Yujia Liu

Dr. Yujia Liu


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 May 2025 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
Yujia LiuYujia Liu
Yujia Liu
CYChenxi Yang
Chenxi Yang
Dingquan LiDingquan Li
Dingquan Li
TJTingting Jiang
Tingting Jiang
THTiejun Huang
Tiejun Huang

9 April 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
Yujia LiuYujia Liu
Yujia Liu
CYChenxi Yang
Chenxi Yang
ZYzhaofei yu
zhaofei yu
THTiejun Huang
Tiejun Huang
No-Reference Image Quality Assessment (NR-IQA) plays a crucial role in various real-world applications by predicting image quality scores without the need for reference images. Despite the impressive performance of deep learning-based NR-IQA models, they remain vulnerable to adversarial attacks, which introduce imperceptible perturbations to input images, causing significant changes in predicted scores. In this study, we explore the use of simple JPEG compression techniques, as well as their combination with norm regularization training, to defend against these adversarial attacks. Our results demonstrate that image compression is an effective method to enhance model robustness, and it can further improve the robustness of NR-IQA models when combined with appropriate training strategies. Since excessive compression may reduce performance on clean images, it is essential to strike a balance. This work provides valuable insights into designing effective image compression methods for NR-IQA models.

24 April 2024 in arXiv
Verified
Preprint
Open access
PDF file
CYChenxi Yang
Chenxi Yang
Yujia LiuYujia Liu
Yujia Liu
Dingquan LiDingquan Li
Dingquan Li
YZYan Zhong
Yan Zhong
TJTingting Jiang
Tingting Jiang
Deep neural networks have demonstrated impressive success in No-Reference Image Quality Assessment (NR-IQA). However, recent researches highlight the vulnerability of NR-IQA models to subtle adversarial perturbations, leading to inconsistencies between model predictions and subjective ratings. Current adversarial attacks, however, focus on perturbing predicted scores of individual images, neglecting the crucial aspect of inter-score correlation relationships within an entire image set. Meanwhile, it is important to note that the correlation, like ranking correlation, plays a significant role in NR-IQA tasks. To comprehensively explore the robustness of NR-IQA models, we introduce a new framework of correlation-error-based attacks that perturb both the correlation within an image set and score changes on individual images. Our research primarily focuses on ranking-related correlation metrics like Spearman's Rank-Order Correlation Coefficient (SROCC) and prediction error-related metrics like Mean Squared Error (MSE). As an instantiation, we propose a practical two-stage SROCC-MSE-Attack (SMA) that initially optimizes target attack scores for the entire image set and then generates adversarial examples guided by these scores. Experimental results demonstrate that our SMA method not only significantly disrupts the SROCC to negative values but also maintains a considerable change in the scores of individual images. Meanwhile, it exhibits state-of-the-art performance across metrics with different categories. Our method provides a new perspective on the robustness of NR-IQA models.

29 January 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
Yujia LiuYujia Liu
Yujia Liu
Dingquan LiDingquan Li
Dingquan Li
ZLZhixuan Li
Zhixuan Li
THTiejun Huang
Tiejun Huang
No-Reference Image Quality Assessment (NR-IQA) models play an important role in various real-world applications. Recently, adversarial attacks against NR-IQA models have attracted increasing attention, as they provide valuable insights for revealing model vulnerabilities and guiding robust system design. Some effective attacks have been proposed against NR-IQA models in white-box settings, where the attacker has full access to the target model. However, these attacks often suffer from poor transferability to unknown target models in more realistic black-box scenarios, where the target model is inaccessible. This work makes the first attempt to address the challenge of low transferability in attacking NR-IQA models by proposing a transferable Signed Ensemble Gaussian black-box Attack (SEGA). The main idea is to approximate the gradient of the target model by applying Gaussian smoothing to source models and ensembling their smoothed gradients. To ensure the imperceptibility of adversarial perturbations, SEGA further removes inappropriate perturbations using a specially designed perturbation filter mask. Experimental results demonstrate the superior transferability of SEGA, validating its effectiveness in enabling successful transfer-based black-box attacks against NR-IQA models.

15 March 2019
Verified
Book Chapter
Closed access
PDF file
LZLi-Ming Zheng
Li-Ming Zheng
WLWen-Feng Long
Wen-Feng Long
Yujia LiuYujia Liu
Yujia Liu
WSWei-Dong Sun
Wei-Dong Sun

8 April 2022
Verified
Conference Paper
Open access
PDF file
NSNuoxing Shang
Nuoxing Shang
Yujia LiuYujia Liu
Yujia Liu
ZLZewei Lin
Zewei Lin
In this paper, the researcher creates a model for trinomial tree option pricing with multiple time periods by using Monte-Carlo estimation and Python. However, the delta hedging strategy needs to be improved to minimize the replication error.