Shangxi Wu

Shangxi Wu

Auto-generated profile, based on publicly available information

Shangxi Wu

School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
4 August 2020 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
JZJiaming Zhang
Jiaming Zhang
JSJitao Sang
Jitao Sang
KXKaiyuan Xu
Kaiyuan Xu
SWShangxi Wu
Shangxi Wu
XZXian Zhao
Xian Zhao
JYJian Yu
Jian Yu
Turing test was originally proposed to examine whether machine?s behavior is indistinguishable from a human. The most popular and practical Turing test is CAPTCHA, which is to discriminate algorithm from human by offering recognitionalike questions. The recent development of deep learning has signi?cantly advanced the capability of algorithm in solving CAPTCHA questions, forcing CAPTCHA designers to increase question complexity. Instead of designing questions dif?cult for both algorithm and human, this study attempts to employ the limitations of algorithm to design robust CAPTCHA questions easily solvable to human. Speci?cally, our data analysis observes that human and algorithm demonstrates different vulnerability to visual distortions: adversarial perturbation is signi?cantly annoying to algorithm yet friendly to human. We are motivated to employ adversarially perturbed images for robust CAPTCHA design in the context of character-based questions. Four modules of multi-target attack, ensemble adversarial training, image preprocessing differentiable approximation, and expectation are proposed to address the characteristics of character-based CAPTCHA cracking. Qualitative and quantitative experimental results demonstrate the effectiveness of the proposed solution. We hope this study can lead to the discussions around adversarial attack/defense in CAPTCHA design and also inspire the future attempts in employing algorithm limitation for practical usage.

27 February 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
SWShangxi Wu
Shangxi Wu
JSJitao Sang
Jitao Sang
KXKaiyuan Xu
Kaiyuan Xu
JZJiaming Zhang
Jiaming Zhang
JYJian Yu
Jian Yu
This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are more vulnerable to adversarial attacks; and (2) successful adversarial attacks lead to deviated and scattered activation map. Therefore, we use the mask method to design an attention-preserving loss and a contrast method to design a loss that makes the model’s attention rectification. Accordingly, an attention-based adversarial defense framework is designed, under which better adversarial training or stronger adversarial attacks can be performed through the above constraints. We hope the attention-related data analysis and defense solution in this study will shed some light on the mechanism behind the adversarial attack and also facilitate future adversarial defense/attack model design.

18 May 2023 in Information Sciences
Verified
Journal Article
Closed access
SWShangxi Wu
Shangxi Wu
QHQiuyang He
Qiuyang He
YZYi Zhang
Yi Zhang
DLDongyuan Lu
Dongyuan Lu
JSJitao Sang
Jitao Sang

18 October 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
SWShangxi Wu
Shangxi Wu
JSJitao Sang
Jitao Sang
KXKaiyan Xu
Kaiyan Xu
GZGuanhua Zheng
Guanhua Zheng
CXChangsheng Xu
Changsheng Xu
Adversarial examples provide an opportunity as well as impose a challenge for understanding image classification systems. Based on the analysis of the adversarial training solution—Adversarial Logits Pairing (ALP), we observed in this work that: (1) The inference of adversarially robust model tends to rely on fewer high-contribution features compared with vulnerable ones. (2) The training target of ALP does not fit well to a noticeable part of samples, where the logits pairing loss is overemphasized and obstructs minimizing the classification loss. Motivated by these observations, we design an Adaptive Adversarial Logits Pairing (AALP) solution by modifying the training process and training target of ALP. Specifically, AALP consists of an adaptive feature optimization module with Guided Dropout to systematically pursue fewer high-contribution features, and an adaptive sample weighting module by setting sample-specific training weights to balance between logits pairing loss and classification loss. The proposed AALP solution demonstrates superior defense performance on multiple datasets with extensive experiments.

6 March 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
SWShangxi Wu
Shangxi Wu
QHQiuyang He
Qiuyang He
JYJian Yu
Jian Yu
JSJitao Sang
Jitao Sang
With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing methods face challenges such as poor utilization of data or intricate training requirements. In this work, we found that the backdoor attack can construct an artificial bias similar to the model bias derived in standard training. Considering the strong adjustability of backdoor triggers, we are motivated to mitigate the model bias by carefully designing reverse artificial bias created from backdoor attack. Based on this, we propose a backdoor debiasing framework based on knowledge distillation, which effectively reduces the model bias from original data and minimizes security risks from the backdoor attack. The proposed solution is validated on both image and structured datasets, showing promising results. This work advances the understanding of backdoor attacks and highlights its potential for beneficial applications. The code for the study can be found at https://github.com/KirinNg/DwB.

1 January 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
SWShangxi Wu
Shangxi Wu
JXJinlin Xiao
Jinlin Xiao
JSJitao Sang
Jitao Sang