Xiaodan Li

Xiaodan Li

Auto-generated profile, based on publicly available information

Xiaodan Li

Alibaba Group, Hangzhou, China

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
29 March 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YZYao Zhu
Yao Zhu
YCYuefeng Chen
Yuefeng Chen
XLXiaodan Li
Xiaodan Li
RZRong Zhang
Rong Zhang
XTXiang Tian
Xiang Tian
YCYaowu Chen
Yaowu Chen
With the development of deep learning technology, the facial manipulation system has become powerful and easy to use. Such systems can modify the attributes of the given facial images, such as hair color, gender, and age. Malicious applications of such systems pose a serious threat to individuals’ privacy and reputation. Existing studies have proposed various approaches to protect images against facial manipulations. Passive defense methods aim to detect whether the face is real or fake, which works for posterior forensics but can not prevent malicious manipulation. Initiative defense methods protect images upfront by injecting adversarial perturbations into images to disrupt facial manipulation systems but can not identify whether the image is fake. To address the limitation of existing methods, we propose a novel two-tier protection method named Information-containing Adversarial Perturbation (IAP), which provides more comprehensive protection for facial images. We use an encoder to map a facial image and its identity message to a cross-model adversarial example which can disrupt multiple facial manipulation systems to achieve initiative protection. Recovering the message in adversarial examples with a decoder serves passive protection, contributing to provenance tracking and fake image detection. We introduce a feature-level correlation measurement that is more suitable to measure the difference between the facial images than the commonly used mean squared error. Moreover, we propose a spectral diffusion method to spread messages to different frequency channels, thereby improving the robustness of the message against facial manipulation. Extensive experimental results demonstrate that our proposed IAP can recover the messages from the adversarial examples with high average accuracy and effectively disrupt the facial manipulation systems.

22 October 2022
Verified
Book Chapter
Closed access
PDF file
LSLuchuan Song
Luchuan Song
ZFZheng Fang
Zheng Fang
XLXiaodan Li
Xiaodan Li
XDXiaoyi Dong
Xiaoyi Dong
ZJZhenchao Jin
Zhenchao Jin
SLSiwei Lyu
Siwei Lyu

26 October 2023
Verified
Conference Paper
Open access
HLHonggu Liu
Honggu Liu
XLXiaodan Li
Xiaodan Li
WZWenbo Zhou
Wenbo Zhou
HFHan Fang
Han Fang
PBPaolo Bestagini
Paolo Bestagini
HXHui Xue
Hui Xue
The rapid progress of the DeepFake technique has caused severe privacy problems. Thus protecting facial data against DeepFake becomes an urgent requirement. Face protection can be regarded as a bidirectional process: Face-out-detection (FOD) and Face-in-forensics (FIF). For FOD, the detectability should be satisfied when using the protected face to replace other faces. For FIF, traceability should be guaranteed when the protected face is replaced by others. For this, we propose a Bidirectional Facial-data Protection Framework (BiFPro) to protect face data comprehensively. This framework is composed of three main parts: Watermarking embedding, Face-out-detection (FOD) and Face-in-forensics (FIF). For the FOD case, we ensure the vulnerability of the original face by embedding fragile watermarking. Once the protected facial image is used to replace other faces, the watermarking information will be corrupted in the synthesized face images which can be used to detect the authenticity of the protected facial images. As for the FIF case, we guarantee the traceability of the protected face image by embedding robust watermarking, with which the fake faces can be traced with the reserved watermarking even after the face is swapped. Experimental results demonstrate that our proposed BiFPro could generate the watermarking which is fragile to FOD and at the same time robust to FIF with an average watermark extraction success rate reaching more than 95% when defending against the four advanced DeepFake techniques. Finally, we hope this work can encourage more initiative countermeasures against DeepFake.

22 May 2024 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YZYao Zhu
Yao Zhu
YCYuefeng Chen
Yuefeng Chen
XLXiaodan Li
Xiaodan Li
RZRong Zhang
Rong Zhang
HXHui Xue
Hui Xue
YCYaowu Chen
Yaowu Chen

7 July 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
CZCong Zhang
Cong Zhang
SWShuhui Wang
Shuhui Wang
XLXiaodan Li
Xiaodan Li
YZYao Zhu
Yao Zhu
HQHongang Qi
Hongang Qi
QHQingming Huang
Qingming Huang
While Vision-Language Models (VLMs) based on large-scale models have shown revolutionary advancements across various vision-language tasks, research on improving VLM robustness remains underexplored. Existing studies primarily focus on attacking VLM after the pretrained visual or textual encoders, typically requiring obvious noise or long inference time. In this study, we look into VLM structure and highlight alignment module’s role as a protective filter that enhances VLM robustness against various perturbations. Motivated by these insights, we investigate VLM from both user and model developer perspectives and introduce the alignment perturbation strategy, which consists of multimodal, visual, and textual perturbations. Multimodal perturbation aims to achieve targeted textual output generation and is further utilized to enhance VLM robustness. Minimal perturbations to visual or textual inputs can lead to significant changes in the overall output of VLMs, revealing their sensitivity to both visual and textual input variations. Building on the alignment perturbation strategy, we propose alignment robust training, which efficiently improves VLM robustness by finetuning the parameters of alignment module without excessive resource consumption. Experiment results across various tasks and models demonstrate the effectiveness of the proposed alignment perturbation and alignment robust training. These methods deepen the understanding of VLM robustness, allowing for secure and reliable deployment towards diverse real-world scenarios. Codes are available at https://github.com/zhangconghhh/RobustVLMs.

7 October 2025 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
XLXiaodan Li
Xiaodan Li
YZYao Zhu
Yao Zhu
YCYuefeng Chen
Yuefeng Chen
CCCen Chen
Cen Chen
JGJianmei Guo
Jianmei Guo
SWShuhui Wang
Shuhui Wang
In recent years, massive datasets have significantly driven the advancement of visual learning such as multi-modal large model at the expense of high computational costs and extensive storage requirements. Dataset distillation (DD) aims to address this challenge by learning a small synthetic dataset such that a model trained on it can achieve a test performance comparable to that of the model trained on the original dataset. This task can be formulated as a bi-level learning problem where the outer loop optimizes the learned dataset and the inner loop updates the model parameters based on the distilled data. Different from previous studies that focus primarily on optimizing the inner loop in this bi-level problem, we delve into the task of dataset distillation from the perspective of sample cruciality. We find that discarding easy samples and keeping the hard ones that are difficult to be represented by the learned synthetic samples in the outer loop can be beneficial for DD. Motivated by this observation, we further develop an Infinite Semantic Augmentation (ISA) based dataset distillation algorithm, which discards some easier samples and implicitly enriches harder ones in the semantic space through continuous interpolation between two target feature vectors. Through detailed mathematical derivation, the joint contribution to the training loss of all interpolated feature points is formed into an analytical closed-form solution of an integral that can be optimized with almost no extra computational cost. Experimental results on several benchmark datasets demonstrate the effectiveness of our approach in reducing the dataset size while preserving the accuracy of the model. Furthermore, we show that high-quality distilled data can also benefit downstream applications, such as continual learning and membership inference defense. The code is available at https://github.com/fiona-lxd/ISA.git.