Haozhe Zhao

Haozhe Zhao

Auto-generated profile, based on publicly available information

Haozhe Zhao

Peking University, National Key Laboratory for Multimedia Information Processing, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
4 August 2023
Verified
Conference Paper
Open access
LWLewen Wang
Lewen Wang
HZHaozhe Zhao
Haozhe Zhao
CFCunguang Feng
Cunguang Feng
WLWeiqing Liu
Weiqing Liu
CHCongrui Huang
Congrui Huang
JBJiang Bian
Jiang Bian
As one of the major threats to the healthy development of various online platforms, fraud has become increasingly committed in the form of gangs since collusive fraudulent activities are much easier to obtain illicit benefits with lower exposure risk. To detect fraudsters in a gang, spatio-temporal graph neural network models have been widely applied to detect both temporal and spatial collusive patterns. However, a closer peek into real-world records of fraudsters can reveal that fraud gangs usually conduct community-level camouflage, specified by two types, i.e., temporal and spatial camouflage. Such camouflage can disguise gangs as benign communities by concealing collusive patterns and thus deceiving many existing graph neural network models. In the meantime, many existing graph neural network models suffer from the challenge of extreme sample imbalance caused by rare fraudsters hidden among massive users. To handle all these challenges, in this paper, we propose a generative adversarial network framework, named Adversarial Camouflage Detector, to detect fraudsters. Concretely, this ACD framework consists of four modules, in charge of community division, camouflage identification, fraudster detection, and camouflage generation, respectively. The first three modules form up a discriminator that uses spatio-temporal graph neural networks as the foundation model and enhance fraudster detection by amplifying the gangs' collusive patterns through automatically identifying and removing camouflage. Meanwhile, the camouflage generation module plays as the generator role that generates fraudsters samples by competing against the discriminator to alleviate the challenge of sample imbalance and increase the model robustness. The experimental result shows that our proposed method outperforms other methods on real-world datasets.

28 July 2023
Verified
Conference Paper
Open access
WHWenjuan Han
Wenjuan Han
HZHaozhe Zhao
Haozhe Zhao
ZCZefan Cai
Zefan Cai
Pretrained visual-language models (VLMs) have made progress in developing multimodal models to improve various tasks. However, they lack reasoning and in-context learning ability. Building on the success of large language models (LLMs) in general-purple NLP tasks, researchers anticipate that the VLM should also have the same strong reasoning and ICL ability through specific techniques, for example benefiting from LLMs. To boost VLMs to solve vision-language problems via few-shot exemplars, we suggest a vision-language model, called MIC1.

10 November 2025
Verified
Conference Paper
Open access
LCLiang Chen
Liang Chen
HZHaozhe Zhao
Haozhe Zhao
YHYinzhen Huang
Yinzhen Huang
YLYang Luo
Yang Luo
TLTsekai Lin
Tsekai Lin
BCBaobao Chang
Baobao Chang