Danni Xu

Danni Xu

Auto-generated profile, based on publicly available information

Danni Xu

School of Computing, National University of Singapore, Singapore, Singapore

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
DXDanni Xu
Danni Xu
SFShaojing Fan
Shaojing Fan
MKMohan Kankanhalli
Mohan Kankanhalli
Misinformation has been a persistent and harmful phenomenon affecting our society in various ways, including individuals' physical health and economic stability. With the rise of short video platforms and related applications, the spread of multi-modal misinformation, encompassing images, texts, audios, and videos have exacerbated these concerns. The introduction of generative AI models like ChatGPT and Stable Diffusion has further complicated matters, giving rise to Artificial Intelligence Generated Content (AIGC) and presenting new challenges in detecting and mitigating misinformation. Consequently, traditional approaches to misinformation detection and intervention have become inadequate in this evolving landscape. This paper explores the challenges posed by AIGC in the context of misinformation. It examines the issue from psychological and societal perspectives, and explores the subtle manipulation traces found in AIGC at signal, perceptual, semantic, and human levels. By scrutinizing manipulation traces such as signal manipulation, semantic inconsistencies, logical incoherence, and psychological strategies, our objective is to tackle AI-generated misinformation and provide a conceptual design of systematic explainable solution. Ultimately, we aim for this paper to contribute valuable insights into combating misinformation, particularly in the era of AIGC.

26 October 2023
Verified
Conference Paper
Open access
ZZZhuo Zhou
Zhuo Zhou
WLWenxuan Liu
Wenxuan Liu
DXDanni Xu
Danni Xu
Zheng WangZheng Wang
Zheng Wang
Jian ZhaoJian Zhao
Jian Zhao
This paper introduces a new and challenging Hidden Intention Discovery (HID) task. Unlike existing intention recognition tasks, which are based on obvious visual representations to identify common intentions for normal behavior, HID focuses on discovering hidden intentions when humans try to hide their intentions for abnormal behavior. HID presents a unique challenge in that hidden intentions lack the obvious visual representations to distinguish them from normal intentions. Fortunately, from a sociological and psychological perspective, we find that the difference between hidden and normal intentions can be reasoned from multiple micro-behaviors, such as gaze, attention, and facial expressions. Therefore, we first discover the relationship between micro-behavior and hidden intentions and use graph structure to reason about hidden intentions. To facilitate research in the field of HID, we also constructed a seminal dataset containing a hidden intention annotation of a typical theft scenario for HID. Extensive experiments show that the proposed network improves performance on the HID task by 9.9% over the state-of-the-art method SBP.

28 October 2024
Verified
Conference Paper
Open access
JWJie Wu
Jie Wu
DXDanni Xu
Danni Xu
WLWenxuan Liu
Wenxuan Liu
JZJoey Zhou
Joey Zhou
YOYew Ong
Yew Ong
Zheng WangZheng Wang
Zheng Wang
The prevalence of fake news, in both visual and textual forms, has become a critical and urgent issue. Existing multi-modal fake news detection methods aim to improve detection performance by leveraging information from different modalities and integrating it into a unified, comprehensive representation. However, challenges arise when different modalities hold conflicting beliefs. This suggests the existence of information asymmetry and imbalance between various modalities, which has not been adequately recognized in previous work. In this regard, focusing on the uncertainty of each modality facilitates a more nuanced understanding of its reliability and informativeness. In this work, we distinguish among uni-modal information sources through accurate estimation of their decision uncertainty, employing this uncertainty as a confidence measure and indicator of information imbalance to guide feature fusion. In particular, 1) To provide accurate uncertainty estimation, an uncertainty learning method based on the Dirichlet distribution is employed; 2) To fuse multi-modal information, uncertainty is used as a guiding factor to govern the contribution of each modality. Extensive experiments on two real-world datasets Weibo and Twitter validate the effectiveness of the proposed method.

27 October 2025
Verified
Conference Paper
Open access
BYBingjian Yang
Bingjian Yang
DXDanni Xu
Danni Xu
KNKaipeng Niu
Kaipeng Niu
WLWenxuan Liu
Wenxuan Liu
Zheng WangZheng Wang
Zheng Wang
MKMohan Kankanhalli
Mohan Kankanhalli

27 October 2025
Verified
Conference Paper
Open access
RZRuixu Zhang
Ruixu Zhang
YWYuran Wang
Yuran Wang
XHXinyi Hu
Xinyi Hu
CMChaoyu Mai
Chaoyu Mai
WLWenxuan Liu
Wenxuan Liu
Zheng WangZheng Wang
Zheng Wang

8 June 2022 in Frontiers in Physics
Verified
Journal Article
Open access
YTYuanhong Tao
Yuanhong Tao
XYXin-Lei Yong
Xin-Lei Yong
YBYa-Ru Bai
Ya-Ru Bai
DXDan-Ni Xu
Dan-Ni Xu
SWShuhui Wu
Shuhui Wu
We systematically study the constructions of unextendible entangled bases with a fixed Schmidt number k (UEBk) in a bipartite system Cd⊗Cd′. Motivated by the methods of [J. Phys. A 52 : 375,303, 2019], we construct (dd’ − v)-member UEBks in Cd⊗Cd′ by using generalized weighing matrices and thus generalize the results of [arXiv: 1909.10043, 2020]. We also present the corresponding expressions of our constructions and graphically illustrate UEB3s in C5⊗C6 and C6⊗C6.