DejAIvu: Identifying and Explaining AI Art on the Web in Real-Time with Saliency Maps
Jocelyn Dzuong
TL;DR
DejAIvu addresses the need for transparent AI-generated image detection on the web by delivering real-time, in-browser inference with saliency-based explanations. It uses an ONNX-optimized CNN deployed inside a Chrome extension, enabling privacy-preserving, low-latency detection without server-side computation and overlays gradient-based saliency maps to highlight influential regions. The model is trained on a large curated dataset of AI-generated and human artworks (~271,993 samples) with a $256×256$ preprocessing pipeline and a log-ratio bias to mitigate class imbalance. Demonstrations on live pages like Google Images illustrate practical utility for AI image accountability and transparency, making it a viable tool for readers, platforms, and users to verify authenticity.
Abstract
The recent surge in advanced generative models, such as diffusion models and generative adversarial networks (GANs), has led to an alarming rise in AI-generated images across various domains on the web. While such technologies offer benefits such as democratizing artistic creation, they also pose challenges in misinformation, digital forgery, and authenticity verification. Additionally, the uncredited use of AI-generated images in media and marketing has sparked significant backlash from online communities. In response to this, we introduce DejAIvu, a Chrome Web extension that combines real-time AI-generated image detection with saliency-based explainability while users browse the web. Using an ONNX-optimized deep learning model, DejAIvu automatically analyzes images on websites such as Google Images, identifies AI-generated content using model inference, and overlays a saliency heatmap to highlight AI-related artifacts. Our approach integrates efficient in-browser inference, gradient-based saliency analysis, and a seamless user experience, ensuring that AI detection is both transparent and interpretable. We also evaluate DejAIvu across multiple pretrained architectures and benchmark datasets, demonstrating high accuracy and low latency, making it a practical and deployable tool for enhancing AI image accountability. The code for this system can be found at https://github.com/Noodulz/dejAIvu.