Login with your Social Account

algorithm image deep learning

Researchers develop deep neural network to identify deepfakes

It was normally considered that seeing is believing until we learnt that photo editing tools can be used to alter the images we see. Technology has taken this one notch higher where facial expressions of one person can be mapped onto another in realistic videos known as deepfakes. However, each of these manipulations is not conclusive as all the image and video editing tools leave traces to be identified. 

A group of researchers led by Video Computing Group of Amit Roy Chowdhury at the University of California, Riverside has created a deep neural network architecture which can detect the manipulated images at pixel level with very high accuracy. Amit Roy Chowdhury is a professor of computer science and electrical engineering at Rosemary Bourns College of Engineering. He is also a Bourns Family Faculty Fellow. The study has been published in the IEEE Digital Library

As per artificial intelligence researchers, the deep neural network is a computer system which has been trained to perform specific tasks which, in this case, identify the altered images. The networks are organised in several connected layers. 

Objects which are present in images have boundaries and whenever an object is removed or inserted to an image, its boundary will be different than the boundary which is normally present. People having good Photoshop skills will try their best to make these boundaries look natural. Examining pixel by pixel brings out the differences in the boundaries. As a result, by checking the boundaries, a computer can distinguish between a normal and an altered image. 

Scientists labelled the images which were not manipulated and relevant pixels in the boundaries of the altered images in a large photo dataset. The neural network was fed the information about manipulated and the natural regions of the images. Then it was tested with a training dataset of different images and it could successfully detect the manipulated images most of the times along with the region. It provided the probability of the image being a manipulated one. Scientists are working with still images as of now, but this technique can also be used for deepfake videos. 

Roy Chowdhury pointed out that a video is essentially a collection of still images, so the application for a still image will also be applied to a video. However, the challenge lies to figure out if a frame in a video is altered or not. It is a long way to go before deepfake videos are identified by automated tools.

Roy Chowdhury pointed out that in cybersecurity, the situation is similar to a cat mouse game, with better defence mechanisms the attackers also come up with better alternatives. He pointed out that a combination of a human and automated system is the right mix to perform the tasks. Neural networks can make a list of suspicious images and videos to be reviewed by people. Automation can then help in the amount of data to be sifted through to determine if an image has been altered or not. He said that this might be possible in a few years’ time with the help of the technologies.

Journal Reference: IEEE Digital Library

Cygnus A composite image

Astronomers manage to capture image of dusty torus around black hole

Yeah it’s true that in current world generation, on every day we come to know about something weird and amazing related to entire universe. In recent research through astronomy, researchers have found a clear view of dusty clouds near a black whole. Actually this not a cloud but a dusty torus that is surrounding a very active supermassive black hole.

It is around 800 million light-years away and spews out radio waves.

The ring – referred to as a torus – was imaged round the part at the centre of Cygnus A, one of the most powerful radio galaxies in the Universe. The image contributes to a growing faculty of thought that claims these dirt riddled black holes, known collectively as active galactic nuclei (AGN), form the centre of enormously powerful galaxies.

Astronomers have taken the first-ever direct image of a dust covered doughnut moving around a supermassive part. The ring – referred to as a torus – was imaged round the core of Cygnus A, one of the most powerful radio galaxies in the Universe. The image contributes to a growing school of thought which claims these dust riddled black holes, known collectively as active galactic nuclei (AGN), form the centre of enormously powerful galaxies.

Everyone knows what black hole exactly is, if not then we tell you ,” Black holes are so dense and their gravitational pull is so strong that no form of radiation will escape them – not even light-weight.” Supermassive black holes are incredibly dense areas in the centre of galaxies with masses that can be billions of times that of the sun.

They cause dips in reference system and even light-weight cannot escape their gravitative pull. Black holes never let light enter around them because they absorb it. This is a source image of dusty torus ring that has been seen clearly. Further observations may reveal even additional details concerning the dynamics of the torus, and the role it plays in the AGN system.”It’s really great to finally see direct evidence of something that we’ve long presumed should be there,” said Chris Carelli of National Radio Astronomy Observatory (NRAO).

The torus structure scientists have managed to capture is among the radio galaxy Cygnus A. Although Cygnus A is around 760-800 million light-years away, it is one of the brightest radio sources in the sky. At its centre may be a supermassive part such as the mass of around a pair of.5 billion Suns, actively accreting tremendous amounts of matter and shooting relativistic jets of plasma light-years into space from its poles.