found a new awakening. We plan to take this task a step further, in order to automate the entire process. Our system generates a multi-lined story given a single sentence using a deep neural network. This story is then fed into our networks of multiple stage GANs inorder to produce a photorealistic image sequence. Keyword - Deep Learning, Generative Adversarial Networks, Natural Language Processing, Computer Vision, LSTM, CNN, RNN, GRU, GPT-2. 1. INTRODUCTION between images. In order to maintain the intertextuality between the images, the paper Tell me and I will forget, Teach me and I will proposes the use of a Deep Context Encoder that remember, Show me and I will learn.
    [Show full text]
  • Countering Violent Extremism and Radicalization That Lead to Terrorism: Leveraging the OSCE’S ....93 Comprehensive and Co-Operative Approach to Security Mehdi Knani
    Countering Violent Extremism: Dialogue, Training, and Research 6eleFteG %rieÀng 3DSers C M Y CM MY CY CMY Hedayah and/or K and Gulf Military Analysis. Content may have been edited for formatting purposes. All rights reserved. Reproduction and/or circulation of this document or of any individual Institute for Near East and Gulf Military Analysis as publisher. Published in 2012 by the Institute for Near East and Gulf Military Analysis (INEGMA) P.O.Box 502066, Dubai, UAE www.inegma.com Contents Exe uti e umm r .......................................................................................................9 ulti is i lin r ers e ti es on Countering Violent Extremism .............................15 Rehabilitation First, Countering Inmate Radicalization Second: ...................................................................17 Setting Priorities in Dealing with Violent Extremist Offenders in Prison Tinka M. Veldhuis, Siegwart Lindenberg From Caged Bodies to Caged Souls: ................................................................................................................23 The Case of Former Muslim Prisoners and The Importance of Religious Counseling Gabriele Marranci C M Unlocking the Terrorist Mindset: A Psychological Approach ......................................................................27 Y Malkanthi Hettiarachchi CM Countering Violent Extremism: The Evolving Role of Think Tanks ..........................................................33 MY Rohan Gunaratna CY CMY K essons e rne rom t e iel ....................................................................................41
    [Show full text]
  • Human Synthesis and Scene Compositing
    The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20) Human Synthesis and Scene Compositing Mihai Zanfir,3,1 Elisabeta Oneata,3,1 Alin-Ionut Popa,3,1 Andrei Zanfir,1,3 Cristian Sminchisescu1,2 1Google Research 2Department of Mathematics, Faculty of Engineering, Lund University 3Institute of Mathematics of the Romanian Academy {mihai.zanfir, elisabeta.oneata, alin.popa, andrei.zanfir}@imar.ro, [email protected] Abstract contrast, other approaches avoid the 3d modeling pipeline altogether, aiming to achieve realism by directly manipulat- Generating good quality and geometrically plausible syn- ing images and by training using large-scale datasets. While thetic images of humans with the ability to control appear- ance, pose and shape parameters, has become increasingly this is cheap and attractive, offering the advantage of produc- important for a variety of tasks ranging from photo editing, ing outputs with close to real statistics, they are not nearly fashion virtual try-on, to special effects and image compres- as controllable as the 3d graphics ones, and results can be sion. In this paper, we propose a HUSC (HUman Synthesis geometrically inconsistent and often unpredictable. and Scene Compositing) framework for the realistic synthe- In this work we attempt to combine the relatively accessi- sis of humans with different appearance, in novel poses and ble methodology in both domains and propose a framework scenes. Central to our formulation is 3d reasoning for both that is able to realistically synthesize a photograph of a per- people and scenes, in order to produce realistic collages, by correctly modeling perspective effects and occlusion, by tak- son, in any given pose and shape, and blend it veridically ing into account scene semantics and by adequately handling with a new scene, while obeying 3d geometry and appear- relative scales.
    [Show full text]
  • Challenging the Traditional Gender Roles As Seen by University Students in Saudi Arabia Fawziah Al-Bakr King Saud University, [email protected]
    FIRE: Forum for International Research in Education Volume 4 | Issue 1 Article 3 Empowered but not Equal: Challenging the Traditional Gender Roles as Seen by University Students in Saudi Arabia Fawziah Al-bakr King Saud University, [email protected] Elizabeth R. Bruce Lehigh University, [email protected] Petrina M. Davidson Lehigh University, [email protected] Edit Schlaffer Women without Borders, [email protected] Ulrich Kropiunigg Medical University of Vienna, [email protected] Follow this and additional works at: http://preserve.lehigh.edu/fire Part of the Curriculum and Social Inquiry Commons, Educational Administration and Supervision Commons, Educational Assessment, Evaluation, and Research Commons, International and Comparative Education Commons, Science and Mathematics Education Commons, Social and Philosophical Foundations of Education Commons, and the Teacher Education and Professional Development Commons Recommended Citation Al-bakr, F., Bruce, E. R., Davidson, P. M., Schlaffer, E., & Kropiunigg, U. (2017). Empowered but not Equal: Challenging the Traditional Gender Roles as Seen by University Students in Saudi Arabia. FIRE: Forum for International Research in Education, 4(1). Retrieved from http://preserve.lehigh.edu/fire/vol4/iss1/3 This Article is brought to you for free and open access by Lehigh Preserve. It has been accepted for inclusion in FIRE: Forum for International Research in Education by an authorized editor of Lehigh Preserve. For more information, please contact [email protected]. Empowered but not Equal: Challenging the Traditional Gender Roles as Seen by University Students in Saudi Arabia Abstract This study examines perspectives of Saudi university students regarding changing gender roles as affected by women’s rights, education, employment, and activity in the public sphere.
    [Show full text]
  • Deep Fake Creation by Deep Learning
    International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 07 Issue: 07 | July 2020 www.irjet.net p-ISSN: 2395-0072 Deep Fake Creation by Deep Learning Harshal Vyas -------------------------------------------------------------------------***---------------------------------------------------------------------- Abstract: Machine Learning techniques are escalating technology’s sophistication. Deep Learning is also known as Deep Structured Learning which is a part of the broader family of Machine Learning. Deep Learning architectures such as Deep Neural Networks, Deep Belief Networks, Convolutional Neural Networks(CNN) have been used for computer visions and for language processing. One of those deep learning-powered applications recently emerged is “deep fake”. Deep fake is a technique or technology where one can create fake images and videos which are difficult for humans to detect. This paper deals with how deep fakes are created and what kind of algorithms are used in it. This will help people to get to know about the deep fakes that are being generated on a daily basis, a way for them to know what is real and what isn’t. 1. Introduction: Deep fake (a portmanteau of "deep learning" and "fake") is a technique for human image synthesis based on artificial intelligence. Deep learning models such as Autoencoders and Generative Adversarial Networks have been applied widely in the computer vision domain to solve various problems. All these models have been used by deepfake algorithms to examine facial expressions and moments of an individual person and later synthesize facial images of another person making comparable expressions and moments. Generally, deepfake algorithms require a large amount of image and video data set to train models.
    [Show full text]
  • Deep Fake Detection Using Neural Networks
    Special Issue - 2021 International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181 NTASU - 2020 Conference Proceedings Deep Fake Detection using Neural Networks Anuj Badale Chaitanya Darekar Information Technology Information Technology St.Francis Institute of Technology St.Francis Institute of Technology Mumbai, India Mumbai, India Lionel Castelino Joanne Gomes Information Technology Information Technology St.Francis Institute of Technology St.Francis Institute of Technology Mumbai, India Mumbai, India Abstract— Deepfake is a technique for human image synthesis with the body of John Calhoun. The engravings of his head on based on artificial intelligence. Deepfake is used to merge and other bodies appeared quite often after his assassination. superimpose existing images and videos onto source images or videos using machine learning techniques. They are realistic Authors David Guera Edward J. Delp put forth a paper based looking fake videos that cannot be distinguished by naked eyes. on Artificial Intelligence. The topic discussed in the paper is They can be used to spread hate speeches, create political distress, Convolution Neural Network(CNN), Recurrent Neural blackmail someone, etc. Currently, Cryptographic signing of Network(RNN). The author tried to evaluate method against a videos from its source is done to check the authenticity of videos. large set of DeepFake videos collected from multiple video Hashing of a video file into “fingerprints” (small string of text) is websites. Scenarios where these realistic fake videos are used done and reconfirmed with the sample video and thus verified to create political distress, black-mail someone or fake whether the video is the one originally recorded or not. However, terrorism events are easily envisioned.
    [Show full text]