Peng Sun

Peng Sun

Auto-generated profile, based on publicly available information

Peng Sun

Chinese Academy of Sciences, Ministry of Justice, Key Lab of Forensic Science, Shanghai, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
9 March 2021 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
YYYao Ying
Yao Ying
NZNengbo Zhang
Nengbo Zhang
PSPeng Shan
Peng Shan
LMLigang Miao
Ligang Miao
PSPeng Sun
Peng Sun
SPSilong Peng
Silong Peng

1 August 2018 in Forensic Science International
Verified
Journal Article
Closed access
PSPeng Sun
Peng Sun
YLYubo Lang
Yubo Lang
SFShu Fan
Shu Fan
ZSZhe Shen
Zhe Shen
LLLei Liu
Lei Liu
SPSilong Peng
Silong Peng

3 January 2020 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
SZShen Zhe
Shen Zhe
SPSun Peng
Sun Peng

11 September 2022 in Forensic Science International
Verified
Journal Article
Closed access
LLLei Liu
Lei Liu
PSPeng Sun
Peng Sun
YLYubo Lang
Yubo Lang
JLJingjiao Li
Jingjiao Li
SSShaopei Shi
Shaopei Shi

28 April 2023 in arXiv
Verified
Preprint
Open access
PDF file
ZYZhiyuan Yan
Zhiyuan Yan
PSPeng Sun
Peng Sun
YLYubo Lang
Yubo Lang
SDShuo Du
Shuo Du
SZShanzhuo Zhang
Shanzhuo Zhang
LLLei Liu
Lei Liu
Existing deepfake detectors face several challenges in achieving robustness and generalization. One of the primary reasons is their limited ability to extract relevant information from forgery videos, especially in the presence of various artifacts such as spatial, frequency, temporal, and landmark mismatches. Current detectors rely on pixel-level features that are easily affected by unknown disturbances or facial landmarks that do not provide sufficient information. Furthermore, most detectors cannot utilize information from multiple domains for detection, leading to limited effectiveness in identifying deepfake videos. To address these limitations, we propose a novel framework, namely Multimodal Graph Learning (MGL) that leverages information from multiple modalities using two GNNs and several multimodal fusion modules. At the frame level, we employ a bi-directional cross-modal transformer and an adaptive gating mechanism to combine the features from the spatial and frequency domains with the geometric-enhanced landmark features captured by a GNN. At the video level, we use a Graph Attention Network (GAT) to represent each frame in a video as a node in a graph and encode temporal information into the edges of the graph to extract temporal inconsistency between frames. Our proposed method aims to effectively identify and utilize distinguishing features for deepfake detection. We evaluate the effectiveness of our method through extensive experiments on widely-used benchmarks and demonstrate that our method outperforms the state-of-the-art detectors in terms of generalization ability and robustness against unknown disturbances.

1 November 2023 in Journal of Electronic Imaging
Verified
Journal Article
Closed access
PDF file
LLLei Liu
Lei Liu
PSPeng Sun
Peng Sun
YLYubo Lang
Yubo Lang
JLJingjiao Li
Jingjiao Li
HGHong Guo
Hong Guo
QLQimeng Lu
Qimeng Lu
Powerful image editing software makes the process of image manipulation easy, which increases security risks. Therefore, it is urgent to locate the tampered region to uncover the processing history. However, previous research has mainly focused on feature extraction, with little discussion on classifiers for classifying original and tampered regions. We improve the splicing forgery localization method from a statistical perspective. The refined color filter array feature provides sufficient data for statistical analysis, and the geometric mean is used to eliminate anomalous data. Subsequently, a classifier that combines the expectation–maximization algorithm and Bayesian theory is proposed to binarize the original and tampered regions. The two steps of feature extraction and feature classification are associated from a statistical perspective, which ultimately improve the performance of the method effectively. Extensive experimental results demonstrate that the refined feature used for classification has several advantages, and the proposed classifier is appropriate for handling complex image manipulation across different statistical distributions. The proposed method outperforms the reference methods in both the Columbia and Korus datasets.