Few-shot Forgery Detection via Guided Adversarial Interpolation

TL;DR

This paper introduces a novel few-shot forgery detection method called Guided Adversarial Interpolation (GAI), which leverages transferable distribution characteristics between forgery classes to improve detection of unseen forgeries, achieving state-of-the-art results.

Contribution

The paper proposes GAI, a new adversarial interpolation technique guided by a teacher network, and establishes a comprehensive benchmark for few-shot face forgery detection.

Findings

GAI outperforms existing methods on the benchmark

GAI is robust across different forgery approaches

The benchmark reveals coverage gaps among forgery techniques

Abstract

The increase in face manipulation models has led to a critical issue in society - the synthesis of realistic visual media. With the emergence of new forgery approaches at an unprecedented rate, existing forgery detection methods suffer from significant performance drops when applied to unseen novel forgery approaches. In this work, we address the few-shot forgery detection problem by 1) designing a comprehensive benchmark based on coverage analysis among various forgery approaches, and 2) proposing Guided Adversarial Interpolation (GAI). Our key insight is that there exist transferable distribution characteristics between majority and minority forgery classes1. Specifically, we enhance the discriminative ability against novel forgery approaches via adversarially interpolating the forgery artifacts of the minority samples to the majority samples under the guidance of a teacher network. Unlike the standard re-balancing method which usually results in over-fitting to minority classes, our method simultaneously takes account of the diversity of majority information as well as the significance of minority information. Extensive experiments demonstrate that our GAI achieves state-of-the-art performances on the established few-shot forgery detection benchmark. Notably, our method is also validated to be robust to choices of majority and minority forgery approaches. The formal publication version is available in Pattern Recognition.