Dong Wenjie, Song Zhenbo, Zhang Zhenyuan, Lin Xuanzheng, Lu Jianfeng
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China.
School of AI and Advanced Computing, Xi'an Jiaotong-Liverpool University, Suzhou 215123, China.
Sensors (Basel). 2025 May 28;25(11):3386. doi: 10.3390/s25113386.
This study presents a novel defense framework to fortify Under-Display Camera (UDC) image restoration models against adversarial attacks, a previously underexplored vulnerability in this domain. Our research initially conducts an in-depth robustness evaluation of deep-learning-based UDC image restoration models by employing several white-box and black-box attacking methods. Following the assessment, we propose a two-stage approach integrating diffusion-based adversarial purification and efficient fine-tuning, uniquely designed to eliminate perturbations while retaining restoration fidelity. For the first time, we systematically evaluate seven state-of-the-art UDC models (such as DISCNet, UFormer, etc.) under diverse attacks (PGD, C&W, etc.), revealing severe performance degradation (DISCNet's PSNR drops from 35.24 to 15.16 under C&W attack). Our framework demonstrates significant improvements: after purification and fine-tuning, DISCNet's PSNR rebounds to 32.17 under PGD attack (vs. 30.17 without defense), while UFormer achieves a 19.71 PSNR under LPIPS-guided attacks (vs. 17.38 baseline). The effectiveness of our proposed approach is validated through extensive experiments, showing marked improvements in resilience against various adversarial attacks.
本研究提出了一种新颖的防御框架，以强化屏下摄像头（UDC）图像恢复模型抵御对抗攻击的能力，这是该领域此前未被充分探索的一个漏洞。我们的研究首先通过采用几种白盒和黑盒攻击方法，对基于深度学习的UDC图像恢复模型进行了深入的鲁棒性评估。评估之后，我们提出了一种两阶段方法，该方法整合了基于扩散的对抗净化和高效微调，其独特设计旨在消除扰动同时保持恢复保真度。我们首次在多种攻击（如PGD、C&W等）下系统地评估了七个最先进的UDC模型（如DISCNet、UFormer等），结果显示性能严重下降（在C&W攻击下，DISCNet的PSNR从35.24降至15.16）。我们的框架展示了显著的改进：经过净化和微调后，在PGD攻击下，DISCNet的PSNR回升至32.17（无防御时为30.17），而在LPIPS引导攻击下，UFormer的PSNR达到19.71（基线为17.38）。通过广泛的实验验证了我们提出的方法的有效性，结果表明在抵御各种对抗攻击方面有显著改进。
