LoRAX: LoRA eXpandable Networks for Continual Synthetic Image Attribution
This addresses the need for scalable attribution models to verify image authenticity and identify generative models, with incremental improvements in efficiency for real-world applications.
The paper tackles the problem of continual synthetic image attribution by proposing LoRAX, a parameter-efficient class incremental algorithm that adapts to novel generative models without full retraining, achieving competitive performance on the Continual Deepfake Detection benchmark while using less than 3% of trainable parameters per feature extractor.
As generative AI image technologies become more widespread and advanced, there is a growing need for strong attribution models. These models are crucial for verifying the authenticity of images and identifying the architecture of their originating generative models-key to maintaining media integrity. However, attribution models struggle to generalize to unseen models, and traditional fine-tuning methods for updating these models have shown to be impractical in real-world settings. To address these challenges, we propose LoRA eXpandable Networks (LoRAX), a parameter-efficient class incremental algorithm that adapts to novel generative image models without the need for full retraining. Our approach trains an extremely parameter-efficient feature extractor per continual learning task via Low Rank Adaptation. Each task-specific feature extractor learns distinct features while only requiring a small fraction of the parameters present in the underlying feature extractor's backbone model. Our extensive experimentation shows LoRAX outperforms or remains competitive with state-of-the-art class incremental learning algorithms on the Continual Deepfake Detection benchmark across all training scenarios and memory settings, while requiring less than 3% of the number of trainable parameters per feature extractor compared to the full-rank implementation. LoRAX code is available at: https://github.com/mit-ll/lorax_cil.