no code implementations • 26 May 2024 • Tianyun Yang, Juan Cao, Chang Xu
Experimental results show a significant enhancement in our model's ability to resist adversarial inputs, achieving nearly a 40% improvement in erasing the NSFW content and a 30% improvement in erasing artwork style.
no code implementations • 26 May 2024 • Qiong Nan, Qiang Sheng, Juan Cao, Beizhe Hu, Danding Wang, Jintao Li
Without obtaining the comments from the ``silent'' users, the perceived opinions may be incomplete, subsequently affecting news veracity judgment.
1 code implementation • 29 Mar 2024 • You Wu, Kean Liu, Xiaoyue Mi, Fan Tang, Juan Cao, Jintao Li
Extensive experiments on various kinds of visual attributes with SOTA personalization methods show the ability of the proposed method to mimic target visual appearance in novel contexts, thus improving the controllability and flexibility of personalization.
no code implementations • 28 Mar 2024 • Yu Xu, Fan Tang, Juan Cao, Yuxin Zhang, Oliver Deussen, WeiMing Dong, Jintao Li, Tong-Yee Lee
Based on the adapters broken apart for separate training content and style, we then make the entity parameter space by reconstructing the content and style PLPs matrices, followed by fine-tuning the combined adapter to generate the target object with the desired appearance.
1 code implementation • 25 Mar 2024 • Ziyao Huang, Fan Tang, Yong Zhang, Xiaodong Cun, Juan Cao, Jintao Li, Tong-Yee Lee
We adopt a two-stage training strategy for the diffusion model, effectively binding movements with specific appearances.
1 code implementation • 14 Feb 2024 • Yuhui Shi, Qiang Sheng, Juan Cao, Hao Mi, Beizhe Hu, Danding Wang
With the rapidly increasing application of large language models (LLMs), their abuse has caused many undesirable societal problems such as fake news, academic dishonesty, and information pollution.
1 code implementation • 27 Dec 2023 • Zhengjia Wang, Danding Wang, Qiang Sheng, Juan Cao, Silong Su, Yifan Sun, Beizhe Hu, Siyuan Ma
As the disruptive changes in the media economy and the proliferation of alternative news media outlets, news intent has progressively deviated from ethical standards that serve the public interest.
no code implementations • 29 Nov 2023 • Xiaoyue Mi, Fan Tang, Yepeng Weng, Danding Wang, Juan Cao, Sheng Tang, Peng Li, Yang Liu
Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i. e., accuracy on natural samples has reduced significantly.
no code implementations • 29 Nov 2023 • Xiaoyue Mi, Fan Tang, Zonghan Yang, Danding Wang, Juan Cao, Peng Li, Yang Liu
Despite the remarkable advances that have been made in continual learning, the adversarial vulnerability of such methods has not been fully discussed.
no code implementations • 29 Nov 2023 • Zhihao Sun, Haipeng Fang, Xinying Zhao, Danding Wang, Juan Cao
However, the lack of comprehensive dataset containing images edited with abundant and advanced generative regional editing methods poses a substantial obstacle to the advancement of corresponding detection methods.
no code implementations • 20 Oct 2023 • Haipeng Fang, Zhihao Sun, Ziyao Huang, Fan Tang, Juan Cao, Sheng Tang
The advancement of generative AI has extended to the realm of Human Dance Generation, demonstrating superior generative capacities.
no code implementations • 16 Oct 2023 • Qiong Nan, Qiang Sheng, Juan Cao, Yongchun Zhu, Danding Wang, Guang Yang, Jintao Li, Kai Shu
To break such a dilemma, a feasible but not well-studied solution is to leverage social contexts (e. g., comments) from historical news for training a detection model and apply it to newly emerging news without social contexts.
1 code implementation • 21 Sep 2023 • Beizhe Hu, Qiang Sheng, Juan Cao, Yuhui Shi, Yang Li, Danding Wang, Peng Qi
To instantiate this proposal, we design an adaptive rationale guidance network for fake news detection (ARG), in which SLMs selectively acquire insights on news analysis from the LLMs' rationales.
no code implementations • 29 Jul 2023 • Tianyun Yang, Juan Cao, Danding Wang, Chang Xu
It is verified in existing works that CNN-based generative models leave unique fingerprints on generated images.
1 code implementation • 26 Jun 2023 • Beizhe Hu, Qiang Sheng, Juan Cao, Yongchun Zhu, Danding Wang, Zhengjia Wang, Zhiwei Jin
In this paper, we observe that the appearances of news events on the same topic may display discernible patterns over time, and posit that such patterns can assist in selecting training instances that could make the model adapt better to future data.
1 code implementation • CVPR 2023 • Tianyun Yang, Danding Wang, Fan Tang, Xinying Zhao, Juan Cao, Sheng Tang
In this study, we focus on a challenging task, namely Open-Set Model Attribution (OSMA), to simultaneously attribute images to known models and identify those from unknown ones.
2 code implementations • 7 Feb 2023 • Yuyan Bu, Qiang Sheng, Juan Cao, Peng Qi, Danding Wang, Jintao Li
With information consumption via online video streaming becoming increasingly popular, misinformation video poses a new threat to the health of the online information ecosystem.
no code implementations • ICCV 2023 • Zhihao Sun, Haoran Jiang, Danding Wang, Xirong Li, Juan Cao
Since image editing methods in real world scenarios cannot be exhausted, generalization is a core challenge for image manipulation detection, which could be severely weakened by semantically related features.
no code implementations • COLING 2022 • Qiong Nan, Danding Wang, Yongchun Zhu, Qiang Sheng, Yuhui Shi, Juan Cao, Jintao Li
To address this issue, we propose a Domain- and Instance-level Transfer Framework for Fake News Detection (DITFEND), which could improve the performance of specific target domains.
no code implementations • 1 Sep 2022 • Guang Yang, Wu Liu, Xinchen Liu, Xiaoyan Gu, Juan Cao, Jintao Li
To close the frequency gap between the natural and synthetic videos, we propose a novel Frequency-based human MOtion TRansfer framework, named FreMOTR, which can effectively mitigate the spatial artifacts and the temporal inconsistency of the synthesized videos.
1 code implementation • 26 Jun 2022 • Yongchun Zhu, Qiang Sheng, Juan Cao, Qiong Nan, Kai Shu, Minghui Wu, Jindong Wang, Fuzhen Zhuang
In this paper, we propose a Memory-guided Multi-view Multi-domain Fake News Detection Framework (M$^3$FEND) to address these two challenges.
1 code implementation • 6 May 2022 • Qiang Sheng, Juan Cao, H. Russell Bernard, Kai Shu, Jintao Li, Huan Liu
False news that spreads on social media has proliferated over the past years and has led to multi-aspect threats in the real world.
1 code implementation • 20 Apr 2022 • Yongchun Zhu, Qiang Sheng, Juan Cao, Shuokai Li, Danding Wang, Fuzhen Zhuang
In this paper, we propose an entity debiasing framework (\textbf{ENDEF}) which generalizes fake news detection models to the future data by mitigating entity bias from a cause-effect perspective.
no code implementations • 21 Mar 2022 • Yuting Yang, Pei Huang, Juan Cao, Jintao Li, Yun Lin, Jin Song Dong, Feifei Ma, Jian Zhang
Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs).
1 code implementation • ACL 2022 • Qiang Sheng, Juan Cao, Xueyao Zhang, Rundong Li, Danding Wang, Yongchun Zhu
To differentiate fake news from real ones, existing methods observe the language patterns of the news post and "zoom in" to verify its content with knowledge sources or check its readers' replies.
1 code implementation • 17 Mar 2022 • Guang Yang, Juan Cao, Qiang Sheng, Peng Qi, Xirong Li, Jintao Li
However, these methods have two limitations: 1) they neglect other important elements like scenes, textures, and objects beyond the capacity of pretrained object detectors; 2) the correlation among objects is fixed, but a fixed correlation is not appropriate for all the images.
1 code implementation • 28 Feb 2022 • Tianyun Yang, Ziyao Huang, Juan Cao, Lei LI, Xirong Li
With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images.
no code implementations • 15 Jan 2022 • Yuting Yang, Wenqiang Lei, Pei Huang, Juan Cao, Jintao Li, Tat-Seng Chua
In this paper, we focus on how to utilize the language understanding and generation ability of pre-trained language models for DST.
no code implementations • 11 Jan 2022 • Yuting Yang, Pei Huang, Feifei Ma, Juan Cao, Meishan Zhang, Jian Zhang, Jintao Li
Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations.
1 code implementation • 4 Jan 2022 • Qiong Nan, Juan Cao, Yongchun Zhu, Yanyan Wang, Jintao Li
In this paper, we first design a benchmark of fake news dataset for MFND with domain label annotated, namely Weibo21, which consists of 4, 488 fake news and 4, 640 real news from 9 different domains.
1 code implementation • ACL 2021 • Qiang Sheng, Juan Cao, Xueyao Zhang, Xirong Li, Lei Zhong
By fusing event and pattern information, we select key sentences to represent an article and then predict if the article fact-checks the given claim using the claim, key sentences, and patterns.
2 code implementations • 16 Dec 2021 • Chengbo Dong, Xinru Chen, Ruohan Hu, Juan Cao, Xirong Li
As both clues are meant to be semantic-agnostic, the learned features are thus generalizable.
1 code implementation • 23 Sep 2021 • Qiang Sheng, Xueyao Zhang, Juan Cao, Lei Zhong
To this end, we build a Preference-aware Fake News Detection Framework (Pref-FEND), which learns the respective preferences of pattern- and fact-based models for joint detection.
no code implementations • 16 Jun 2021 • Tianyun Yang, Juan Cao, Qiang Sheng, Lei LI, Jiaqi Ji, Xirong Li, Sheng Tang
Adopting a multi-task framework, we propose a GAN Fingerprint Disentangling Network (GFD-Net) to simultaneously disentangle the fingerprint from GAN-generated images and produce a content-irrelevant representation for fake image attribution.
3 code implementations • 31 May 2021 • Yongchun Zhu, Yudan Liu, Ruobing Xie, Fuzhen Zhuang, Xiaobo Hao, Kaikai Ge, Xu Zhang, Leyu Lin, Juan Cao
Besides, MetaHeac has been successfully deployed in WeChat for the promotion of both contents and advertisements, leading to great improvement in the quality of marketing.
no code implementations • 11 May 2021 • Yongchun Zhu, Ruobing Xie, Fuzhen Zhuang, Kaikai Ge, Ying Sun, Xu Zhang, Leyu Lin, Juan Cao
The cold item ID embedding has two main problems: (1) A gap is existing between the cold ID embedding and the deep model.
2 code implementations • ICCV 2021 • Xinru Chen, Chengbo Dong, Jiaqi Ji, Juan Cao, Xirong Li
The key challenge of image manipulation detection is how to learn generalizable features that are sensitive to manipulations in novel data, whilst specific to prevent false alarms on authentic images.
Ranked #4 on Image Manipulation Localization on COVERAGE
1 code implementation • CVPR 2021 • Lei LI, Ke Gao, Juan Cao, Ziyao Huang, Yepeng Weng, Xiaoyue Mi, Zhengze Yu, Xiaoya Li, Boyang xia
A series of strategies are introduced to guarantee the safety and effectiveness of the expanded domains.
no code implementations • 27 Jan 2021 • Yongchun Zhu, Fuzhen Zhuang, Xiangliang Zhang, Zhiyuan Qi, Zhiping Shi, Juan Cao, Qing He
However, in real-world applications, few-shot learning paradigm often suffers from data shift, i. e., samples in different tasks, even in the same task, could be drawn from various data distributions.
no code implementations • ACL 2020 • Lei Zhong, Juan Cao, Qiang Sheng, Junbo Guo, Ziang Wang
Identifying controversial posts on social media is a fundamental task for mining public sentiment, assessing the influence of events, and alleviating the polarized views.
no code implementations • 13 Aug 2019 • Peng Qi, Juan Cao, Tianyun Yang, Junbo Guo, Jintao Li
In the real world, fake-news images may have significantly different characteristics from real-news images at both physical and semantic levels, which can be clearly reflected in the frequency and pixel domain, respectively.
1 code implementation • 24 Jun 2019 • Feng Dai, Hao liu, Yike Ma, Juan Cao, Qiang Zhao, Yongdong Zhang
The key component of our network is the dense dilated convolution block, in which each dilation layer is densely connected with the others to preserve information from continuously varied scales.
1 code implementation • 5 Mar 2019 • Xueyao Zhang, Juan Cao, Xirong Li, Qiang Sheng, Lei Zhong, Kai Shu
Emotion plays an important role in detecting fake news online.
no code implementations • 2 Feb 2019 • Yuting Yang, Juan Cao, Mingyan Lu, Jintao Li, Chia-Wen Lin
SNQAM performs excellently on predicting quality, presenting interpretable quality score and giving accessible suggestions on how to improve it according to writing guidelines we referred to.
no code implementations • 1 Jan 2019 • Jiarong Dong, Ke Gao, Xiaokai Chen, Junbo Guo, Juan Cao, Yongdong Zhang
To address this issue, we propose a novel learning strategy called Information Loss, which focuses on the relationship between the video-specific visual content and corresponding representative words.
no code implementations • 12 Dec 2018 • Tianyi Wu, Sheng Tang, Rui Zhang, Juan Cao, Jintao Li
Therefore, it can capture partial information and enlarge the receptive field of filters simultaneously without introducing extra parameters.
no code implementations • Mountain View, CA, USA 2017 • Zhiwei Jin, Juan Cao, Han Guo, Yongdong Zhang
In this paper, we propose a novel Recurrent Neural Network with an at- tention mechanism (att-RNN) to fuse multimodal features for e ective rumor detection.
no code implementations • 16 Nov 2016 • Zhiwei Jin, Juan Cao, Jiebo Luo, Yongdong Zhang
In order to overcome the scarcity of training samples of fake images, we first construct a large-scale auxiliary dataset indirectly related to this task.