From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics
Open accessThe DOI matches its Crossref record; 66 of the 66 references it cites were found in a registry or an index; 11 of the 32 sources its claims cite were checked for support.
Abstract
Systematic review of explainable deepfake detection methods, categorizing forensic, model-centric, multimodal, and natural-language explanation approaches and emphasizing trustworthy forensics.
Overview
CoChat Summary
## TL;DR
This is a survey paper on explainable AI for deepfake forensics, arguing that high detection accuracy alone is not enough for high-stakes use because detectors must also provide trustworthy, human-understandable explanations. It organizes the field into forensic-analysis methods, model-centric explainability, and multimodal/natural-language explanations, and also reviews evaluation metrics and specialized datasets.
## Key findings
- The paper categorizes explainable deepfake detection into three main approaches: forensic analysis, model-centric methods, and multimodal/natural-language explanations.
- It argues that the field has evolved from physical/algorithmic artifact detection (e.g., PRNU, convolutional traces, residuals) toward model-centric explanations and then to large multimodal models that generate human-readable reasoning.
- For evaluation, it highlights quantitative explainability metrics proposed by Baldassarre et al. that assess visual quality (smoothness, spatial locality, sparsity) and informativeness, and notes that standard deepfake metrics like Accuracy, AUC, and EER do not measure interpretability.
- On data, it notes that newer explainability-oriented datasets such as DDL contain 1.8 million samples, 75 manipulation types, and fine-grained annotations, while ExDDV adds clicks and textual descriptions.
## Methods
- The paper is a systematic review/survey of explainable deepfake detection methods, not an experimental study.
- It synthesizes prior work across forensic traces, post hoc XAI, interpretable architectures, multimodal frameworks, metrics, and datasets.
- Its main analysis is a taxonomy and conceptual comparison of methods, discussing strengths, limitations, and research directions grounded in the cited literature.
## Limitations
- The paper does not report original experiments or new benchmark results; this is evident from the text because it is a review and does not present a study sample or empirical protocol.
- It explicitly states that many existing explanations are still evaluated subjectively or with metrics not tailored to deepfake forensics, and that explanation fidelity remains a concern.
- It also states that generalization to unseen forgery techniques and robustness against anti-forensic/adversarial attacks remain open problems.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
9 Valid · 5 Not valid · 19 Not checked · 58 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“Baldassarre et al. [47] formalized evaluation by proposing metrics such as sparsity and spatial locality, enabling quantitative comparisons of the quality of visual explanations.”
What the sources say
- Supportedcites [47] Baldassarre, F., Debard, Q., Pontiveros, G.F., and Wijaya, T.K. (2022, January 23–27). Quantitative metrics for evaluating explanations of video deepfake detectors. Proceedings of the European Conference on Computer Vision Workshops (ECCVW), Tel Aviv, Israel. source
The Introduction says the paper proposes metrics for sparsity and locality within a quantitative framework for evaluating DeepFake explanations. Section 3.2 says it formulates metrics for evaluating human-centric properties, and the Conclusion says these enable quantitative comparisons of explanation quality. Page numbers are not provided in our copy. (LLM, conf=0.94)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Foundational benchmarks have been instrumental in advancing the accuracy of deepfake detectors.”
What the sources say
- Supportedcites [48] Li, Y., Yang, X., Sun, P., Qi, H., and Lyu, S. (2020, January 13–19). Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA. source
The Introduction (p. 1) calls large-scale DeepFake datasets an enabling factor in developing detection methods. Results and Analysis (p. 7) reports progress in detection performance, supporting the broad claim, while cautioning that high accuracy on earlier datasets may not transfer to more challenging videos. (LLM, conf=0.85)
- Partly supportedcites [49] Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., and Canton-Ferrer, C. (2020). The DeepFake Detection Challenge (DFDC) Dataset. arXiv. sourceExperimental — accuracy not yet measured
The Introduction (p. 1) says deepfake datasets are used to train and evaluate detectors and that the DFDC challenge aims to invigorate detection research. It does not establish that benchmarks have already advanced detector accuracy, as the claim asserts. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [50] Zi, B., Chang, M., Chen, J., Ma, X., and Jiang, Y. (2020, January 12–16). WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA. source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Recent datasets such as DDL [51] and ExDDV [52] are explicitly designed with explainability in mind, combining binary labels, pixel-level masks, and human-generated textual descriptions.”
What the sources say
- Partly supportedcites [51] Miao, C., Chen, Y., Zhang, Z., Liu, Z., Wang, Z., Wang, S., and Feng, J. (2024). DDL: A Dataset for Interpretable Deepfake Detection and Localization in Real-World Scenarios. arXiv. sourceExperimental — accuracy not yet measured
The Datasets section says DDL provides spatial forgery-region masks and temporal segment labels to support localization and interpretation, consistent with the claim's explainability focus. The Introduction discusses binary classification alongside localization, but our copy does not say DDL includes human-generated textual descriptions. This verdict concerns DDL, not the separately cited ExDDV. (LLM, conf=0.86)
- Partly supportedcites [52] Hondru, V., Hogea, E., Onchis, D.M., and Ionescu, R.T. (2025). ExDDV: A New Dataset for Explainable Deepfake Detection in Video. arXiv. sourceExperimental — accuracy not yet measured
Our copy confirms ExDDV was built for explainability and carries binary (real/fake) labels plus human-written textual explanations: Related Work (p. 2) contrasts prior sets that 'contain the binary label (real or fake)' with ExDDV's 'textual explanations for the artifacts observed by human annotators, along with clicks (points) that indicate artifact locations', and the Abstract/Introduction (pp. 1-2) repeat the manual text-description annotation. However, the localization annotation is clicks — relative pixel coordinates plus timestamps (Section 7, p. 12) — not pixel-level masks; the only masks in the paper are the soft/hard input-masking heuristics the authors derive around a click ROI for training (Section 4.4, p. 6), not dataset annotations. So the 'pixel-level masks' component of the claim is not what ExDDV provides. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Despite significant accuracy improvements in existing detection models, their inherent opacity limits their practical application in high-risk areas such as forensic investigations and news verification.”
What the sources say
- Supportedcites [1] Tolosana, 2020, Deepfakes and beyond: A Survey of face manipulation and fake detection, Inf. Fusion source
The Manipulation Detection section says recent deep-learning methods were applied to improve detection and reports accuracies above 90% for one approach. It also reports near-100% AUC on some first-generation datasets, while cautioning that performance degrades on newer datasets. The attributed claim concerns accuracy improvements, not the citing sentence’s separate assertion about opacity. (LLM, conf=0.86)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“models such as TruthLens and M2F2-Det perform detection through the process of explanation itself [40,41].”
What the sources say
- Supportedcites [40] Kundu, R., Jia, S., Mohanty, V., Balachandran, A., and Roy-Chowdhury, A.K. (2024). TruthLens: Explainable DeepFake Detection for Face Manipulated and Fully Synthetic Data. arXiv. source
Our copy states exactly this for its own model in §3.1 Problem Setup: the objective is 'to generate a detailed answer ... that determines whether the image is real or manipulated and provides an explanation for the decision', reinforced in §A3 ('For a system whose deployment value is the explanation itself') and the Abstract ('accurate predictions along with detailed, fine-grained reasoning'). M2F2-Det (Guo et al., 2025) is placed in §1 Related Work under 'Face Manipulation Reasoning' — methods that 'generate natural language explanations through finetuned MLLMs' — explicitly contrasted with the 'Detection without Reasoning' thread that 'produces only binary labels', so the grouping of the two models as explanation-based detectors is what our copy says. Caveat: our copy never prints the name 'TruthLens'; it labels its own framework FORGE (metadata title aside), so the model name in the claim is not verifiable from the text. (LLM, conf=0.80)
- Not checked — no full text of the sourcecites [41] Guo, X., Song, X., Zhang, Y., Liu, X., and Liu, X. (2024). Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector. arXiv. source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
32 more claims · 1 with their cited sources checked
Create a free account to see all 91 claims and to verify the 13 references still open.
- Probably not a substantial claim. 33
- It may state two separate claims as one. 35
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Abbreviations
“| LLMs | Large Multimodal Models |”
§ References
“| LLM | Large Language Model |”
Citations
Cites
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2662206 · Cited by 8,983 · cited 1×
“Zhang et al. [18] pioneered this approach with DnCNN, a CNN designed to predict the residual (noise) rather than the clean image.”
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01228-7 · Cited by 6,909 · cited 1×
“Among the most popular of these are gradient-based attribution methods such as Gradient-weighted class activation mapping (Grad-CAM) [26].”
FaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · cited 2×
“Within the context of Deepfake detection, explain-ability transcends a simple classification label; It is the comprehensive ability to provide the reasoning for a decision, localize the evidence artifacts, and even shed light on the manipulation methodology [2].”
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846 · cited 1×
“Key resources include FaceForensics++, a widely adopted dataset for benchmarking, and Celeb-DF [48], known for its high-realism forgeries.”
Digital Camera Identification From Sensor Pattern Noise
Luka, J., Fridrich, J., & Goljan, M. (2006) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2006.873602 · Cited by 1,328 · cited 2×
“The seminal work by Lukas et al. [9] systematically introduced the use of sensor pattern noise, particularly PRNU, as a unique identifier for the source camera.”
Deepfakes and beyond: A Survey of face manipulation and fake detection
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.06.014 · Cited by 1,237 · cited 1×
“In response, the research community has developed a vast array of detection models, achieving remarkable success in classification accuracy [1].”
Exposing DeepFake Videos By Detecting Face Warping Artifacts
Li, Y., & Lyu, S. (2018) · arXiv · doi:10.48550/arxiv.1811.00656 · Cited by 785 · cited 1×
“More recently, advances have emerged in multimodal and natural language explanations, where Large Multimodal Models (LMMs) are leveraged to generate rich, human-readable reports that articulate the reasoning behind detection outcomes [3].”
Noiseprint: A CNN-Based Camera Model Fingerprint
Cozzolino, D., & Verdoliva, L. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2916364 · Cited by 499 · cited 2×
“Cozzolino et al. [14] introduced Noiseprint, which improves on traditional hand-crafted PRNU features by replacing the fixed noise model with a learned representation.”
WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
Zi, B., Chang, M., Chen, J., Ma, X., & Jiang, Y.-G. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413769 · Cited by 448 · cited 1×
“Additionally, large-scale efforts such as the Deepfake Detection Challenge (DFDC) [49] and the WildDeepfake [50] dataset have driven the development of more generalizable models.”
The deepfake detection challenge (dfdc) dataset
Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., & Ferrer, C. C. (2020) · arXiv · doi:10.48550/arxiv.2006.07397 · Cited by 427
The Deepfake Detection Challenge (DFDC) Preview Dataset
Dolhansky, B., Howes, R., Pflaum, B., Baram, N., & Ferrer, C. C. (2019) · arXiv · doi:10.48550/arxiv.1910.08854 · Cited by 413
DeepFake Detection by Analyzing Convolutional Traces
Guarnera, L., Giudice, O., & Battiato, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00341 · Cited by 374 · cited 1×
“Guarnera et al. [16] targeted artifacts inherent to GAN-based image generation, particularly those introduced by transposed convolution layers during upsampling, termed convolutional traces.”
DeepFake Detection Based on Discrepancies Between Faces and Their Context
Nirkin, Y., Wolf, L., Keller, Y., & Hassner, T. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3093446 · Cited by 312 · cited 2×
“Re-synthesis [21] evaluates an image’s compatibility with models trained on genuine data, while contextual identity checks [22] test for semantic contradictions.”
DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
Qi, H., Guo, Q., Juefei-Xu, F., Xie, X., Ma, L., Feng, W., Liu, Y., & Zhao, J. (2020) · arXiv · doi:10.48550/arxiv.2006.07634 · Cited by 280
DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
Qi, H., Guo, Q., Juefei-Xu, F., Xie, X., Ma, L., Feng, W., Liu, Y., & Zhao, J. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413707 · Cited by 220 · cited 2×
“In DeepRhythm [34], for example, the model learns which facial areas are most informative for rPPG extraction, and the attention map functions both as a signal-processing step and as an explanation.”
Dual Contrastive Learning for General Face Forgery Detection
Sun, K., Yao, T., Chen, S., Ding, S., Li, J., & Ji, R. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20130 · Cited by 209
Voice-Face Homogeneity Tells Deepfake
Cheng, H. H., Guo, Y., Wang, T., Li, Q., Chang, X., & Nie, L. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3625231 · Cited by 171 · cited 1×
“The Voice-Face Homogeneity approach [33], for example, operates on the premise that an individual’s voice and face share a biometric link.”
Fighting Deepfake by Exposing the Convolutional Traces on Images
Guarnera, L., Giudice, O., & Battiato, S. (2020) · IEEE Access · doi:10.1109/access.2020.3023037 · Cited by 149 · cited 2×
“Guarnera et al. [17] advance this further by directly modeling the fingerprints of the GAN architecture, changing the explanatory statement from “captured by camera X” to “generated by algorithm Y”.”
Snis: a signal noise separation-based network for post-processed image forgery detection
Chen, J., Liao, X., Wang, W., Qian, Z., Qin, Z., & Wang, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3204753 · Cited by 129
Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes
Trinh, L., Tsang, M., Rambhatla, S., & Liu, Y. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00202 · Cited by 115 · cited 3×
“For instance, a decision tree is inherently interpretable, as each decision can be traced through explicit logical splits [7].”
InfluentialGanguly, S., Ganguly, A., Mohiuddin, S., Malakar, S., & Sarkar, R. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118423 · Cited by 115 · cited 1×
“For example, prominent Deepfake detection architectures include XceptionNet [4], which has achieved strong performance on benchmarks like FaceForensics++ [2], as well as various meth-ods that analyze frequency-domain artifacts.”
Deepfake Detection: A Comprehensive Survey from the Reliability Perspective
Wang, T., Liao, X., Chow, K. P., Lin, X., & Wang, Y. (2025) · ACM Computing Surveys · doi:10.1145/3699710 · Cited by 107 · cited 2×
“Explainable AI provides a diagnostic lens that reveals whether a model relies on fundamental generalizable manipulation traces, such as blending boundaries or frequency inconsistencies, or overfits to superficial, generator-specific cues [6].”
PRRNet: Pixel-Region relation network for face forgery detection
Shang, Z., Xie, H., Zha, Z., Yu, L., Li, Y., & Zhang, Y. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107950 · Cited by 106 · cited 1×
“Shang et al. [37] introduced PRRNet, which captures inconsistencies between local facial regions and global context.”
MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection
Kong, C., Luo, A., Bao, P., Yu, Y., Li, H., Zheng, Z., Wang, S., & Kot, A. C. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3604443 · Cited by 106
Explaining Deepfake Detection by Analysing Image Matching
Dong, S., Wang, J., Liang, J., Fan, H., & Ji, R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19781-9_2 · Cited by 105
WildDeepfake: A Challenging Real-World Dataset for Deepfake DetectionPreprint
Zi, B., Chang, M., Chen, J., Ma, X., & Jiang, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.01456 · Cited by 92
Blind PRNU-Based Image Clustering for Source Identification
Marra, F., Poggi, G., Sansone, C., & Verdoliva, L. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2701335 · Cited by 84 · cited 1×
“Marra et al. [10] addressed a more challenging forensic setting involving large collections of images with unknown origins.”
Exposing Deepfake Face Forgeries With Guided Residuals
Guo, Z., Yang, G., Chen, J., & Sun, X. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3237169 · Cited by 74 · cited 2×
“Motivated by this concept, Guo et al. [19] introduced GRnet, featuring a Manipulation Trace Extractor (MTE) that leverages guided filtering to retain genuine content while extracting detailed residual information.”
Explainable Deep-Fake Detection Using Visual Interpretability Methods
Malolan, B., Parekh, A., & Kazi, F. (2020) · 2020 3rd International Conference on Information and Computer Technologies (ICICT) · doi:10.1109/icict50521.2020.00051 · Cited by 70 · cited 2×
“Malolan et al. [27] proposed a framework utilizing visual interpretability methods such as saliency maps and guided backpropagation to reveal which facial regions a CNN relies on in its decision-making process.”
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
He, Y., Yu, N., Keuper, M., & Fritz, M. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/349 · Cited by 70 · cited 2×
“He et al. [21] argued that reliance on static frequency artifacts is unsustainable as generative quality improves.”
Supervised Contrastive Learning for Generalizable and Explainable DeepFakes Detection
Xu, Y., Raja, K., & Pedersen, M. (2022) · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw54805.2022.00044 · Cited by 62 · cited 1×
“Xu et al. [23] applied Supervised Contrastive Learning (SupCon) to enhance generalization in Deepfake detection.”
Huang, Z., Hu, J., Li, X., He, Y., Zhao, X., Peng, B., Wu, B., Huang, X., & Cheng, G. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.02685 · Cited by 62 · cited 1×
“Huang et al. [44] developed SIDA, a framework tailored to social media platforms that performs detection, localization, and explanation simultaneously.”
Ge, W., Patino, J., Todisco, M., & Evans, N. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9747476 · Cited by 40 · cited 2×
“Ge et al. [28] demonstrated the utility of SHAP for analyzing both spoofing and Deepfake detectors.”
Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector
Guo, X., Song, X., Zhang, Y., Liu, X., & Liu, X. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.00019 · Cited by 34 · cited 2×
“Instead of training a classifier and then constructing an auxiliary explanation mechanism, models such as TruthLens and M2F2-Det perform detection through the process of explanation itself [40,41].”
An adversarial attack approach for eXplainable AI evaluation on deepfake detection models
Gowrisankar, B., & Thing, V. L. L. (2024) · Computers & Security · doi:10.1016/j.cose.2023.103684 · Cited by 30 · cited 4×
“As Gowrisankar et al. [31] emphasized, standard XAI evaluation frameworks may not be suitable for Deepfake detection, and the validity of explanations must themselves be scrutinized.”
InfluentialDIPPAS: a deep image prior PRNU anonymization scheme
Picetti, F., Mandelli, S., Bestagini, P., Lipari, V., & Tubaro, S. (2022) · EURASIP Journal on Information Security · doi:10.1186/s13635-022-00128-7 · Cited by 26 · cited 2×
“Furthermore, anti-forensic techniques such as DIPPAS [12] can deliberately suppress PRNU traces while preserving high visual fidelity.”
den Bouter, M. L. D. L., Pardo, J., Geradts, Z., & Worring, M. (2024) · Information Visualization · doi:10.1177/14738716241238476 · Cited by 26 · cited 2×
“ProtoExplorer [36] exemplifies how expert-guided curation of prototype sets can ensure interpretability and non-redundancy.”
Correlation clustering for PRNU-based blind image source identification
Marra, F., Poggi, G., Sansone, C., & Verdoliva, L. (2016) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs.2016.7823910 · Cited by 23
A defensive attention mechanism to detect deepfake content across multiple modalities
Asha, S., Vinod, P., & Menon, V. G. (2024) · Multimedia Systems · doi:10.1007/s00530-023-01248-x · Cited by 16 · cited 2×
“Similarly, in Asha et al. [32], cross-modal attention weights directly quantify consistency between audio and video streams, making them both computationally essential and interpretable.”
Tariq, S., Woo, S. S., Singh, P., Irmalasari, I., Gupta, S., & Gupta, D. (2025) · Proceedings of the 33rd ACM International Conference on Multimedia · doi:10.1145/3746027.3755786 · Cited by 15
Explainable Deepfake Video Detection using Convolutional Neural Network and CapsuleNetPreprint
Ishrak, G. H., Mahmud, Z., Farabe, M. Z. A. Z., Tinni, T. K., Reza, T., & Parvez, M. Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.12841 · Cited by 14
Extracting Local Information from Global Representations for Interpretable Deepfake Detection*
Soltandoost, E., Plesh, R. O., Schuckers, S., Peer, P., & Štruc, V. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00177 · Cited by 14
A Theoretical Framework for Estimating False Acceptance Rate of PRNU-Based Camera Identification
Saito, S., Tomioka, Y., & Kitazawa, H. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2692683 · Cited by 11 · cited 1×
“Saito et al. [11] focused on the statistical reliability of PRNU-based source attribution, introducing a theoretical framework for estimating the False Acceptance Rate (FAR).”
Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization
Zhang, K., Kong, C., Liu, H., Ding, B., Jiang, X., & Li, H. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3677584 · Cited by 10
FractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarks
Wang, T., Cheng, H., Liu, M.-H., & Kankanhalli, M. (2025) · Proceedings of the 33rd ACM International Conference on Multimedia · doi:10.1145/3746027.3754544 · Cited by 9
Expressivity Landscape for Logics with Probabilistic Interventionist CounterfactualsPreprint
Barbero, F., & Virtema, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.48550/arxiv.2303.11993 · Cited by 6
Beyond the Spectrum: Detecting Deepfakes via Re-SynthesisPreprint
He, Y., Yu, N., Keuper, M., & Fritz, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.14376 · Cited by 6
Interpretable and Trustworthy Deepfake Detection via Dynamic PrototypesPreprint
Trinh, L., Tsang, M. Y. C., Rambhatla, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.15473 · Cited by 4
ExDDV: A New Dataset for Explainable Deepfake Detection in Video
Hondru, V., Hogea, E., Onchiş, D., & Ionescu, R. T. (2026) · 2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv61042.2026.00416 · Cited by 3
LayLens: Improving Deepfake Understanding through Simplified ExplanationsPreprint
Narang, A., Gupta, P., Su, L., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.10066 · Cited by 1
Huang, Z., Hu, J., Li, X., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.04292 · Cited by 1
Quantitative Metrics for Evaluating Explanations of Video DeepFake Detectors
Baldassarre, F., Debard, Q., Pontiveros, G. F., & Wijaya, T. K. (2022) · arXiv · doi:10.48550/arxiv.2210.03683 · Cited by 1
LayLens: Improving Deepfake Understanding through Simplified Explanations
Narang, A., Gupta, P., Su, L., & Dhall, A. (2025) · Proceedings of the 27th International Conference on Multimodal Interaction · doi:10.1145/3716553.3757093 · Cited by 1
(2024) · doi:10.48550/arxiv.2503.15867 · Cited by 1
Explaining Deepfake Detection by Analysing Image MatchingPreprint
Dong, S., Wang, J., Liang, J., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.09679
Learn To be Efficient: Build Structured Sparsity in Large Language ModelsPreprint
Zheng, H., Bai, X., Liu, X., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.06126
Cosmological bouncing solutions and their stability in teleparallel gravityPreprint
Malik, A., Rauf, A., Bamba, K., Lin, W., & Mofarreh, F. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.15867
Xiao, B., Zhang, J., Ni, W., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.14811
Field Theory Approach to Classical $N$-Particle Systems In and Out of EquilibriumPreprint
Daus, T., & Kozlikin, E. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.03425
ExDDV: A New Dataset for Explainable Deepfake Detection in VideoPreprint
Hondru, V., Hogea, E., Onchis, D., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.14421
Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation LocalizationPreprint
Zhang, K., Kong, C., Liu, H., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.17976
Miao, C., Zhang, Y., Gao, W., Tan, Z., Feng, W., Luo, M., Li, J., Liu, A., Diao, Y., Chu, Q., et al. (2025) · arXiv · doi:10.48550/arxiv.2506.23292
FractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarks
Wang, T., Cheng, H., Liu, M.-H., et al. (2025) · arXiv · doi:10.48550/arxiv.2504.09451
Dolci, G., Cruciani, F., Rahaman, M. A., et al. (2024) · arXiv · doi:10.48550/arxiv.2406.13292
Tariq, S., Woo, S. S., Singh, P., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.07596
Research works printed but not linked: 6
- Koopman, M., Rodriguez, A.M., and Geradts, Z. (2018, January 29–31). Detection of deepfake video manipulation. Proceedings of the 20th Irish Machine Vision and Image Processing Conference (IMVIP), Belfast, UK.
- Cozzolino, D., Poggi, G., and Verdoliva, L. (2019, January 16–20). Extracting camera-based fingerprints for video forensics. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.
- Khan, S. (2022). Explainable Deepfake Detection Using Deep Learning. [Master’s Thesis, NED University of Engineering and Technology].
- Pellcier, A.L., Li, Y., and Angelov, P. (2023, January 18–24). PUDD: Prototype-based Unified Framework for Deepfake Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.
- Jia, S., Kundu, R., Balachandran, A., Moreira, D., and Roy-Chowdhury, A.K. (2024). Common Sense Reasoning for Deepfake Detection. arXiv.
- Yan, H., Han, J., Jiang, Y., Yan, B., Liu, J., Wang, X., and Lyu, S. (2024). X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection. arXiv.
Cited by
Thakur, G., & Dutta, K. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10523-9 · Cited by 3
Vijay, B., Chandra, J., Nagendra, N., et al. (2026) · doi:10.1109/icdsaai69492.2026.11505190
“Xu et al. (2024) proposed the Fake Shield, a multimodal big language model system, and it is designed to detect and localize explainable image forgery [9].”
Deepfake Forensics: Threats and Detection of AI-Manipulated Media
Cardoso, P. M. C., Oliveira, R. S., Gomes, T. F. N., Bastos, E. S., & Lopes, S. F. S. F. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7660-8.ch015 · Cited by 1
Towards Secure Media Deepfake Detection Using Explainable AI
Rajathi, S., Hemalatha, J., Rajeswari, S., Parameswaran, S., Ramya, D., & Balamurugan, S. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-28939-1_24
Aydın, Y. (2026) · International Journal of Intelligent Systems · doi:10.1155/int/9932351
Metadata
- Authors
- Qian, H., Xia, L., Ge, R., Fan, Y., Wang, Q., & Jing, Z.
- Affiliations
- Department of Computer Information and Cybersecurity, Jiangsu Police Institute, Nanjing 210031, China
- College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, China
- Jiangsu University of Technology (CN)
- Corresponding author
- Xia, Lingling
- Venue
- Cryptography
- Publisher
- MDPI AG
- Published
- 2025-09-26
- Volume
- 9
- Issue
- 4
- Pages
- 61
- ISSN
- 2410-387X (ISSN-L)
- OpenAlex
- W4414554223
- Semantic Scholar
- 515c2b155d88a961435a2412679031ba3d7151f3
- Cited by
- 10
- References
- 36
- Citations by year
- 2026: 10
- FWCI
- 3.47
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Cryptography (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- MOE Industry-University Collaborative Education Project
- Philosophy and Social Sciences Research Project of Universities in Jiangsu Province (2024SJYB0345, 2023SJYB0464, 2023SJYB0468)
- “Cyberspace Security” construction project of key disciplines in Jiangsu Province during the “14th Five-Year Plan”
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, explainable AI, deepfake forensics, model interpretability, post-hoc explanation, multimodal explanations, natural language explanations, online misinformation, trustworthy AI, forensic analysis, evaluation dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.