scholarly journals Deep fake : An Understanding of Fake Images and Videos

2021 ◽  
pp. 183-189
Author(s):  
Shweta Negi ◽  
Mydhili Jayachandran ◽  
Shikha Upadhyay
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
National Security ◽  
Review Paper ◽  
Preventive Measures ◽  
Major Research ◽  
Creative Imagination ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Learning Machine

The Deepfake algorithm allows its user to create fake images, audios, videos that gives very real impression but is fake in real sense. This degree of technology is achieved due to advancements in Deep Learning, Machine Learning, Artificial Intelligence and Neural Networking that is a combination of algorithms like generative adversarial network (GAN), autoencoders etc. Any technology has its positive and negative repercussions. Deep fake can come in use for helping people who have lost their speech to give them new improved voice, commercially deepfake can be used in improving animation or movie quality putting in creative imagination to work as well is therapeutic to people who have lost their dear once. Negative aspects of deep fake include creating fake images, videos, audios that look very real can cause threats to an individual’s privacy, organizations, democracy, and even national security. This review paper presents history on how deep fake emerged, will comprehend on how it works including various algorithms, major research works done on understanding deep fakes in the literature and most importantly discuss recent advancements in detection of deep fake methods and its robust preventive measures.

scholarly journals GAINESIS: Generative Artificial Intelligence NEtlists SynthesIS

Electronics ◽  
2022 ◽  
Vol 11 (2) ◽  
pp. 245
Author(s):  
Konstantinos G. Liakos ◽  
Georgios K. Georgakilas ◽  
Fotis C. Plessas ◽  
Paris Kitsos
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Power Analysis ◽  
Public Libraries ◽  
Data Sets ◽  
Hardware Trojan ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Encrypted Data ◽  
Adversarial Network

A significant problem in the field of hardware security consists of hardware trojan (HT) viruses. The insertion of HTs into a circuit can be applied for each phase of the circuit chain of production. HTs degrade the infected circuit, destroy it or leak encrypted data. Nowadays, efforts are being made to address HTs through machine learning (ML) techniques, mainly for the gate-level netlist (GLN) phase, but there are some restrictions. Specifically, the number and variety of normal and infected circuits that exist through the free public libraries, such as Trust-HUB, are based on the few samples of benchmarks that have been created from circuits large in size. Thus, it is difficult, based on these data, to develop robust ML-based models against HTs. In this paper, we propose a new deep learning (DL) tool named Generative Artificial Intelligence Netlists SynthesIS (GAINESIS). GAINESIS is based on the Wasserstein Conditional Generative Adversarial Network (WCGAN) algorithm and area–power analysis features from the GLN phase and synthesizes new normal and infected circuit samples for this phase. Based on our GAINESIS tool, we synthesized new data sets, different in size, and developed and compared seven ML classifiers. The results demonstrate that our new generated data sets significantly enhance the performance of ML classifiers compared with the initial data set of Trust-HUB.

scholarly journals A Novel Technique to Regenerate Sculpture Using Generative Adversarial Network

2020 ◽  
Author(s):  
S.A.K. Jainulabudeen ◽  
H. Shalma ◽  
S. Gowri Shankar ◽  
D. Anuradha ◽  
K. Soniya
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
The Other ◽  
Generative Adversarial Network ◽  
Novel Technique ◽  
The Past ◽  
Adversarial Network ◽  
The Many

Dancing, music or any format of art has been a prominent thing from the past centuries. The many dynasties ruled the nation for centuries but every king encouraged the art one way or the other. The present day is just a minute part of the finest part of that era of art; the art of any form had been lost in the shadows to redeem the lost art we are going to use the latest technology like machine learning and artificial intelligence. The art lovers of the present age can seek the knowledge of lost art through this modern day technology. The retrieval of this art can only be done if there is a possibility to learn their language which helps in reading the old sculptures or the paintings on the walls of the ancient architecture. Now using the present day technology we are going to recoup that lost art through reading the walls of those structures where the art has been hidden for centuries. So at present we do not allow the art to continue to fall into shadow and extinguish later on, thus in this paper we present a DC-GAN model which has been created to inherit all the artistic skills of our ancestors by training from the key images of art designed as sculptures by our forefathers.

scholarly journals Deep Fakes, Artificial Intelligence & Eco Species

2020 ◽  
Author(s):  
Abhilasha Semwal
Keyword(s):  
Machine Learning ◽  
National Security ◽  
Cyber Security ◽  
Research Effort ◽  
The Body ◽  
Machine Learning Algorithms ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
The World ◽  
Mona Lisa

Interestingly art is full of reproductions. Some are replicas, like Mona Lisa and others are fake or forgeries, like the ‘Vermeers’ painted by Han van Meegeren that was sold for $60 million (Kreuger and van Meegeren 2010).Now the distinction between real and fake is based on the concept of authenticity. The question is, is this artefact what it claims to be? The answer seems simple, but in reality, things are complicated. Today, the painting of the forger John Myatt are so famous that they are valued at up to $40,000 each, as ‘genuine fake’ (Furlong 1986). So technically, they are not what they say they are, but they are authentically painted by him and not by any other forger. And they are beautiful, “a bit as if one were to utter a beautiful lie, not any ordinary lie.”According to research out of cyber security company, Deeptrace, the numbers of ‘deepfake’ videos on the internet have doubled in just nine months from 7,964 in December 2018 to 14,698. Of these ‘deepfakes’, 96% were pornographic, often with a face of a celebrity morphed onto the body of an adult actor engaged in sexual activity . Accordingly, Facebook has invested $ 10M into research effort to produce a database and benchmark for detecting deepfakes, and is partnering with top research institutions such as MIT, UC Berkeley, and Cornell Tech . It is clear that deepfakes are alarming and firms like Facebook are doing something about it, but the question is what are deepfakes? And why are they alarming?Due to increased concentration of users around social media and democratization of means by which deepfakes are produced, the web is seeing and increasing propagation of hyper-realistic deepfakes without technical understanding of machine learning, and their increased realism and scale is largely due to improvements in the organization of datasets being fed into machine learning algorithms, as well as the introduction of Generative Adversarial Network (GANs).When truths are indistinguishable from falsehoods, we put at risk our democracy, our ‘national security, and public safety. When the world of the ‘perfect’ deepfake, the waters of fact and fiction are muddled, creating a fog of questioning what’s real and what’s fake?How might deepfakes make us question our national security in times of war? Deepfakes sent from adversaries can show our soldiers killing civilian to invoke an environment of distrust and instability.

ORGANIC (1).pdf

2017 ◽  
Author(s):  
Benjamin Sanchez-Lengeling ◽  
Carlos Outeiral ◽  
Gabriel L. Guimaraes ◽  
Alan Aspuru-Guzik
Keyword(s):  
Machine Learning ◽  
Learning Community ◽  
Chemical Species ◽  
Material Design ◽  
Organic Photovoltaic ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Photovoltaic Material

Molecular discovery seeks to generate chemical species tailored to very specific needs. In this paper, we present ORGANIC, a framework based on Objective-Reinforced Generative Adversarial Networks (ORGAN), capable of producing a distribution over molecular space that matches with a certain set of desirable metrics. This methodology combines two successful techniques from the machine learning community: a Generative Adversarial Network (GAN), to create non-repetitive sensible molecular species, and Reinforcement Learning (RL), to bias this generative distribution towards certain attributes. We explore several applications, from optimization of random physicochemical properties to candidates for drug discovery and organic photovoltaic material design.

Development of innovative hygienic technologies for preservation of the workers’ reproductive health

2020 ◽  
pp. 792-792
Author(s):  
M. A. Fesenko ◽  
G. V. Golovaneva ◽  
A. V. Miskevich
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Reproductive Health ◽  
Reproductive System ◽  
Preventive Measures ◽  
Learning Algorithms ◽  
Reproductive Function ◽  
Machine Learning Algorithms ◽  
New Model

The new model «Prognosis of men’ reproductive function disorders» was developed. The machine learning algorithms (artificial intelligence) was used for this purpose, the model has high prognosis accuracy. The aim of the model applying is prioritize diagnostic and preventive measures to minimize reproductive system diseases complications and preserve workers’ health and efficiency.

scholarly journals Machine Learning for Dissimulating Reality

Proceedings ◽  
2021 ◽  
Vol 77 (1) ◽  
pp. 17
Author(s):  
Andrea Giussani
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Huge Amount ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Technological Advances ◽  
Textual Data ◽  
Musical Scores ◽  
Mathematical Formulas

In the last decade, advances in statistical modeling and computer science have boosted the production of machine-produced contents in different fields: from language to image generation, the quality of the generated outputs is remarkably high, sometimes better than those produced by a human being. Modern technological advances such as OpenAI’s GPT-2 (and recently GPT-3) permit automated systems to dramatically alter reality with synthetic outputs so that humans are not able to distinguish the real copy from its counteracts. An example is given by an article entirely written by GPT-2, but many other examples exist. In the field of computer vision, Nvidia’s Generative Adversarial Network, commonly known as StyleGAN (Karras et al. 2018), has become the de facto reference point for the production of a huge amount of fake human face portraits; additionally, recent algorithms were developed to create both musical scores and mathematical formulas. This presentation aims to stimulate participants on the state-of-the-art results in this field: we will cover both GANs and language modeling with recent applications. The novelty here is that we apply a transformer-based machine learning technique, namely RoBerta (Liu et al. 2019), to the detection of human-produced versus machine-produced text concerning fake news detection. RoBerta is a recent algorithm that is based on the well-known Bidirectional Encoder Representations from Transformers algorithm, known as BERT (Devlin et al. 2018); this is a bi-directional transformer used for natural language processing developed by Google and pre-trained over a huge amount of unlabeled textual data to learn embeddings. We will then use these representations as an input of our classifier to detect real vs. machine-produced text. The application is demonstrated in the presentation.

scholarly journals Self-Supervised Machine Learning Approach for Identifying Biochemical Influences on Protein-Ligand Binding Affinity

2021 ◽  
Author(s):  
Arjun Singh
Keyword(s):  
Machine Learning ◽  
Binding Affinity ◽  
3D Models ◽  
Target Protein ◽  
Supervised Machine Learning ◽  
Significant Feature ◽  
Computational Techniques ◽  
Lasso Regression ◽  
Generative Adversarial Network ◽  
Adversarial Network

Abstract Drug discovery is incredibly time-consuming and expensive, averaging over 10 years and $985 million per drug. Calculating the binding affinity between a target protein and a ligand is critical for discovering viable drugs. Although supervised machine learning (ML) models can predict binding affinity accurately, they suffer from lack of interpretability and inaccurate feature selection caused by multicollinear data. This study used self-supervised ML to reveal underlying protein-ligand characteristics that strongly influence binding affinity. Protein-ligand 3D models were collected from the PDBBind database and vectorized into 2422 features per complex. LASSO Regression and hierarchical clustering were utilized to minimize multicollinearity between features. Correlation analyses and Autoencoder-based latent space representations were generated to identify features significantly influencing binding affinity. A Generative Adversarial Network was used to simulate ligands with certain counts of a significant feature, and thereby determine the effect of a feature on improving binding affinity with a given target protein. It was found that the CC and CCCN fragment counts in the ligand notably influence binding affinity. Re-pairing proteins with simulated ligands that had higher CC and CCCN fragment counts could increase binding affinity by 34.99-37.62% and 36.83%-36.94%, respectively. This discovery contributes to a more accurate representation of ligand chemistry that can increase the accuracy, explainability, and generalizability of ML models so that they can more reliably identify novel drug candidates. Directions for future work include integrating knowledge on ligand fragments into supervised ML models, examining the effect of CC and CCCN fragments on fragment-based drug design, and employing computational techniques to elucidate the chemical activity of these fragments.

scholarly journals Class Imbalanced Fault Diagnosis via Combining K-Means Clustering Algorithm with Generative Adversarial Networks

2021 ◽  
Vol 25 (3) ◽  
pp. 346-355
Author(s):  
Huifang Li ◽  
◽  
Rui Fan ◽  
Qisong Shi ◽  
Zijian Du
Keyword(s):  
Machine Learning ◽  
Fault Diagnosis ◽  
Diagnostic Accuracy ◽  
Clustering Algorithm ◽  
Generative Adversarial Networks ◽  
Similar Distribution ◽  
Generative Adversarial Network ◽  
Minority Class ◽  
Adversarial Network ◽  
Original Dataset

Recent advancements in machine learning and communication technologies have enabled new approaches to automated fault diagnosis and detection in industrial systems. Given wide variation in occurrence frequencies of different classes of faults, the class distribution of real-world industrial fault data is usually imbalanced. However, most prior machine learning-based classification methods do not take this imbalance into consideration, and thus tend to be biased toward recognizing the majority classes and result in poor accuracy for minority ones. To solve such problems, we propose a k-means clustering generative adversarial network (KM-GAN)-based fault diagnosis approach able to reduce imbalance in fault data and improve diagnostic accuracy for minority classes. First, we design a new k-means clustering algorithm and GAN-based oversampling method to generate diverse minority-class samples obeying the similar distribution to the original minority data. The k-means clustering algorithm is adopted to divide minority-class samples into k clusters, while a GAN is applied to learn the data distribution of the resulting clusters and generate a given number of minority-class samples as a supplement to the original dataset. Then, we construct a deep neural network (DNN) and deep belief network (DBN)-based heterogeneous ensemble model as a fault classifier to improve generalization, in which DNN and DBN models are trained separately on the resulting dataset, and then the outputs from both are averaged as the final diagnostic result. A series of comparative experiments are conducted to verify the effectiveness of our proposed method, and the experimental results show that our method can improve diagnostic accuracy for minority-class samples.

scholarly journals A hybrid quantum-classical conditional generative adversarial network algorithm for human-centered paradigm in cloud

2020 ◽  
Author(s):  
Wenjie Liu ◽  
Ying Zhang ◽  
Zhiliang Deng ◽  
Jiaojiao Zhao ◽  
Lian Tong
Keyword(s):  
Machine Learning ◽  
Quantum Circuit ◽  
Machine Learning Algorithms ◽  
Generation Process ◽  
Generative Adversarial Network ◽  
Computing Platform ◽  
Adversarial Network ◽  
Quantum Machine Learning ◽  
Huge Impact ◽  
Conditional Information

Abstract As an emerging field that aims to bridge the gap between human activities and computing systems, human-centered computing (HCC) in cloud, edge, fog has had a huge impact on the artificial intelligence algorithms. The quantum generative adversarial network (QGAN) is considered to be one of the quantum machine learning algorithms with great application prospects, which also should be improved to conform to the human-centered paradigm. The generation process of QGAN is relatively random and the generated model does not conform to the human-centered concept, so it is not quite suitable for real scenarios. In order to solve these problems, a hybrid quantum-classical conditional generative adversarial network (QCGAN) algorithm is proposed, which is a knowledge-driven human-computer interaction computing mode in cloud. The purpose of stabilizing the generation process and the interaction between human and computing process is achieved by inputting conditional information in the generator and discriminator. The generator uses the parameterized quantum circuit with an all-to-all connected topology, which facilitates the tuning of network parameters during the training process. The discriminator uses the classical neural network, which effectively avoids the ”input bottleneck” of quantum machine learning. Finally, the BAS training set is selected to conduct experiment on the quantum cloud computing platform. The result shows that the QCGAN algorithm can effectively converge to the Nash equilibrium point after training and perform human-centered classification generation tasks.

Sign in / Sign up

Export Citation Format

Share Document