• Arsh Shaikh
• Hashim Deshmukh
• Rudein Karbari
• Mustafiz Siddiqui
• Prof. Rasika Thakare

With the widespread use of sophisticated manipulation techniques such as splicing, copy-move, and deepfake attacks, there is an urgent need for a comprehensive solution that combines computer vision, machine learning, and deep learning methodologies. The proposed framework leverages advanced feature extraction and convolutional neural networks to identify manipulated regions in images and videos. Additionally, a novel fusion of image and document forensics and video analysis extends the system's capabilities to detect forgeries in moving sequences. The system is designed to identify a spectrum of forgery types, including splicing, copy-move, and deepfake attacks. By demonstrating the effectiveness of machine learning in handling the changing issues of digital manipulation, this effort advances the field of forgery detection. The suggested framework highlights the potential of machine learning in bolstering the security and authenticity of multimedia content in the digital era and provides a workable and trustworthy method for detecting image and video forgeries.

Machine learning, Forgery Detection, CNN, ELA, SVM, PBFD, DRBL

"Image And Video Forgery Detection Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.b1-b6, January-2025, Available :http://www.jetir.org/papers/JETIR2501126.pdf

"Image And Video Forgery Detection Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppb1-b6, January-2025, Available at : http://www.jetir.org/papers/JETIR2501126.pdf