AIFIND: Artifact-Aware Interpreting Fine-Grained Alignment for Incremental Face Forgery Detection
For face forgery detection systems that must adapt to new forgery types over time, AIFIND provides a method to mitigate forgetting without relying on data replay.
AIFIND addresses catastrophic forgetting in incremental face forgery detection by using artifact-driven semantic anchors to stabilize feature space, achieving superior performance across multiple incremental protocols.
As forgery types continue to emerge consistently, Incremental Face Forgery Detection (IFFD) has become a crucial paradigm. However, existing methods typically rely on data replay or coarse binary supervision, which fails to explicitly constrain the feature space, leading to severe feature drift and catastrophic forgetting. To address this, we propose AIFIND, Artifact-Aware Interpreting Fine-Grained Alignment for Incremental Face Forgery Detection, which leverages semantic anchors to stabilize incremental learning. We design the Artifact-Driven Semantic Prior Generator to instantiate invariant semantic anchors, establishing a fixed coordinate system from low-level artifact cues. These anchors are injected into the image encoder via Artifact-Probe Attention, which explicitly constrains volatile visual features to align with stable semantic anchors. Adaptive Decision Harmonizer harmonizes the classifiers by preserving angular relationships of semantic anchors, maintaining geometric consistency across tasks. Extensive experiments on multiple incremental protocols validate the superiority of AIFIND.