Combining Deep Learning and Super-Resolution Algorithms for Deep Fake Detection

Ivanov, Nikita S.; Arzhskov, Anton V.; Ivanenko, Vitaliy G.

doi:10.1109/eiconrus49466.2020.9039498

Cited by 22 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, there are fake photos based on AI-manipulated fabrication, which can be pasted on another photo to change the identity or to spread the wrong message. 45 4. Health effect: This technology has proved to be addictive sometimes to some people.…”

Section: Computer Vision: It Stores the Image For Future Reference An...mentioning

confidence: 99%

“…Because of this attack, sometimes it may show some wrong information and may damage the operating system Physical damage: This is a type of attack in which the AR will not work perfectly if the internal chip breaks for some reason. Deep fakes: It can be done through fake photos, videos, images, and so forth. Here, there are fake photos based on AI‐manipulated fabrication, which can be pasted on another photo to change the identity or to spread the wrong message 45 Health effect: This technology has proved to be addictive sometimes to some people.…”

Section: Background Conceptsmentioning

confidence: 99%

See 1 more Smart Citation

Safeguarding the IoT: Taxonomy, security solutions, and future research opportunities

Patel,

Kakkar

et al. 2023

Security and Privacy

View full text Add to dashboard Cite

With the advancement of innovative technologies, the Internet of Things (IoT) has become quite popular in various applications such as smart homes, smart cities, agriculture, healthcare, and so forth. However, the heterogeneity of IoT protocols can pose security challenges to wireless networks. Thus, we have presented a systematic review of IoT technologies such as ZigBee, Radio Frequency Identification (RFID), Bluetooth, WiFi, Ethernet, AR, embedded subscriber identification modules (E‐SIM), and smart sensors, along with their communication protocols, which are part of the IoT‐layered architecture. We have bifurcated the IoT‐layered architecture into the perception, network, and application layers. Furthermore, we have presented IoT security attacks associated with the perception, network, and application layers of the IoT‐layered architecture. Moreover, we have discussed several IoT security solutions, open issues, and research challenges dedicated to the security of IoT networks. IoT security solutions can provide secure and efficient data communication over wireless networks.

show abstract

Section: Computer Vision: It Stores the Image For Future Reference An...mentioning

confidence: 99%

Section: Background Conceptsmentioning

confidence: 99%

Safeguarding the IoT: Taxonomy, security solutions, and future research opportunities

Patel,

Kakkar

et al. 2023

Security and Privacy

View full text Add to dashboard Cite

show abstract

“…The work of Ivanov et al [44] focused on the classification of counterfeit content proposing a method based on deep learning and super-resolution algorithms to expose deepfakes based on the incompatibility between the different regions of the face and the head position.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

A Review of Deep Learning-based Approaches for Deepfake Content Detection

Passos,

Jodas,

Costa

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent advancements in deep learning generative models have raised concerns as they can create highly convincing counterfeit images and videos. This poses a threat to people's integrity and can lead to social instability. To address this issue, there is a pressing need to develop new computational models that can efficiently detect forged content and alert users to potential image and video manipulations. This paper presents a comprehensive review of recent studies for deepfake content detection using deep learning-based approaches. We aim to broaden the state-of-the-art research by systematically reviewing the different categories of fake content detection. Furthermore, we report the advantages and drawbacks of the examined works and future directions towards the issues and shortcomings still unsolved on deepfake detection.

show abstract

“…Various attempts have been made to find a solution to this problem. Visual artifacts, common among deep fakes [10], have been used frequently in solution strategies. The Deepfake Detection Challenge was developed in collaboration with META, Microsoft, and AWS on AI's Media Integrity Steering Committee and academics (DFDC).…”

Section: Introductionmentioning

confidence: 99%

A Performance Enhancement of Deepfake Video Detection through the use of a Hybrid CNN Deep Learning Model

Ikram

Priya

Chambial

et al. 2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

In the current era, many fake videos and images are created with the help of various software and new AI (Artificial Intelligence) technologies, which leave a few hints of manipulation. There are many unethical ways videos can be used to threaten, fight, or create panic among people. It is important to ensure that such methods are not used to create fake videos. An AI-based technique for the synthesis of human images is called Deep Fake. They are created by combining and superimposing existing videos onto the source videos. In this paper, a system is developed that uses a hybrid Convolutional Neural Network (CNN) consisting of InceptionResnet v2 and Xception to extract frame-level features. Experimental analysis is performed using the DFDC deep fake detection challenge on Kaggle. These deep learning-based methods are optimized to increase accuracy and decrease training time by using this dataset for training and testing. We achieved a precision of 0.985, a recall of 0.96, an f1-score of 0.98, and support of 0.968.

show abstract

Combining Deep Learning and Super-Resolution Algorithms for Deep Fake Detection

Cited by 22 publications

References 4 publications

Safeguarding the IoT: Taxonomy, security solutions, and future research opportunities

Safeguarding the IoT: Taxonomy, security solutions, and future research opportunities

A Review of Deep Learning-based Approaches for Deepfake Content Detection

A Performance Enhancement of Deepfake Video Detection through the use of a Hybrid CNN Deep Learning Model

Contact Info

Product

Resources

About