Detecting Generated Image Based on a Coupled Network with Two-Step Pairwise Learning

Zhuang, Yi-Xiu; Hsu, Chih–Chung

doi:10.1109/icip.2019.8803464

Cited by 18 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, different depth features are extracted in the proposed network structure, and the experimental results were obtained on DCGAN and Celeba with a classification accuracy of 97.2% and a recall accuracy of 91.6%. In a study by Zhuang [ 15 ], as in [ 13 ], to solve the problem that in order to solve the deep learning network the model cannot effectively identify the deep-network-generated images that are not included in the training process, pairwise learning was used, and, based on this, triplet-state loss was used to learn the relationship between the deep-network-generated images and real images. They also proposed a new coupled network to extract features of different depths of the target image, and the experimental results were obtained on DCGAN and Celeba, with a classification accuracy of 98.6% and a recall accuracy of 98.6%.…”

Section: Related Workmentioning

confidence: 99%

AI-Generated Face Image Identification with Different Color Space Channel Combinations

Lü

Liu

2022

Sensors

View full text Add to dashboard Cite

With the rapid development of the Internet and information technology (in particular, generative adversarial networks and deep learning), network data are exploding. Due to the misuse of technology and inadequate supervision, deep-network-generated face images flood the network, and the forged image is called a deepfake. Those realistic faked images launched a serious challenge to the human eye and the automatic identification system, resulting in many legal, ethical, and social issues. For the needs of network information security, deep-network-generated face image identification based on different color spaces is proposed. Due to the extremely realistic effect of deepfake images, it is difficult to achieve high accuracy with ordinary methods for neural networks, so we used the image processing method here. First, by analyzing the differences in different color space components in the deep learning network model for face sensitivity, a combination of color space components that can effectively improve the discrimination rate of the deep learning network model is given. Second, to further improve the discriminative performance of the model, a channel attention mechanism was added at the shallow level of the model to further focus on the features contributing to the model. The experimental results show that this scheme achieved better accuracy in the same face generation model and in different face generation models than the two compared methods, and its accuracy reached up to 99.10% in the same face generation model. Meanwhile, the accuracy of this model only decreased to 98.71% when coping with a JPEG compression factor of 100, which shows that this model is robust.

show abstract

Section: Related Workmentioning

confidence: 99%

AI-Generated Face Image Identification with Different Color Space Channel Combinations

Lü

Liu

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In recent years, many deep learning based works have been proposed to expose AI-generated fake face images [42]- [44]. Afchar et al [45] proposed a compact CNN model, namely MesoNet, for facial video forgery detection.…”

Section: Related Workmentioning

confidence: 99%

Fake face detection via adaptive manipulation traces extraction network

Guo

Yang

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

With the proliferation of face image manipulation (FIM) techniques such as Face2Face and Deepfake, more fake face images are spreading over the internet, which brings serious challenges to public confidence. Face image forgery detection has made considerable progresses in exposing specific FIM, but it is still in scarcity of a robust fake face detector to expose face image forgeries under complex scenarios. Due to the relatively fixed structure, convolutional neural network (CNN) tends to learn image content representations. However, CNN should learn subtle tampering artifacts for image forensics tasks. We propose an adaptive residuals extraction network (AREN), which serves as pre-processing to suppress image content and highlight tampering artifacts. AREN exploits an adaptive convolution layer to predict image residuals, which are reused in subsequent layers to maximize manipulation artifacts by updating weights during the back-propagation pass. A fake face detector, namely ARENnet, is constructed by integrating AREN with CNN. Experimental results prove that the proposed AREN achieves desirable preprocessing. When detecting fake face images generated by various FIM techniques, ARENnet achieves an average accuracy up to 98.52%, which outperforms the state-of-the-art works. When detecting face images with unknown post-processing operations, the detector also achieves an average accuracy of 95.17%.

show abstract

“…While media forensic has been a long existing field, the countermeasures against deep-faked images and videos are scarce. As we mentioned earlier, existing methods can be categorized into three genres, respectively by utilizing a deep neural network [30,48,49,1,67,3,37,28,53], by exploiting the unnatural low-level statistics and by detecting the abnormality of high-level information. In the very first category, it has been usually considered as a binary classification problem where a classifier is constructed to learn the boundary between original and manipulated data via hand-crafted or deep features.…”

Section: Deep-faked Manipulation Detectionmentioning

confidence: 99%

“…Therefore, the demand for forensic approaches explicitly against deep-faked videos is increasing. Existing deep forensic models can be readily categorized into three branches including realforged binary classification-based methods [30,67,49,1], anomaly image statistics detection based approaches [29,32,36,10,64] and high-level information driven cases [62,63,31]. However, no matter which kind of methods, their success heavily relies on a high-quality, uncompressed and well-labeled forensic dataset to facilitate the learning.…”

Section: Introductionmentioning

confidence: 99%

Exposing Deep-faked Videos by Anomalous Co-motion Pattern Detection

Wang,

Zhou,

2020

Preprint

View full text Add to dashboard Cite

Recent deep learning based video synthesis approaches, in particular with applications that can forge identities such as "Deep-Fake", have raised great security concerns. Therefore, corresponding deep forensic methods are proposed to tackle this problem. However, existing methods are either based on unexplainable deep networks which greatly degrades the principal interpretability factor to media forensic, or rely on fragile image statistics such as noise pattern, which in real-world scenarios can be easily deteriorated by data compression. In this paper, we propose an fully-interpretable video forensic method that is designed specifically to expose deep-faked videos. To enhance generalizability on videos with various content, we model the temporal motion of multiple specific spatial locations in the videos to extract a robust and reliable representation, called co-motion pattern. Such kind of conjoint pattern is mined across local motion features which is independent of the video contents so that the instance-wise variation can also be largely alleviated. More importantly, our proposed co-motion pattern possesses both superior interpretability and sufficient robustness against data compression for deep-faked videos. We conduct extensive experiments to empirically demonstrate the superiority and effectiveness of our approach under both classification and anomaly detection evaluation settings against the state-of-the-art deep forensic methods.

show abstract

Detecting Generated Image Based on a Coupled Network with Two-Step Pairwise Learning

Cited by 18 publications

References 6 publications

AI-Generated Face Image Identification with Different Color Space Channel Combinations

AI-Generated Face Image Identification with Different Color Space Channel Combinations

Fake face detection via adaptive manipulation traces extraction network

Exposing Deep-faked Videos by Anomalous Co-motion Pattern Detection

Contact Info

Product

Resources

About