Deepfake attacks: Generation, detection, datasets, challenges, and research directions

A Naitali, M Ridouani, F Salahdine, N Kaabouch - Computers, 2023 - mdpi.com
Recent years have seen a substantial increase in interest in deepfakes, a fast-developing
field at the nexus of artificial intelligence and multimedia. These artificial media creations …

An automatic and efficient malware traffic classification method for secure Internet of Things

X Zhang, L Hao, G Gui, Y Wang… - IEEE Internet of …, 2023 - ieeexplore.ieee.org
Malware traffic classification (MTC) plays an important role in cyber security and network
resource management for the secure Internet of Things (IoT). Many deep learning (DL) …

Multimedia datasets for anomaly detection: a review

P Kumari, AK Bedi, M Saini - Multimedia Tools and Applications, 2024 - Springer
Multimedia anomaly datasets play a crucial role in automated surveillance. They have a
wide range of applications expanding from outlier objects/situation detection to the detection …

Parents and children: Distinguishing multimodal deepfakes from natural images

R Amoroso, D Morelli, M Cornia, L Baraldi… - arXiv preprint arXiv …, 2023 - arxiv.org
Recent advancements in diffusion models have enabled the generation of realistic
deepfakes by writing textual prompts in natural language. While these models have …

Generation and detection of manipulated multimodal audiovisual content: Advances, trends and open challenges

H Liz-Lopez, M Keita, A Taleb-Ahmed, A Hadid… - Information …, 2024 - Elsevier
Generative deep learning techniques have invaded the public discourse recently. Despite
the advantages, the applications to disinformation are concerning as the counter-measures …

Pvass-mdd: predictive visual-audio alignment self-supervision for multimodal deepfake detection

Y Yu, X Liu, R Ni, S Yang, Y Zhao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Deepfake techniques can forge the visual or audio signals in the video, which leads to
inconsistencies between visual and audio (VA) signals. Therefore, multimodal detection …

Integrating audio-visual features for multimodal deepfake detection

S Muppalla, S Jia, S Lyu - 2023 IEEE MIT Undergraduate …, 2023 - ieeexplore.ieee.org
Deepfakes are AI-generated media in which an image or video has been digitally modified.
The advancements made in deepfake technology have led to privacy and security issues …

[HTML][HTML] Glitch in the matrix: A large scale benchmark for content driven audio–visual forgery detection and localization

Z Cai, S Ghosh, A Dhall, T Gedeon, K Stefanov… - Computer Vision and …, 2023 - Elsevier
Most deepfake detection methods focus on detecting spatial and/or spatio-temporal changes
in facial attributes and are centered around the binary classification task of detecting …

Audio multi-view spoofing detection framework based on audio-text-emotion correlations

J Wu, Q Yin, Z Sheng, W Lu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
In recent years, audio spoofing detection has received widespread attention for protecting
personal privacy and social security. Despite the significant progress achieved in audio …

Deepfake generation and detection: A benchmark and survey

G Pei, J Zhang, M Hu, G Zhai, C Wang, Z Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
In addition to the advancements in deepfake generation, corresponding detection
technologies need to continuously evolve to regulate the potential misuse of deepfakes …