Metadata encoding and extraction for AI-generated content

Audio watermarking system for deepfake detection and media authentication.

EfficientNet+MTCNN deepfake detection achieving 87% accuracy with 12.96% EER - Multi-modal video forensics for misinformation prevention

Materials for our paper: K. Apostolidis, J. Abesser, L. Cuccovillo, V. Mezaris, "Visual and audio scene classification for detecting discrepancies in video: a baseline method and experimental protocol", Proc. ACM Int. Workshop on Multimedia AI against Disinformation (MAD’24) at the ACM Int. Conf. on Multimedia Retrieval (ICMR’24)

Certified Human-Made content verification badges

Decentralized content platform with IPFS storage, multi-layer hash verification, and blockchain-based ownership proof

Cryptographic proof of video authenticity. Verify video origin and integrity using perceptual hashing and digital signatures to combat manipulated media.

ClipCert: Web-based video authenticity checker. Compare two videos frame-by-frame using advanced similarity algorithms (pHash/pixel comparison). Secure, client-side processing ensures data never leaves your browser.

Verify image authenticity instantly. Upload a photo and get an instant verdict on whether it's real or an AI-generated deepfake. Enterprise-grade accuracy with a simple, intuitive interface.

A robust Python CLI tool for precise plagiarism detection and text similarity analysis across documents. Utilizes advanced cosine similarity algorithms to identify intellectual overlap, ensuring content originality and integrity for academic, research, and professional applications.