FastForensics: Efficient Two-Stream Design for Real-Time Image Manipulation Detection

TL;DR

FastForensics introduces a lightweight, two-stream neural network architecture that efficiently detects image manipulations in real-time by combining frequency-based global traces and fine-grained local features.

Contribution

The paper presents a novel two-stream design with wavelet-guided Transformer blocks and simple convolutions, enabling real-time image manipulation detection with high efficiency.

Findings

Achieves competitive accuracy with only ~8M parameters.

Demonstrates real-time performance suitable for portable devices.

Outperforms existing methods in efficiency while maintaining effectiveness.

Abstract

With the rise in popularity of portable devices, the spread of falsified media on social platforms has become rampant. This necessitates the timely identification of authentic content. However, most advanced detection methods are computationally heavy, hindering their real-time application. In this paper, we describe an efficient two-stream architecture for real-time image manipulation detection. Our method consists of two-stream branches targeting the cognitive and inspective perspectives. In the cognitive branch, we propose efficient wavelet-guided Transformer blocks to capture the global manipulation traces related to frequency. This block contains an interactive wavelet-guided self-attention module that integrates wavelet transformation with efficient attention design, interacting with the knowledge from the inspective branch. The inspective branch consists of simple convolutions that capture fine-grained traces and interact bidirectionally with Transformer blocks to provide mutual support. Our method is lightweight ($\sim$ 8M) but achieves competitive performance compared to many other counterparts, demonstrating its efficacy in image manipulation detection and its potential for portable integration.