Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models

• URL: http://arxiv.org/abs/2509.00820v1
• Date: Sun, 31 Aug 2025 12:35:12 GMT
• Title: Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
• Authors: Zhenhua Xu, Zhaokun Yan, Binhan Xu, Xin Tong, Haitao Xu, Yourong Chen, Meng Han,
• Abstract summary: LoRA-FP is a lightweight, plug-and-play framework that embeds backdoor fingerprints into LoRA adapters through constrained fine-tuning.<n> Experimental results demonstrate that LoRA-FP not only significantly reduces computational overhead compared to conventional approaches.
• Score: 19.771871663634737
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid advancement of large language models (LLMs), safeguarding intellectual property (IP) has become increasingly critical. To address the challenges of high costs and potential contamination in fingerprint integration, we propose LoRA-FP, a lightweight, plug-and-play framework that embeds backdoor fingerprints into LoRA adapters through constrained fine-tuning. This design enables seamless fingerprint transplantation via parameter fusion, eliminating the need for full-parameter updates while preserving model integrity. Experimental results demonstrate that LoRA-FP not only significantly reduces computational overhead compared to conventional approaches but also achieves superior robustness across diverse scenarios, including incremental training and model fusion. Our code and datasets are publicly available at https://github.com/Xuzhenhua55/LoRA-FP.

Related papers

• Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration [56.074760766965085]
  PRISM achieves a dynamics-aware framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.<n>Our findings suggest that disentangling data based on internal optimization regimes is crucial for scalable and robust agent alignment.
  arXiv  Detail & Related papers  (2026-01-12T05:43:20Z)
• Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning [15.880906462267935]
  VILA is a novel unlearning framework that explicitly considers the assumptions overlooked in FILA.<n>We set new state-of-the-art performance on benchmarks including TOFU, WMDP, and MUSE.
  arXiv  Detail & Related papers  (2025-08-29T01:45:09Z)
• EditMF: Drawing an Invisible Fingerprint for Your Large Language Models [11.691985114214162]
  EditMF is a training-free fingerprinting paradigm that achieves highly imperceptible fingerprint embedding with minimal computational overhead.<n>We show that EditMF combines high imperceptibility with negligible model's performance loss, while delivering robustness far beyond LoRA-based fingerprinting.
  arXiv  Detail & Related papers  (2025-08-12T10:52:48Z)
• FPEdit: Robust LLM Fingerprinting through Localized Knowledge Editing [9.351260848685229]
  FPEdit is a novel knowledge-editing framework that injects semantically coherent natural language fingerprints by modifying a sparse subset of model weights.<n> experiments show that FPEdit achieves $95$-$100%$ fingerprint retention.<n> FPEdit can embed 10 fingerprint pairs into LLaMA2-7B in under 10 minutes using less than 32 GB of GPU memory.
  arXiv  Detail & Related papers  (2025-08-04T06:00:22Z)
• Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation [158.37640586809187]
  Restoring any degraded image efficiently via just one model has become increasingly significant.<n>Our approach, termed AnyIR, takes a unified path that leverages inherent similarity across various degradations.<n>To fuse the degradation awareness and the contextualized attention, a spatial-frequency parallel fusion strategy is proposed.
  arXiv  Detail & Related papers  (2025-04-19T09:54:46Z)
• PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning [8.61459170031022]
  This paper introduces a novel security threat to FedPEFT, termed PEFT-as-an-Attack (PaaA)<n>Our evaluation of PaaA reveals that with less than 1% of the model's parameters set as trainable, and a small subset of clients acting maliciously, the attack achieves an approximate 80% attack success rate using representative PEFT methods such as LoRA.<n>Our results underscore the urgent need for more effective defense mechanisms that simultaneously ensure security and maintain the performance of the FedPEFT paradigm.
  arXiv  Detail & Related papers  (2024-11-28T19:05:01Z)
• Towards Resource-Efficient Federated Learning in Industrial IoT for Multivariate Time Series Analysis [50.18156030818883]
  Anomaly and missing data constitute a thorny problem in industrial applications. Deep learning enabled anomaly detection has emerged as a critical direction. The data collected in edge devices contain user privacy.
  arXiv  Detail & Related papers  (2024-11-06T15:38:31Z)
• LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration [62.3751291442432]
  We propose LoRA-IR, a flexible framework that dynamically leverages compact low-rank experts to facilitate efficient all-in-one image restoration. LoRA-IR consists of two training stages: degradation-guided pre-training and parameter-efficient fine-tuning. Experiments demonstrate that LoRA-IR achieves SOTA performance across 14 IR tasks and 29 benchmarks, while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2024-10-20T13:00:24Z)
• Restore Anything Model via Efficient Degradation Adaptation [129.38475243424563]
  RAM takes a unified path that leverages inherent similarities across various degradations to enable efficient and comprehensive restoration.<n> RAM's SOTA performance confirms RAM's SOTA performance, reducing model complexity by approximately 82% in trainable parameters and 85% in FLOPs.
  arXiv  Detail & Related papers  (2024-07-18T10:26:53Z)
• FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers [72.83770102062141]
  Vision Transformer (ViT) model has gradually become mainstream in various computer vision tasks.<n>Existing large models tend to prioritize performance during training, potentially neglecting the robustness.<n>We develop novel LNLoRA module, incorporating a learnable layer normalization before the conventional LoRA module.<n>We propose the FullLoRA framework by integrating the learnable LNLoRA modules into all key components of ViT-based models.
  arXiv  Detail & Related papers  (2024-01-03T14:08:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.