IMD2020: A Large-Scale Annotated Dataset Tailored for Detecting Manipulated Images

Novozámský, Adam; Mahdian, Babak; Saic, Stanislav

doi:10.1109/wacvw50321.2020.9096940

Cited by 112 publications

(48 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This table is far from being exhaustive and thus illustrates the wide availability of datasets. In particular since 2019, three extremely large datasets (PS-Battles [53], DEFACTO [54] and IMD2020 [55]) have been publicly released containing all kinds of forgeries that should allow researchers to properly evaluate, train or test their forensic algorithms.…”

Section: Images Datasetsmentioning

confidence: 99%

“…The Biometix datasets, released in 2017, contained 1082 Face Morphing based on the FERET face dataset. In the Columbia gray and colour [56] Splicing 1092 MICC F220 and F2000 [57] Copy-move 810 Casia v1 and v2 [58] Splicing, copy-move 6044 COVERAGE [46] Copy-move 100 Biometix [59] Face morphing 1082 FaceSwap [60] Face swapping 1,927 PS-Battles [53] All 102,028 DEFACTO [54] All 229,000 IMD2020 [55] All 72000 OpenMFC2020 [61] All 16,000…”

Section: Images Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Face Manipulation Detection in Remote Operational Systems

Pic

Mahfoudi

Trabelsi

et al. 2022

Handbook of Digital Face Manipulation and Detection

View full text Add to dashboard Cite

In this chapter, we present the various categories of Face Manipulation and their use within different remote operational systems. We then use the example of remote identity document onboarding systems to illustrate how each category can be used in practice to compromise such a system. After a definition of the different Face Manipulation categories and the common algorithms used to produce them, we go through the various manipulation detection algorithms and common image and video forgery datasets. We then introduce some known counter-forensics methods that can be used by an attacker to avoid detection. Knowing the detection methods and the counter-forensic, we present how we can build up a safer system by using the correct methods at the correct time. But also how knowledge about the tampering process could be used to design the user experience to make the systems harder to compromise. We complete this review by the standardisation effort and legal aspect on the matter. And we conclude by discussing the remaining challenges and perspectives for better use of nowadays detection methods in practical usage.

show abstract

Section: Images Datasetsmentioning

confidence: 99%

Section: Images Datasetsmentioning

confidence: 99%

Face Manipulation Detection in Remote Operational Systems

Pic

Mahfoudi

Trabelsi

et al. 2022

Handbook of Digital Face Manipulation and Detection

View full text Add to dashboard Cite

show abstract

“…The foreground and background predictions in this mutual learning are considered to contribute equally, thus no additional hyper-parameter is added. The proposed MC-Net is trained on a synthetic data set 37 and evaluated on four standard data sets (NIST16, 56 Coverage, 57 CASIA, 58 and IMD20 59 ) for generalizability testing. The synthetic data set combines real images from DRESDEN 60 and NIST16 with targets from MS-COCO 61 to simulate splicing attacks, containing 65k images for pre-training.…”

Section: Training Detailsmentioning

confidence: 99%

MC‐Net: Learning mutually‐complementary features for image manipulation localization

Shen

Lyu

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Deep learning has become an emerging technical for image manipulation localization, which can automatically recognize abnormal traces caused by manipulation. However, as manipulations mainly happens in the foreground regions, these methods largely focus on the foreground contents and neglect the background, which contain complementary signal for fully understanding the image and are meaningful for manipulation localization. We propose a Mutually‐Complementary Network (MC‐Net), which is a two‐branch network to operate the foreground and background features, respectively. To distill complementary signals from the features, we propose a mutual attentive module composed of self‐feature attentive, and cross‐feature attentive components to advance the communication across the foreground and background branches. Extensive qualitative and quantitative experiments demonstrate that our proposed MC‐Net distinctly improves the prediction of foreground and background, obtains consistent performance increments on four benchmark data sets, and significantly outperforms the state‐of‐the‐art methods.

show abstract

“…We also use Defacto for inpainting data. We use the IMD-Real dataset [39] for untam-pered images. For both pre-trained and finetuned evaluation we use the four standard datasets: CASIAv2 [18], NIST16 [22], COVERAGE [58] and IMD-2020 [39], following the training/testing split described in [33].…”

Section: Datasetsmentioning

confidence: 99%

GCA-Net : Utilizing Gated Context Attention for Improving Image Forgery Localization and Detection

Das¹,

Islam²,

Amin³

2021

Preprint

View full text Add to dashboard Cite

Forensic analysis depends on the identification of hidden traces from manipulated images. Traditional neural networks fail in this task because of their inability in handling feature attenuation and reliance on the dominant spatial features. In this work we propose a novel Gated Context Attention Network (GCA-Net) that utilizes the non-local attention block for global context learning. Additionally, we utilize a gated attention mechanism in conjunction with a dense decoder network to direct the flow of relevant features during the decoding phase, allowing for precise localization. The proposed attention framework allows the network to focus on relevant regions by filtering the coarse features. Furthermore, by utilizing multi-scale feature fusion and efficient learning strategies, GCA-Net can better handle the scale variation of manipulated regions. We show that our method outperforms state-of-the-art networks by an average of 4.2% − 5.4% AUC on multiple benchmark datasets. Lastly, we also conduct extensive ablation experiments to demonstrate the method's robustness for image forensics.

show abstract

IMD2020: A Large-Scale Annotated Dataset Tailored for Detecting Manipulated Images

Cited by 112 publications

References 20 publications

Face Manipulation Detection in Remote Operational Systems

Face Manipulation Detection in Remote Operational Systems

MC‐Net: Learning mutually‐complementary features for image manipulation localization

GCA-Net : Utilizing Gated Context Attention for Improving Image Forgery Localization and Detection

Contact Info

Product

Resources

About