This paper presents the SparkShield system submitted to ArA-DF 2026 Track 2, which focuses on robust Arabic speech deepfake detection under realistic acoustic degradations. To improve robustness, we apply a comprehensive augmentation pipeline involving background noise, reverberation, codec compression, reencoding, and volume perturbation. Our system consists of three parallel subsystems using XLS-R models with 300M, 1B, and 2B parameters as front-end feature extractors. Each subsystem employs learnable layer-wise feature fusion, followed by a Multi-kernel gated Convolution (MultiConv) module and Multi-Head Attention Pooling (MHAP) for utterance-level spoof detection. The output logits of the three independently trained subsystems are finally fused. The proposed system achieves an EER of 0.6575% on the evaluation set and ranks first in ArA-DF 2026 Track 2.

With the rapid development of large language models (LLMs), protecting intellectual property (IP) has become increasingly crucial. To tackle high costs and potential contamination in fingerprint integration, we propose LoRA-FP, a lightweight plug-and-play framework that encodes backdoor fingerprints into LoRA adapters via constrained fine-tuning. This enables seamless fingerprint transplantation through parameter fusion, eliminating full-parameter updates while maintaining integrity. Experiments demonstrate that LoRA-FP achieves superior robustness against various scenarios like incremental training and model fusion, while significantly reducing computational overhead compared to traditional approaches.