{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lorax-lora-expandable-networks-for-continual","title":"LoRAX: LoRA eXpandable Networks for Continual Synthetic Image Attribution","arxiv_id":"2504.08149","date":"2025-04-10","proceeding":null,"authors":["Danielle Sullivan-Pao","Nicole Tian","Pooya Khorrami"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2504.08149v1","url_pdf":"https://arxiv.org/pdf/2504.08149v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lorax-lora-expandable-networks-for-continual","repo_url":"https://github.com/mit-ll/lorax_cil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"deepfake-detection","task_name":"DeepFake Detection"},{"task_slug":"face-swapping","task_name":"Face Swapping"},{"task_slug":"image-attribution","task_name":"Image Attribution"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"synthetic-image-attribution","task_name":"Synthetic Image Attribution"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.08149","atlas_url":"https://app.syntology.ai/?focus=2504.08149","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}