Explainable Deepfake Detection

Ask about this topic

Overview

Explainable deepfake detection studies how to identify manipulated images, videos, and audio while making the evidence behind a prediction understandable and checkable. Approaches include highlighting suspicious regions or time segments, using explicit forensic and phonetic features, and training vision-language models to connect explanations to localized evidence. Evaluation uses datasets and benchmarks for detection, localization, explanation quality, and cross-dataset testing across generators, recording conditions, and media types. A central challenge is ensuring that convincing explanations reflect cues that actually drive the decision, while remaining reliable on unfamiliar manipulations and after compression or other changes.

Latest papers

CardsList

63 papers8 papers in the last four weeks, down 20% on the four weeks before. 0.1% of all new papers.

Nov 3, 2026

VeriSpoof: Beyond Real or Fake with One Audio LLM

A speech deepfake detector estimates whether a recording is synthetic, but a forensic analyst also asks which system produced it, whether recordings share a source, and what evidence supports each conclusion. We present VeriSpoof, an audio language model that unifies five tasks with shared weights: deepfake detection, generator attribution (generator, acoustic model and vocoder), recording-condition analysis, synthesized-span localisation, and source verification. Each decision is supported by grounded rationales whose statements can be independently verified. Answers are scored by sentence likelihood, allowing detection and source verification to be thresholded without separate heads. Rationale statements can be checked against waveform measurements, span labels, or generator metadata. Counterfactual examples train decisions to follow the stated evidence. Across the 14 Speech-DF-Arena test sets, VeriSpoof-Plus achieves 2.14% pooled EER, ranking third of 28 systems and first among open-weight systems. VeriSpoof-Base, trained only on official training splits of eight corpora, achieves 4.43% EER, less than half that of the next open-weight detector. With the same weights, VeriSpoof-Plus verifies whether recordings from generators unseen in training share a source at 6.2% EER. Controlled studies show that the audio representation governs detection, the LLM governs recording comparison, and source supervision is necessary for neural-codec fakes. Statement-checkable rationales catch partial fakes missed by one-step answers (99.6% vs. 78.4% on PartialEdit) and determine decisions under edits unseen in training (99.5%). Training updates only 29.7M of 2.85B parameters, fitting a single 24 GB GPU with gradient checkpointing. We release both models, inference code, a demo, and VeriSpoof-Bench, the evaluation suite covering these questions.

Yang Xiao, Ting Dang

The University of Melbourne

Audio Deepfake DetectionExplainable Deepfake DetectionAudio-Language Models
AskPDF
Nov 3, 2026

Generalizable AI-Generated Image Detection with Embedding-Space Explanations

AI-generated images have reached unprecedented realism, while instruction-driven AI editors re-synthesize images for local changes, leaving no splice boundary to localize. Most detectors are black boxes with unverifiable verdicts and generalize poorly because adapting a backbone on the detection distribution memorizes generator-specific fingerprints that quickly become obsolete. Specialist detectors built on pure-vision representations, particularly DINOv3, generalize well across generators, but explainable methods forgo this advantage: jointly training one multimodal model for classification and language generation subjects its visual representation to the language objective. We therefore require that explanation training cannot alter the verdict. We introduce FOX, which first builds and locks a specialist DINOv3 detector, then uses its representation to guide a lightweight VLM toward forensic explanation. A joint-embedding predictor maps locked visual evidence into a frozen text encoder's semantic space, producing guidance that the VLM verbalizes on demand. FOX achieves 97.4 mean AUC across 14 unseen generators, 69.8 BERTScore on XPlainVerse, and 56.1 on LOKI.

Nikos Giakoumoglou, Paschalis Giakoumoglou, Tania Stathaki +1

Imperial College London · Information Technologies Institute, CERTH

AI-Generated Image DetectionExplainable Deepfake Detection
AskPDF
Oct 29, 2026

Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection

Automated detection has become the essential safeguard against realistic synthetic media, but deploying it at scale requires training on sensitive data from multiple organizations, putting privacy and the transparency demanded by forensic review in direct conflict. Federated learning resolves the privacy side by sharing only model updates rather than raw data, but whether this comes at the cost of trustworthy gradient-based explanations, which analysts rely on to decide whether or not to trust a flagged clip, has not been studied. We present the systematic study of Grad-CAM explanation faithfulness under federated deepfake detection, evaluating an EfficientNet-B4 detector on FaceForensics++ across five federated clients under varying degrees of data heterogeneity. We find that the relationship between federation and explanation quality is non-monotonic: at near-IID (Independent and Identically Distributed Data) and moderate heterogeneity, federated models match or exceed the faithfulness of a centralized baseline, but at extreme heterogeneity, explanations break down entirely, becoming spatially incoherent and, on average, causally misleading. This degradation is not a general cost of federated training but a threshold effect tied to client heterogeneity, and we offer practical guidance for identifying when privacy-preserving deepfake detection can be deployed safely and when its explanations can no longer be trusted. Code and data partitions are available for reproducibility.

Muhammad Uzair Shahid, Muhammad Zabil Mehboob

independent researcher based in Pakistan

Explainable Deepfake DetectionGradient-Based AttributionFederated LearningDeepfake DetectionNon-IID Federated Learning
AskPDF
Oct 22, 2026

Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos

Recent advances in video generation have made synthetic videos increasingly realistic, placing greater demands on reliable AI-generated video detection. Existing artifact-based detectors typically identify generation artifacts as evidence for source prediction, yet they may either fail to recognize subtle artifacts or reach the correct source decision without faithfully identifying the evidence underlying it. In this work, we systematically investigate how to design and train effective artifact detectors and formulate artifact detection as a structured process comprising three complementary capabilities: Inspection Planning, which determines what should be examined; Evidence Verification, which verifies whether the inspected content exhibits genuine generation artifacts; and Evidence Aggregation, which integrates the verified evidence into the final source decision. Building on this formulation, we introduce Verus-Insight, trained with human-anchored full-process supervision and progressive capability training to strengthen both fine-grained artifact detection and video-level detection. We further introduce Verus-Bench, a benchmark with fine-grained human annotations of perceptible artifacts for evaluating artifact detection. Extensive experiments across diverse benchmarks demonstrate that Verus-Insight achieves strong performance in both fine-grained artifact analysis and AI-generated video detection, with substantial gains in recovering human-perceived artifacts. Further analyses reveal that the three capabilities are complementary yet distinct, and that Verus-Insight more reliably converts relevant inspection targets into supported artifact evidence without increasing spurious artifact claims.

Zhuoran Zhang, Yang Shi, Qixun Wang +11

Peking University · Kling Team · HKUST (GZ) +2

Synthetic Video Detection BenchmarksExplainable Deepfake DetectionDeepfake Detection
AskPDF
Oct 15, 2026

Deep Learning for Deepfake Image Detection: Comparative Model Evaluation and Gradient-Based Visual Attribution

Synthetic facial imagery has made the distinction between authentic and generated content increasingly important for digital forensics and online trust. This study examines an explainable deep-learning workflow for image-level deepfake detection using two contrasting classification strategies: a compact convolutional model trained from scratch and an ImageNet-pretrained MobileNetV2 model adapted through two-stage transfer learning. Experiments were conducted with the balanced 140k Real and Fake Faces dataset, comprising 140,000 facial images. Under the recorded validation protocol, the augmented from-scratch model reached 84.15% accuracy (loss 0.3625), compared with 95.90% accuracy (loss 0.1074) for the fine-tuned pretrained model. Gradient-weighted class activation mapping (Grad-CAM) was used to visualize image regions associated with predictions, and a Flask-based prototype was developed for side-by-side inspection. These observations support the practical value of pretrained visual representations in the studied setting while underscoring the need to interpret validation performance alongside dataset provenance, explanation limitations, and evaluation scope. The reported results are validation results, not held-out test estimates.

Saad Korchi, Abderrahim Waga

Euromed University of Fez, Fez, Morocco

Deepfake DetectionExplainable Deepfake DetectionTransfer Learning
AskPDF
Oct 13, 2026

An Initial Study of Physiological Markers for Deepfake Speech Detection

Conventional deepfake speech detectors primarily target synthesis artifacts and often degrade under unseen attacks or recording conditions. Human speech, however, contains physiological markers associated with respiration, phonation, and temporal coordination arising from the speech-production system that synthesizers may not reproduce faithfully. This motivates the hypothesis that deepfake speech can be detected by identifying inconsistencies in these patterns, which we test using 36 handcrafted physiological markers organized into respiratory, vocal, and temporal categories. We evaluate the marker vectors with logistic regression and SVM classifiers on pooled English recordings. The best in-domain system achieves a 21.40% equal error rate (EER), while logistic regression achieves 32.77% on the out-of-domain dataset pair. Since the markers describe specific speech-production properties, the logistic-regression coefficients indicate whether higher marker values push the classifier toward bona fide or deepfake speech. These results provide initial evidence that physiological markers offer a useful, interpretable signal for deepfake speech detection.

Vojtěch Staněk, Michal Frič, Kamil Malinka +1

Audio Deepfake DetectionExplainable Deepfake Detection
AskPDF
Oct 13, 2026

What Do Deepfake Audio Detectors Hear? From Self-Supervised Models to Audio LLMs

Real-world audio recordings for deepfake detection rarely consist solely of speech; they often are mixtures of speech and background events that themselves may also be synthetic. When processing these mixtures, it remains unclear whether detectors attend to the speech or the background event, and where their spectral evidence lies. We study this on the CompSpoof V2 database, whose mixtures pair independently real-or-fake speech and event components. Our results show that all systems detect fake events more accurately than fake speech. However, this performance gap is largely driven by poor generalization to an unseen fake speech domain, rather than a true difference in difficulty. Furthermore, sub-band probing reveals that the front-end encoder dictates where a countermeasure focuses its frequency evidence. To enable reliable deployment in real-world scenarios, future countermeasures should address out-of-domain generalization failures and carefully select front-end encoders aligned with their target acoustic evidence. Our source code and checkpoints are released at https://github.com/nii-yamagishilab/AntiDeepfake-AudioLLM.

Wanying Ge, Xin Wang, Junichi Yamagishi

National Institute of Informatics, Chiyoda-ku, Tokyo 101-8430, Japan

Audio Deepfake DetectionExplainable Deepfake DetectionOOD Generalization
AskPDF
Oct 12, 2026

EviStress: Evidence Stress Learning for Generalizable Face Forgery Detection with Textual Explanations

The rapid spread of face forgeries on the Web challenges the credibility of visual content. In practical Web environments, manipulated media originate from evolving generation pipelines and undergo diverse processing during dissemination, making reliable authenticity assessment under unseen manipulations and visual changes a critical challenge. We observe that a standard LoRA-adapted CLIP detector exhibits uneven patch-level decision dependence, concen trating a disproportionate share of class-specific relevance on a small fraction of visual patches. To improve robustness to variations in such highly dependent evidence, we propose EviStress, a two-stage framework for generalizable face forgery detection with textual explanations. In the first stage, Evidence-Targeted Patch Perturbation (ETPP) estimates patch dependence from global, relational, and semantic cues and assigns positively correlated perturbation probabilities, explicitly stress-testing highly dependent visual evidence during training. We further introduce Discriminative Variation Preservation (DVP), which constrains the residual between clean and perturbed representations to retain authenticity discriminative information. In the second stage, Intrinsic Evidence Instruction Tuning (IEIT) transfers the adapted CLIP encoder into LLaVA as its vision tower and performs parameter-efficient multimodal instruction tuning, enabling authenticity prediction and textual explanation directly from the learned forgery-sensitive representation without an external detector. Experiments demonstrate improved cross-dataset and cross-method generalization and corruption robustness, with the multimodal model providing authenticity predictions and human-readable explanations.

Jiuyao Jing, Xuanyu Yi, Yu Zheng +1

School of Cyber Engineering, Xidian University, Xi’an, China

Image Forgery DetectionDeepfake DetectionExplainable Deepfake DetectionVLM Adaptation
AskPDF
Oct 12, 2026

Not Every Cue Is Evidence: Cue Supportability for Forensic Distillation in Face Forgery Detection

Explainable face forgery detection requires not only correct judgments but also forensic evidence supported by the input image. However, training cues are typically derived from the forgery generation pipeline. Since images available to the model are of limited quality and resolution, it is difficult to observe the fine-grained traces these cues refer to. Training methods that further supply such cues as privileged supervision exacerbate the problem, as the student is taught to articulate evidence it cannot perceive. The student consequently resorts to templated or over-generalized expressions, giving rise to the correct-answer, wrong-evidence (CAWE) failure. We propose a dual supportability audit that filters privileged cues before distillation. Each candidate cue must be predictable from the remaining privileged context and causally tied to high-attribution visual regions in the current image. Only cues satisfying both conditions receive substantial distillation weight, preventing unsupported details from leaking into the student. Experiments across eight benchmarks show that our method maintains or improves detection accuracy while significantly raising explanation faithfulness compared to existing paradigms.

Binjia Zhou, Dawei Luo, Shuai Chen +7

School of Software Technology, Zhejiang University · Ant Group · College of Computer Science and Technology, Zhejiang University +1

Explainable Deepfake DetectionDeepfake DetectionLearning Using Privileged Information
AskPDF
Oct 7, 2026

MSU Team at the Explainable Deepfake Detection Challenge 2026: Grounded Artifact Evidence for Deepfake Detection

Recent advances in generative image models have made many manipulated images highly realistic, raising the need for detectors that are not only accurate but also able to provide visual evidence for their decisions. In this paper, we present our solution to the Explainable Deepfake Detection Challenge [2] on the XPlainVerse dataset [1], where systems are required to predict whether an image is real or fake and generate both complex and simple explanations grounded in visible forensic cues. Our method follows a modular detection-and-explanation design. For the real/fake decision, we build a multi-backbone detector that combines several DINOv3 models with Mesorch manipulation-localization features, bringing together pretrained visual representations, DCT-aware cues, and multi-scale forensic information. To inject explanation evidence into the detector, we use a Grounding-DINO-based pseudo-mask generation pipeline that converts local artifact descriptions from training explanations into weak patch- level supervision for an Artifact Evidence Map. We further introduce a local patch-level contrastive objective that separates artifact and authenticity evidence in the detector feature space without requiring paired images or pixel-level manipulation masks. For language output, we use class-conditional Qwen3-VL models to generate complex explanations for fake and real predictions, followed by a GRPO-optimized text simplification model. The proposed methods were trained and evaluated on the challenge subset of XPlainVerse. On the full test split, our submission achieves 0.9349 detection accuracy, 0.5571 explanation score, and a 0.7456 final challenge score.

Artem Filippov, Aleksandr Gushchin, Kirill Koltsov +2

Lomonosov Moscow State University Moscow, Russia · MSU Institute for Artificial Intelligence Moscow, Russia

Deepfake DetectionExplainable Deepfake DetectionImage Forgery Localization
AskPDF
Oct 2, 2026

Interpretable Deepfake Detection in Videos via Explicit Forensic Features and Temporal Modeling

Deepfake detection in videos remains challenging, as manipulated content may appear visually consistent at the frame level while exhibiting subtle temporal inconsistencies. This paper introduces an interpretable deepfake detection framework that models spatially and temporally coherent facial features in video sequences. Unlike end-to-end deep models relying on implicit representations, the proposed approach explicitly encodes physically grounded forensic cues, enabling transparent analysis and improved multi-dataset generalization. The pipeline transforms videos into identity-consistent facial trajectories, segments them into fixed-length temporal windows, and represents each frame using 68 structured descriptors spanning four complementary domains: photometric, textural, geometric, and compression-based features. These descriptors provide a compact multi-domain representation of manipulation artifacts and are processed by a Long Short-Term Memory (LSTM) network to capture temporal dependencies and subtle irregularities. Evaluation on four benchmark datasets, FaceForensics++, Celeb-DF v2, a curated subset of the DeepFake Detection Challenge (DFDC), and DeeperForensics, yields strong and consistent F1-scores of 98.0%, 91.0%, 97.6%, and 96.2%, respectively. The approach also demonstrated a good cross-dataset generalization, providing a robust and interpretable solution for video deepfake detection.

Chahira Benhama, Mohand Saïd Allili, Assia Hamadene

LARIVIA laboratory Dep. of Computer science and Eng. University of Quebec in Outaouais Gatineau, QC, Canada · LARIVIA laboratory and Mixed Research Unit INRS-UQO University of Quebec in Outaouais Gatineau, QC, Canada

Video ForensicsDeepfake DetectionExplainable Deepfake DetectionDigital Forensics
AskPDF
Sep 30, 2026

SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Models

Audio language models (ALMs) are increasingly used for audio deepfake detection (ADD), yet existing benchmarks assess their verdicts or rationale plausibility without verifying the underlying acoustic evidence. To address this issue, we first introduce spoofing evidence-grounded audio reasoning (SEAR), a four-task AQA benchmark to evaluate ALM-based ADD through acoustic evidence identification and quantification, deepfake detection, and forensic rationale generation. We further propose a bona-fide-based acoustic evidence agent (BAEA), which equips a frozen ALM with controlled acoustic tools under fixed or adaptive evidence-acquisition policies. Experiments with six ALMs reveal a clear gap between plausible rationales and verifiable acoustic evidence reasoning, while BAEA-Fixed improves final verdicts and forensic rationales on both evaluation partitions. Controlled interventions further show that misleading evidence degrades both detection and grounding performance.

Rong Wan, Suliu Qin, Jiaxi Li +5

University of Surrey · Singapore University of Technology and Design · Guangxi University +1

Audio-Language Model EvaluationAudio Deepfake DetectionEvidence-Grounded ReasoningExplainable Deepfake DetectionAudio-Language Models
AskPDF
Sep 30, 2026

A Generalizable and Explainable Framework for Synthetic Video Detection Using First-Digit Gradient Statistics

AI video generators have not only become harder to detect but are used to generate a diverse set of scenarios from landscapes to street views to animal videos. This creates a problem where CNN-based detectors are effective but offer no insight into their inner workings, while forensics-based detectors are often pretrained for a set scenario or become too complex to derive meaningful insights. We present a novel approach to AI video detection using Sobel gradient values analysed with the first-digit law. Using linear discriminant analysis, we visualise the discriminatory signal, while a multi-layer perceptron is used for classification. The detection method has no generator- or scenespecific features, and the model has no knowledge of container formats, codec, bitrate, or compression artefacts. The model is trained and tested on GenBuster-200K, GenBusterBench, GenVA, FaceForensics++ C23, and CelebDF. We also show how zero-shot detection fails even though the feature set carries a discriminatory signal.

Sidharth Shanu, Gautam Kumar, Tej Singh

B.Tech CSE IIT Jodhpur, India · School of Automation & Robotics GGSIPU, New Delhi, India · Centre for Artificial Intelligence MITS Gwalior, India

Explainable Deepfake DetectionDeepfake Detection
AskPDF
Sep 28, 2026

Look Before You Judge: Training-Free Region Mining for Grounded and Explainable Deepfake Detection

Multimodal large language models (MLLMs) can explain deepfake verdicts in natural language, but such explanations are not necessarily visually grounded in the visual evidence underlying the prediction. A model may describe plausible artifacts inferred from language priors rather than from image evidence. Existing grounding methods improve visual reliance through decoding or attention interventions, but they generally strengthen grounding over the entire image, making them ill-suited for forensic artifacts that are subtle, spatially localized, and image-dependent. We propose Look Before You Judge, a training-free framework that formulates explainable deepfake detection as a sequential evidence acquisition process. Instead of directly predicting image authenticity from holistic visual reasoning, our framework first identifies image-specific candidate evidence regions by contrasting the MLLM's decoder-to-visual attention between an original image and its Gaussian-blurred counterpart. The identified regions are then inspected individually, and the resulting local evidence is integrated with the global image context before reaching a final verdict. The framework operates without manipulation masks, external forensic models, or parameter updates, making it directly applicable to off-the-shelf MLLMs. Across five open-source MLLMs on TriDF and MMTD-Set, our framework improves detection accuracy by up to 12.8%, reduces CHAIR by up to 33.4% and hallucination rate by up to 21.3%, and outperforms representative training-free decoding and attention methods.

Chia-Ling Chen, Yu-Ting Ta, Jian-Yu Jiang-Lin +8

National Taiwan University · National Tsing Hua University · National Yang Ming Chiao Tung University

Explainable Deepfake DetectionDeepfake DetectionVisual GroundingVLM Hallucination MitigationMultimodal Deepfake Detection
AskPDF
Sep 28, 2026

DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detection

Deepfake detection methods have become increasingly effective yet most provide limited insight into the evidence behind their predictions. However, in forensic settings users also need to know which manipulation cues support the decision and where they appear. Existing explainability methods only partially address this need since localization-based approaches lack semantic descriptions while language-based explanation methods are only weakly grounded in visual evidence. In this work, we propose DF-CBM, a region-aware concept bottleneck model for explainable deepfake detection. DF-CBM builds a compact vocabulary of manipulation-related concepts from textual artifact annotations and links each concept to plausible facial and boundary regions. It then predicts these concepts from visual features using a concept-specific masked attention mechanism guided by parsed facial masks and the final real/fake decision is made from the predicted concept bottleneck. Our experiments show that DF-CBM outperforms concept-based baselines in concept prediction and deepfake classification while remaining competitive with state-of-the-art black-box detectors. Finally, qualitative results and intervention analyses demonstrate that DF-CBM provides spatially grounded concept evidence and enables counterfactual explanations of how individual manipulation concepts influence the final prediction. Our code is available at: https://github.com/GeorgeTsoumplekas/DF-CBM.

Georgios Tsoumplekas, Vazgken Vanian, Alexandros Doumanoglou +4

Department of Networks and Digital Media, Kingston University London, UK · Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece · Department of Computer Science, Kingston University London, UK

Concept Bottleneck ModelsExplainable Deepfake DetectionDeepfake Detection
AskPDF
Sep 23, 2026

ASAP: Visual Analytics for Identifying and Analyzing Image Patterns in AI-generated Images

Generative image models can produce highly realistic images, raising concerns about potential misuse in creating deceptive content. Current deepfake approaches face several challenges, including limited generalizability, lack of interpretability, and poor actionability. To help address these, we present ASAP, an interactive visualization system designed to empower users in the analysis and summarization of deceptive patterns in AI-generated images. ASAP introduces a novel CLIP-adapted image encoder that generates interpretable representations, enabling the extraction of influential pixel regions via calculated masks. This approach facilitates the identification of key deceptive features through influence measurement techniques. These backend techniques are integrated into a visual analytics dashboard that allows users to quantify and analyze authenticity-indicative patterns in image collections containing both authentic and AI-generated images. This approach also supports the comparative analysis of various generative models, including GANs and diffusion models. We demonstrate ASAP's efficacy through a user study and two application scenarios using established fake image detection benchmarks, showcasing its ability to effectively extract and quantify deceptive patterns.

Jinbin Huang, Yuki Ueno, Chen Chen +4

Arizona State University, AZ, US · University of Maryland, MD, US · Fujitsu Research of America, PA, US +1

Image Forgery DetectionExplainable Deepfake DetectionAI-Generated Image Detection
AskPDF
Sep 15, 2026

ForensicZoom: Adaptive Visual Inspection with Multimodal LLMs for Industrial-Grade Face Forgery Detection

Reliable face forgery detection is critical to the security of online identity verification systems, where missed attacks compromise security and excessive false positives disrupt legitimate users. Specialized forensic detectors achieve strong detection performance but provide limited interpretability, while multimodal large language models (MLLMs) offer strong semantic understanding and interpretable reasoning yet remain substantially weaker for face forgery detection. We argue that a key limitation lies in how visual evidence is acquired: subtle forensic artifacts may be poorly represented at standard resolution, while uniformly processing all cases at higher resolution is computationally inefficient. We therefore introduce ForensicZoom, an industrial-grade MLLM framework for adaptive visual inspection. ForensicZoom first equips a general-purpose MLLM with forensic-aware visual representations and aligns the language model with these features. Its central mechanism, NEED_ZOOM, enables the model to autonomously request magnified views of suspicious regions when the initial evidence is insufficient, turning fixed-pass classification into adaptive multi-round forensic reasoning. The zoom behavior is learned through reward shaping that balances detection accuracy with unnecessary visual inspection, concentrating additional computation on difficult cases. A final attribution optimization stage improves natural-language forensic reports while preserving detection performance. On large-scale industrial identity verification data, ForensicZoom achieves over 97% TPR at 0.1% FPR, substantially outperforming both specialized detectors and existing MLLM-based methods while producing actionable forensic attributions. These results demonstrate that ForensicZoom can provide an effective path toward accurate, interpretable, and scalable MLLM-based face forgery detection.

Hang Zhou, Yiming Tang, Kun Yu +3

Alibaba

Image Forgery DetectionDeepfake DetectionExplainable Deepfake DetectionMultimodal Large Language ModelsActive Visual Perception
AskPDF
Sep 14, 2026

PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection

As generative models continue to advance, AI-generated content (AIGC) is becoming increasingly realistic, weakening the artifact cues commonly exploited by existing detectors. Nevertheless, faithfully reproducing the physical behavior of real-world events remains challenging for current generators. We therefore explore detecting AIGC by assessing whether the depicted event satisfies measurable constraints derived from physical laws. We introduce PIVOT, a physics-grounded AIGC detector, instantiated here for audio-video clips, that estimates physical quantities from video and audio, selects physical laws relevant to each clip, and verifies their measurable constraints. Beyond a real/fake decision, PIVOT returns supporting evidence that records the verification outcome, relevant time window, and supporting quantities for each applicable law. Although instantiated and evaluated here on audio-video data, the framework can, in principle, extend to other AIGC modalities whenever the physical quantities required for verification can be estimated reliably. We also introduce PhysForensics-Bench, comprising paired real and generated audio-video clips from nine event-centric scene families and two recent audio-video generators. On PhysForensics-Bench, PIVOT achieves 70.30% accuracy and 64.29% F1 score on Real+Seedance, and 72.16% accuracy and 65.82% F1 on Real+VEO. In comparison, direct inspection with Gemini 3.1 Pro obtains 53.96% accuracy and 60.09% F1 on Real+Seedance, and 57.22% accuracy and 63.44% F1 on Real+Veo. These results demonstrate the practical promise of physical-consistency verification as a structured and inspectable source of evidence that complements artifact-based AIGC detection.

Bo Zheng, Kangran Zhao, Xiaoyu Zhang +7

School of Artificial Intelligence, Chinese University of Hong Kong, Shenzhen, Shenzhen 518172, China · Nanjing University of Posts and Telecommunications, Nanjing 210023, China · University at Buffalo, State University of New York, New York 14260, USA

Explainable Deepfake DetectionDeepfake DetectionPhysical Reasoning in Video
AskPDF
Sep 8, 2026

Audio Deepfake Detection Using Temporal Coherence Analysis

The proliferation of AI-generated audio (so-called "deepfake" audio) poses significant threats to information integrity, from voice cloning fraud to synthetic music copyright disputes. We present a temporal coherence analysis framework built upon Contrastive Language-Audio Pretraining (CLAP) embeddings that spans speech, instrumental music, and music with vocals. By computing pairwise cosine similarities between audio segment embeddings and extracting statistical features from the resulting distributions, we train lightweight ensemble classifiers that reliably distinguish authentic from synthetic audio. Our work provides an interpretable, computationally efficient alternative to common deep learning methods while still achieving competitive performance across speech and music domains. Further, we reveal two notable empirical findings about audio deepfakes: (1) a feature-label inversion phenomenon in which 21 of 29 statistical features reverse their discriminative direction between training and in-the-wild deployment, and (2) a speech--music direction reversal in which entropy discriminates in opposite directions for speech and music deepfakes.

Justin D. Norman, Sarah Barrington

University of California, Berkeley

Audio Deepfake DetectionExplainable Deepfake DetectionAI-Generated Music DetectionTemporal Consistency
AskPDF
Sep 8, 2026

From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection

Speech deepfake detectors usually emit one score per utterance, but a borderline score does not reveal why two examples differ during retrospective error analysis. We ask whether a final score can be calibrated from component fields while keeping those fields visible for inspection. We build a decision record with a passive detector score and a score from a probe applied to a marked copy. It also includes retrieval support held out of the evaluated family, a margin from a support-set profile, and raw neighbor closeness. A cross-fit calibrator combines these fields and two differences between raw scores into one final score. On matched ASVspoof development data, the calibrated record reduces equal error rate (EER) by 3.48 percentage points relative to the fixed retrieval-augmented rule. It reaches 8.43% EER, whereas a passive WavLM baseline reaches 6.71% on the same subset. The record is therefore not the strongest detector in this comparison. Its value is to retain inspectable component fields while producing one scalar score for retrospective diagnosis.

Mengzhe Geng, Yujia Lu, Manuela Kunz +1

National Research Council Canada · The Chinese University of Hong Kong

Audio Deepfake DetectionExplainable Deepfake DetectionASVspoof
AskPDF
Sep 3, 2026

ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detection

Audio deepfake detection is commonly formulated as clip-level binary classification of single-domain audio. However, real-world manipulated audio can exhibit mixed authenticity, where genuine and manipulated cues coexist across temporal transitions, overlapping sources, or both. This setting requires not only detecting manipulated audio but also localizing the components that provide evidence for the decision. We propose ToolDF, a tool-integrated reasoning framework for mixed-authenticity audio deepfake detection. ToolDF employs an audio large language model as an orchestrator trained with supervised tool-use trajectories. It adaptively analyzes the audio scene, selectively performs source separation, routes components to domain-specific experts, and aggregates their evidence into an interpretable verdict. We further introduce a mixed-authenticity ADD benchmark covering temporal transitions, acoustic overlaps, and hybrid mixtures. Experimental results show that ToolDF achieves the best overall performance on composite-type detection, achieving macro-F1 gains of 3.72 and 14.39 points over the strongest monolithic baseline and a fixed pipeline, respectively, while providing interpretable evidence localized to temporal regions and acoustic sources. Our source code and dataset are publicly available online.

Taewoo Kim, Young Han Lee, Nam In Park +1

Multi-Modal Research Center, KETI, South Korea · Digital Analysis Section, National Forensic Service, South Korea · Department of Artificial Intelligence, Korea University, South Korea

Audio Deepfake DetectionExplainable Deepfake DetectionAudio Reasoning
AskPDF
Aug 21, 2026

Explainable Deepfake Detection with Feature-robust Augmentation and Evidence-grounded Explanation Optimization

Explainable deepfake detection extends binary classification by requiring models to not only predict authenticity but also provide interpretable justifications. This expanded scope is critical in practice, where users like forensic analysts need insight into the rationale behind the detection. Despite advancements, current approaches suffer from two critical deficiencies: (1)vulnerability to image quality degradation: detection accuracy plummets on low-quality samples, while naive augmentation strategies may induce feature drift and impair performance as diversity expands. (2) factually flawed explanations: explanation models may omit manipulation evidence or hallucinate irrelevant details, undermining interpretability. To address it, we propose a framework with two innovations. For robust deepfake detection, we introduce Feature-robust Augmentation, which comprises diversified degradation-aware augmentation strategies, and a supervised contrastive learning pattern paired with a mean-teacher architecture that stabilizes features against augmentations through consistency constraints. For explanation, we devise an evidence-grounded preference optimization process that guides model to prioritize genuine manipulation traces by learning from chosen-rejected explanation pairs, where rejected samples are constructed via evidence omission or irrelevant information injection. The proposed approach wins the first place in ACM Multimedia 2026 Explainable Deepfake Detection Challenge.The code is available at https://github.com/oceanflowlab/EDD.git.

Zhu Xu, Jiaqi Tang, Pokai Chen +2

Wangxuan Institute of Computer Technology, Peking University Beijing, China

Explainable Deepfake DetectionDeepfake DetectionEvidence-Grounded GenerationPreference Optimization
AskPDF
Aug 19, 2026

PATE-Forensics: Perception-as-Tool for Explainable Deepfake Forensics with General-Purpose MLLMs

Existing explainable deepfake forensic methods typically rely on task-adapted MLLM to jointly address detection, localization, and explanation. Inspired by agent-style tool use, we instead introduce a Perception-as-Tool paradigm and instantiate it as PATE-Forensics, which architecturally decouples detection and localization from explanation generation while coupling detection and localization as tightly as possible within a forensic perception tool. The DINOv3-based tool couples a multi-granularity detection module that integrates global, patch-level, and segment-level evidence with a cue-guided localization module by spatializing the patch-level and segment-level evidence into forgery score maps that guide dense mask prediction. The original image and forensic perception outputs produced by the tool form structured forensic context for a general-purpose MLLM, which is guided by prompt constraints to generate explanations without task-specific fine-tuning. On DDL-X Track 3, PATE-Forensics achieves the best official score of 0.89, outperforming the second-ranked team by 0.19 points. Our code is available at https://github.com/yqli00000/PATE-Forensics.

Yaqi Li, Jielun Peng, Yabin Wang +2

Harbin Institute of Technology

Explainable Deepfake DetectionDigital Image ForensicsImage Forgery Localization
AskPDF
Aug 7, 2026

Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection

The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety. However, existing deepfake video benchmarks provide limited coverage of recent synthesis methods and generally lack reliable fine-grained textual annotations. Meanwhile, conventional detectors and multimodal large language models (MLLMs), whether operating as a single model or relying on a single analytical perspective, often fail to capture subtle forgery artifacts, limiting their generalization to emerging AI-generated methods. To address these limitations, we introduce FaceVid-Forensics-100K, a large-scale deepfake video dataset comprising 100,000 videos and spanning 33 synthesis methods across face swapping, face reenactment, and entire-face synthesis, including recent generators such as Seedance 2.0. The dataset provides fine-grained textual annotations of visual observations and verdict-consistent forensic explanations, automatically synthesized through a multi-model aggregation and conflict-resolution pipeline powered by advanced MLLMs. Building on this benchmark, we propose a multi-agent forensic reasoning framework that employs four specialized domain-expert agents to independently analyze forgery cues from four perspectives: texture, lighting, motion, and physics. A judge agent then reconciles their reports to produce a final prediction together with an explanation. Extensive evaluations on out-of-domain test sets show that, despite being composed entirely of small open-source MLLMs, our framework outperforms all methods including closed-source GPT and Gemini models and ranks first across all reported metrics on this benchmark. The project page is available at https://xavierjiezou.github.io/ARGUS/.

Xuechao Zou, Shun Zhang, Kai Li +6

Beijing Jiaotong University · Tsinghua University · Ant Group

Explainable Deepfake DetectionDeepfake DetectionMulti-Agent Reasoning
AskPDF
Aug 5, 2026

HexMIL: Hierarchical Attention MIL for Ante-Hoc Explainable Detection of AI-Manipulated CT Volumes

The emergence of medical deepfakes, i.e., medical images manipulated by deep generative models, poses a significant threat to clinical workflows. However, existing detectors suffer from two critical limitations: poor generalization to unseen generative architectures for manipulation detection and lack of interpretability. In this context, we present HexMIL (Hierarchical EXplainable Multiple Instance Learning), a mask-free medical deepfake detector that simultaneously addresses both limitations using only binary volume-level supervision. HexMIL decomposes each CT volume into a two-level hierarchy of patches and slices, aggregated via independent Gated Attention modules whose weights are directly combined into a full-resolution 3D attention volume that localizes the manipulated sub-region without any pixel-level annotation. Unlike post-hoc methods such as Grad-CAM, HexMIL's attention weights constitute the exact forward computation driving the classification decision, providing ante-hoc and structurally faithful spatial attribution. We evaluate HexMIL on M3DSynth and CT-GAN datasets under a rigorous cross-generator generalization protocol, training on a single generative architecture and testing on unseen ones. HexMIL outperforms all baselines by +9.1+9.1 AUC and +9.4+9.4 F1 in out-of-domain classification, and achieves the best average IoU and Pointing Game score in localization. Project page: opontorno.github.io/hexmil.

Orazio Pontorno, Luca Guarnera, Zahid Akhtar +1

Department of Mathematics and Computer Science, University of Catania, Catania, Italy · Department of Electrical and Computer Engineering, State University of New York Polytechnic Institute, Utica, NY, USA

Explainable Deepfake DetectionMedical Image Anomaly DetectionDeepfake DetectionMedical Image LocalizationMultiple Instance Learning
AskPDF
Aug 4, 2026

V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors

As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors as black boxes, while the latent forgery-discriminative knowledge inside them remains largely unexplored. Instead of continuing to rely on resource-intensive full-model retraining to steadily improve detection performance, we ask whether video forgery detection can also be achieved by uncovering and activating sparse forensic knowledge within the detector. We find that forgery-discriminative knowledge is not uniformly distributed across the full representation space, but is concentrated in a sparse set of functionally specialized neurons. Based on this insight, we propose a video forgery-intrinsic neuron discovery (V-FIND) framework. V-FIND first localizes critical layers that exhibit pronounced discrepancies between real and forged videos, and then identifies latent anchor neurons that consistently carry forgery-discriminative signals, organizing them into a compact forensic subspace. With the original backbone frozen and only a lightweight linear classifier trained, this subspace still delivers strong detection performance across multiple external benchmarks for generated videos. Further neuron intervention experiments provide direct evidence for the functional specificity of the discovered neurons. Overall, these results suggest that video forgery detectors contain sparse, extractable, and reusable forgery-discriminative knowledge, offering a new perspective on understanding and exploiting their intrinsic forensic capability.

Shichao Kan, Chengpeng Hong, Jingtong Dou +8

Central South University · The University of Sydney · NExT++ Research Centre, National University of Singapore

Explainable Deepfake DetectionMechanistic InterpretabilityDeepfake Detection
AskPDF
Jul 29, 2026

Improved Robustness in AI-Generated Music Detection

AI music generators leave predictable spectral artifacts determined by their architecture. Existing detectors exploit these artifacts with near-perfect accuracy on raw generated tracks, but their performance collapses under simple audio manipulations, such as speed modification or pitch shifting. We address this open robustness problem by introducing a frequency-scaling-invariant detection pipeline that aims to prevent this kind of attack by design. Our method maps audio onto a log-frequency axis via a log-STFT remapping. A single learned cross-correlation filter, combined with max-pooling, provides shift invariance at inference time. Training uses a hybrid loss that jointly supervises binary detection and artifact-peak localization, regularizing boundary weights. Because robustness to speed change is built in by design, the detector is also interpretable: it outputs both a binary decision and an estimate of the applied speed-change factor.

Emile Dugelay, Thomas Barand, Aurélien Laouar +3

Department of Computer Science, Ecole Centrale de Lyon, France · Deezer Research, Paris, France

Audio Deepfake DetectionExplainable Deepfake DetectionAI-Generated Music DetectionInvariant Representation Learning
AskPDF
Jul 29, 2026

ThinkOmni: A Reasoning-Driven Omni-Modal LLM Framework for Audio Forgery Detection and Localization

Existing audio forgery detection and localization (AFDL) methods often overfit dataset-specific low-level artifacts, limiting their generalization to subtle, localized, and unseen manipulations. Recent audio large language model (ALLM)-based approaches cast AFDL as question answering but still model forensic evidence implicitly, without linking manipulation cues to predictions. To bridge this gap, we propose ThinkOmni, a reasoning-driven omni-modal large language model that jointly performs explicit forensic reasoning, spoofing detection, and temporal manipulation localization. To enable explicit reasoning supervision, we construct Forensic-Aware Chain-of-Thought (FACoT), a 100K-sample dataset with structured forensic evidence and reasoning annotations. Leveraging FACoT, we introduce Forensic-Aware Modality-Incremental Learning (FMIL), which progressively aligns semantic, acoustic, and spectral-visual representations with the LLM backbone to capture complementary forensic cues. We further propose Forensic-Consistent Multi-task Loss (FCML), which combines weighted cross-entropy with an adaptive localization loss to coordinate reasoning generation, spoofing detection, and temporal localization. Extensive experiments show that ThinkOmni achieves strong cross-dataset generalization in both detection and localization. Code, models, data, and inference examples are available at https://beyond0814.github.io/ThinkOmni/.

Yuxiong Xu, Kaiqing Lin, Bin Li +2

Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Media Security, Shenzhen University · Afirstsoft Technology Group Co., Ltd.

Audio Deepfake DetectionExplainable Deepfake DetectionAudio-Language Models
AskPDF
Jul 28, 2026

LaP-Forensics: Latent-Pixel Consistency Guided Multimodal Reasoning for Deepfake Detection

Recent generative models can produce images with few obvious visual artifacts, weakening detectors and explanations that rely only on surface appearance. We present LaP-Forensics, a multimodal framework that augments RGB semantics with reconstruction-based forensic evidence. A frozen Stable Diffusion DDIM inversion-reconstruction model provides a fixed reconstruction reference, and its residual map measures local compatibility with that reference. Independent projectors encode the RGB image and residual map before a structured Where-What-Why model predicts a textual analysis and an artifact mask. Supervised fine-tuning is followed by Group Relative Policy Optimization (GRPO), whose reward combines mask overlap with output-structure and evidence-reference terms. These text-side terms encourage the model to refer to the consistency map but do not constitute a verifier of free-form textual truth. A separate image-level head fuses RGB and DDIM-residual class features. Experiments show cross-generator detection on UniversalFakeDetect and competitive artifact localization on the official SynthScars benchmark. Controlled cue-construction, inversion-horizon, component, reward-term, and counterfactual analyses support the utility of the residual stream under the evaluated settings, while free-form textual faithfulness and reliability under post-processing remain open limitations.

Can Wang, Yuhao Wang, Yushe Cao +2

The Hong Kong Polytechnic University, Hong Kong, China · University College London, London, United Kingdom · Tsinghua University, Beijing, China +2

Multimodal Deepfake DetectionDigital Image ForensicsExplainable Deepfake DetectionImage Forgery LocalizationDeepfake Detection
AskPDF
Jul 23, 2026

Toward Interpretable Speech Deepfake Detection using Artifact-Specific Experts and Calibrated Detection Scores

In this work, we propose an interpretable framework for speech deepfake detection based on artifact-specific expert models. Rather than relying on black-box decisions, the framework provides human-understandable evidence, which is critical in high-stakes settings. Each expert is trained to detect a specific speech synthesis artifact, and its output is calibrated into a log-likelihood ratio that serves as an interpretable evidence score. We evaluate five artifact-specific experts and show that, with proper calibration, they can capture their target artifacts and produce meaningful evidence. Importantly, each expert estimates only the presence of its assigned artifact rather than directly performing the final decision. Their outputs are aggregated into an ensemble to produce the actual real-versus-fake classification, while maintaining interpretability by indicating how strongly each expert supports or contradicts a fake classification. Results show that artifact-specific experts capture interpretable signals of synthetic speech across multiple generation pipelines.

Viola Negroni, Xin Wang, Wanying Ge +3

DEIB, Politecnico di Milano Milano, Italy · National Institute of Informatics Tokyo, Japan

Audio Deepfake DetectionExplainable Deepfake DetectionSpeech Processing
AskPDF