gan-detection

About Advanced AI-Generated Image Detection System using EfficientNetB7 with Custom Attention Mechanism. Developed for AICS 2025 (33rd Irish Conference on Artificial Intelligence and Cognitive Science). Detects deepfakes from GANs, Diffusion Models, and other generative AI.

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

🤖 AI-powered face authenticity detection using Deep Learning. Detect AI-generated faces (GAN, Stable Diffusion, Midjourney) with ~95% accuracy using MobileNetV2 + Transfer Learning. REST API with FastAPI.

Production-grade deepfake detection — 3-model ensemble (Xception + EfficientNet-B4 + ViT), calibrated confidence, forensics suite, REST API, and video AV-sync/identity tracking.

VeriScan: Comprehensive Cyber Security tool for image-based malware detection, sanitation, and authentication. Features neural CNN-GAN detection, SRNet steganalysis (ALASKA-1), and forensic authentication (ELA, Copy-Move, Noise Variance).

Upload an image, find out if it was made by AI, and see exactly why. Multi-branch forensic detector: FFT spectral analysis for GAN fingerprints, noise-residual statistics for diffusion, face symmetry checks, and EXIF/C2PA provenance, fused with damped log-odds pooling and explained in plain English by a vision model.