Overview

Deepfake detection studies how to distinguish authentic images, video, and audio from manipulated or AI-generated content, a capability important for verification and security. Detectors look for spatial and frequency artifacts, temporal or physiological irregularities, and inconsistencies across audio, video, and semantic or physical cues; some also use pretrained foundation models, vision-language reasoning, or watermarks. Beyond classifying media, methods increasingly aim to localize altered regions or time spans, identify sources, and provide evidence-grounded explanations. A central challenge is that strong results on familiar benchmarks often fail to transfer to unseen generators, real-world conditions, or degraded media, while shortcuts, calibration, and fairness complicate reliable deployment.

Latest papers

264 papers23 papers in the last four weeks, down 30% on the four weeks before. 0.2% of all new papers.

Nov 16, 2026

FaceJev: Direct Visual Decisions for Face Forgery Detection

Face forgery detection methods often perform well on seen manipulations but generalize poorly to unseen ones. Multimodal Large Language Models (MLLMs) can recognize facial parts and assess their visual plausibility. Existing MLLM-based methods typically express these judgments through textual explanations, but seldom treat individual part decisions as explicit learning targets. We present FaceJev, an MLLM-based method for face forgery detection through direct visual decisions. Following the Jev formulation, FaceJev answers eight independent questions about facial parts using a shared image encoding and reads anomaly probabilities from the native answer logits. A face is classified as forged if any part is predicted to be abnormal, directly linking the detection result to the part decisions. We construct PartForensics, a dataset of approximately 160k images with binary anomaly targets for the eight facial parts, to supervise these decisions. We further propose FS-GRPO, which optimizes each part decision through an exact reward comparison with its alternative, using both detection and part rewards. FaceJev outperforms the strongest baseline by 7.25 percentage points on unseen manipulations. Extensive ablation studies validate our design choices and the effectiveness of the main components.
Nov 16, 2026

WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection

Recent advances in video generation call for reliable detection grounded in explicit forensic evidence. However, current methods primarily depend on single-pass chain-of-thought reasoning that overlooks brief or localized artifacts, or on predefined multi-agent workflows that offer limited flexibility in selecting relevant inspections. Even with adaptive investigation, optimizing the investigation policy alone does not directly improve the forensic capabilities of fixed experts. We introduce WeVisForensics, an agentic framework in which a main investigator agent coordinates a self-evolving library of forensic inspector sub-agents spanning visual and audio cues. The investigator learns which artifact type to examine, over which window, and when to conclude, and these interactions provide shared feedback for both levels of agents. Our dual-timescale policy optimization strategy, DTPO, closes this loop through fast reinforcement learning of the investigator and slower refinement of the inspectors, guided by annotated artifact intervals, to report subtle artifacts they once dismissed. Furthermore, we curate ForenCue-30K, combining role-specific forensic annotations and interaction trajectories to supervise individual inspections and their coordination, with an accompanying reinforcement-learning pool. Experiments show that WeVisForensics averages 95.2% detection accuracy across in-domain, out-of-domain and agentic benchmarks, 9.0% above the strongest prior detector, while grounding its verdicts in localized evidence.
Nov 16, 2026

VAE Rhythm: Temporal Decoding Traces for AI-Generated Video Detection

Visible artifacts are an unreliable cue for detecting generated videos, because newer generators learn to remove them. We instead detect a trace left by the generation pipeline itself. Most video generators decode latents with a 3D causal VAE that groups consecutive frames in time, so the fidelity of generated frames rises and falls periodically with their position in a group. We call this periodic trace VAE Rhythm. Real videos are captured frame by frame and do not have it. To reveal it without training, we propose a phase scan. The scan reconstructs a clip with an off-the-shelf VAE from successive start offsets and measures the periodicity of the reconstruction error across these offsets. We find VAE Rhythm in most of the 39 variants of 31 generators we test, including the closed-source Sora, Kling 3.0 and Seedance 2.0. We use the rhythm as a zero-shot score, as a plug-in for existing detectors and as a data engine that pairs real videos with their VAE reconstructions to train our detector CaDet. On DF26, the training-free rhythm score outperforms all 15 retrained baselines, and as a plug-in it improves all 19 tested detectors by 6.7% to 23.7% AUROC. CaDet achieves the best AUROC on AIGVDBench, DF26 and three 2026 closed-source models, and its variant trained without any generated video still exceeds 90% on AIGVDBench.
Nov 13, 2026

Lasso: Towards Sustainable AI-Generated Media Detection with Intel QAT On-Chip Compression

Synthetic text, images, and video are rising. Software-only detectors are power-hungry, too slow, and costly, and do not scale with demand. When software cannot scale, historically hardware often comes to the rescue. We perform the first reverse engineering of a compression accelerator--Intel QuickAssist Technology (QAT) microarchitecture and--find different amount of time on each, a novel data structure-dependent property. Using this information, we then build Lasso, a low-cost, high-performance detector for AI-generated content that turns the accelerator into a measuring instrument. For text detection, Lasso achieves 100% accuracy on original DetectRL text and retains 92% average accuracy after paraphrasing, compared with 78% for Binoculars and 55% for DetectGPT. Across original, paraphrased, and perturbed text, it achieves 82% average accuracy, outperforming all five baselines. With topic, length, and formatting matched, accuracy reaches 95% for instruction-tuned generators, including when the tested generator is unseen. On RAID, accuracy averages 82% when trained on one generator and tested on another, and 74% across eight held-out domains. Detection takes 0.74 microseconds, a speedup of at least 83,784x across five baselines. At the same time, Lasso consumes over 99% less energy per document than both Binoculars and DetectGPT. At the same time, Lasso detects AI-generated videos, software code, and images with 67.5%, 70% and 78% accuracy, respectively, with low latency and power opening avenues for practical real time and edge device detection of multimodality AI artifacts for the first time. No other compared technique supports detection across all four modalities: text, video, images, and code.
Nov 11, 2026

Reality Perception Gap: Are AI-Manipulated Video Detectors Ready for the Real World?

AI-manipulated video detectors are typically evaluated on clean, curated datasets. In deployment, however, videos have usually passed through repost compression on social-media platforms and sometimes were captured by imperfect hardware. To measure detection under these conditions, we introduce Reality Perception Gap (RPG), a benchmark of 10,000 videos from frontier generators and partially synthetic edits, processed with cross-platform repost compression and paired with real footage that carries camera-side optical artifacts. RPG also includes socially fragile content, such as crime and wartime footage, where fabricated videos can cause severe social harm. Across 18 detectors, none catches more than 15% of fakes at a 1% false-positive rate. A positive control and a re-encoding sweep separate two sources of failure: generator and content shift degrades detectors before any compression, and repost compression erases the low-level traces that the artifact-based detectors relies on. Existing detectors therefore struggle when deployment conditions strip away the generation artifacts they rely on. These complementary failures suggest that robust detection requires training under deployment conditions and combining low-level, temporal, and semantic evidence, where passive detection may have reached its limits.
Nov 11, 2026

Honest Fusion Evaluation for Cross-Domain Deepfake Detection: Leakage Audits and Tail Robustness

Cross-domain video deepfake detection increasingly uses frozen foundation-model experts, combined by calibrated score averaging, a per-video router picking one expert, or a learned head over concatenated features. Expressive routing and feature fusion are often reported to beat plain averaging. Across a 22-dataset frozen-expert testbed, we find those gains are largely evaluation artifacts. A corner theorem locates the gap routing aims to close: because AUC depends only on score ordering, the best any score-space router can do is an oracle reading the test label to pick each video's expert, a ceiling no realisable, label-blind router reaches. The theorem does not order real routers against a calibrated global average; the case against routing is empirical, and no router we test beats that average. Feature fusion reads raw features, falls outside the theorem, and is audited empirically. Reported gains trace to leakage: holding out one dataset leaks siblings sharing identities and reals (over-crediting routing), while holding out one manipulation keeps that dataset's reals in training (over-crediting feature fusion). A 2×22\times 2 over fold and evaluation granularity pins the +2.6+2.6pp feature-fusion "win" to the fold alone: 12/12 significant under leaky folds vs. 0/12 under honest family-held-out folds, where both gains vanish. Fusion still pays off in the tail of hard videos and families: as experts are added, videos every expert misclassifies drop from 15.2% to 2.3%, and global calibrated fusion (InvB) beats the best single expert on worst-family AUC, selective risk (AURC), and low-false-positive recall, stably across protocols. Practitioners should calibrate and combine globally, hold out whole dataset families, and measure tail performance. For score-space routing under ranking metrics, honest evaluation and expert diversity matter more than combiner complexity.
Nov 11, 2026

Paired Geometric Supervision for Generalizable Deepfake Detection

We present OrthoPairGTL, a geometric training framework for cross-domain deepfake detection, built on a partially frozen DINOv3 backbone (∼\sim300M parameters), and make three contributions: (1) We re-evaluate six recent transfer-learning detectors (Forensics Adapter, Effort, three GenD variants and FakeSTormer) using the authors' released checkpoints under a single preprocessing pipeline across 17 cross-domain datasets (2018-2025), so that the reported gaps reflect method rather than per-method pipeline tuning. (2) We model the transformation between paired real and fake samples, training Parameter-Efficient Fine-Tuning (PEFT) adapters with an orthogonal pair decomposition, hyperspherical regularisation, and (in the GSD-LoRA variant) a set-level coherence objective. (3) Under LoRA, this regularisation gives a more stable optimisation profile: GSD-LoRA's post-peak validation degradation is 4.2×4.2\times shallower than plain LoRA at the same parameter footprint, and the time-averaged validation AUC across training is 1.82 pp higher. On the 17 datasets, GSD-LoRA matches or exceeds every re-evaluated baseline (92.82% vs. 91.58% for the strongest; paired Wilcoxon signed-rank p=0.015p=0.015, 13/17 per-dataset wins), with the largest gains on modern reenactment-heavy benchmarks (DSv1.1, DSv2). Under strict parameter budgets, LayerNorm-only tuning (≈\approx0.03% of the backbone) is the most stable configuration and matches the strongest baseline with a mean of 91.97%.
Nov 10, 2026

Pulse or Provenance? What rPPG-Based Deepfake Detectors Learn

Remote photoplethysmography (rPPG) has been proposed as a physiological cue for deepfake detection, based on the premise that synthesized faces lack a genuine cardiac signal. We examine what rPPG-style detectors learn on Celeb-DF++ (22 forgery methods) and FaceForensics++ (FF++), using one identically sampled window per real and fake video. On talking-face forgeries, simple chrominance traces reach an AUC of 0.998, exceeding a dedicated rPPG extractor (0.87). Controlled experiments indicate that this signal is not physiological in origin. On fully synthesized forgeries, it is equally discriminative when extracted from background regions or from full frames without face detection, and it is concentrated above the 0.7 to 4 Hz heart-rate band. It is largely removed by shuffling frame order but persists after normalizing resolution, frame rate and encoding, and an independent reimplementation reproduces these findings. Removing high-frequency content makes most synthesized videos appear real, adding it makes real videos appear fake, and injecting a synthetic pulse has little effect. In controlled self-reenactment experiments with two generators, animating a face from a single frame introduces the same high-frequency signal, whereas reconstructing each frame from its own source does not. Face-based chrominance detectors trained on Celeb-DF++ classify over 99% of real FF++ videos as fake, indicating that they largely encode video source rather than manipulation, and a CLIP-based detector exhibits the same behavior. A frozen CLIP backbone matches or exceeds fusions of CLIP with rPPG and frequency features. Finally, we show that the official Celeb-DF and Celeb-DF++ splits share identities and source-video content between training and test, and that custom protocols reusing test videos and identities in training inflate weaker detectors by up to 0.30 AUC.
Nov 9, 2026

When Are Predictions Enough? An Evaluation Protocol for Frozen Expert Composition

Practitioners often combine independently trained models while keeping their weights frozen. These experts are commonly combined through their final predictions, although their internal features may retain useful information that those predictions omit. We ask when combining features improves on combining predictions, and how to make that comparison fair. We introduce a reusable evaluation protocol, apply it to 21 frozen deepfake detectors from DF40 (Yan et al., 2024), and audit how evaluation choices change the conclusions. The protocol uses strong prediction baselines, compares simple and larger feature combiners, varies architecture and training data separately, and reports results by held-out generator with train/test overlap controls. Under leave-one-generator-out evaluation, logistic regression on the features of six architecture-diverse experts improves macro AUROC by 0.081 over the best tested prediction combiner in each fold, with gains on seven of eight generators. The larger network shows no clear improvement over the linear model (approximately 3.5M versus 10K parameters), suggesting that access to richer information matters more than additional combiner capacity on this pool. Features may help when they retain information that the predictions omit and that transfers to new generators. Predictions may be enough when the strongest prediction baseline already performs well, while neither approach reliably compensates for poor expert transfer. Weakening prediction baselines on the overlap-affected standard split inflates the apparent feature advantage by up to 0.172 AUROC. Overlap-aware evaluation also changes the estimated gain, though the contrast does not isolate overlap. Results by generator and expert pool show where the advantage holds, weakens, or reverses. Without these controls, the same benchmark can support different conclusions.
Nov 9, 2026

MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection

Generalizing deepfake detection across facial manipulation and fully generated video remains challenging due to forgery traces varying with the manipulation method and scene content. Explicit spatial and temporal feature differences offer a way to capture this variation, but also respond to natural texture and motion, motivating their joint interpretation with appearance features. We investigate whether combining multiscale feature differences with adapted appearance representations improves detection across both forgery categories. We introduce Multiscale Appearance-Residual Streams (MARS), a two-path video detector. The residual path applies fixed spatial and temporal difference-of-Gaussians operators to frozen intermediate features and models the resulting differences alongside appearance context across frames. The semantic path adapts the encoder's normalization parameters for frame classification, and a clip-dependent gate combines their predictions. Under a shared protocol across seven datasets, MARS achieves the highest average AUROC of 91.43%, outperforming seven compared detectors. When trained on facial manipulations alone, MARS achieves 93.99% AUROC on GenVideo and 75.50% on DF26, demonstrating transfer to generated videos without generated-video training data. MARS also provides signed patch and frame contributions, whose faithfulness we evaluate through controlled spatial and temporal removal against random controls. MARS is publicly available for research: Project page: https://vectorinstitute.github.io/mars/ Github: https://github.com/VectorInstitute/mars
Nov 9, 2026

MoSTE: Mixture of Spatio-Temporal Experts for Deepfake Detection in Videos

Generalizable deepfake video detection remains challenging because forgery artifacts vary substantially across manipulation types and often combine diverse spatial and temporal inconsistencies. Existing parameter-efficient adaptation methods typically rely on a single shared representation, rendering them prone to manipulation-specific bias and limiting transfer to unseen forgeries. To address this challenge, we propose Mixture Of Spatio-Temporal Experts (MoSTE), an adaptation framework that enables conditional specialization of forensic representations. Instead of forcing one adapter to model all forgery patterns, MoSTE decomposes adaptation into parallel spatial and temporal expert pools and dynamically routes tokens to the most relevant experts through an unsupervised token-level routing mechanism. This allows experts to naturally specialize in complementary forgery cues without requiring explicit manipulation labels or multi-stage training, while effectively transferring representations from CLIP to the video domain. Extensive experiments across cross-dataset and cross-manipulation benchmarks demonstrate that MoSTE sets a new state of the art in average generalization while preserving strong performance across diverse manipulation families. Additional analysis of expert routing and attention behavior reveals the emergence of expert diversity, suggesting that MoSTE learns complementary spatio-temporal forensic features. Code is available at https://github.com/charbelyah/MoSTE
Nov 6, 2026

Beyond Frame-Level Accuracy: Analyzing Video-Level Stability in Transformer-Based Deepfake Forensics

Deepfake videos generated by advanced generative models pose serious threats to digital security, misinformation control, and media forensics. Although numerous detection methods have been proposed, their reported performances are often based on heterogeneous preprocessing pipelines, inconsistent data splits, and model-specific training protocols, hindering fair architectural comparison. This work presents a controlled and reproducible comparative study of convolutional neural networks (ResNet-18 and EfficientNet-B0) and a transformer-based architecture (ViT-B/16) within a unified, face-centric deepfake detection framework. All models are trained using identical preprocessing, augmentation, optimization settings, and data splits on Celeb-DF v2 and FaceForensics++, and results are validated across three independent random seeds with bootstrapped confidence intervals. Experimental results show that while CNN-based models perform competitively at the frame level, their performance degrades after video-level aggregation. In contrast, ViT-B/16 demonstrates more stable video-level performance, achieving 92.8% [95% CI: 91.7--94.0] video-level accuracy and an AUC of 0.950 [95% CI: 0.934--0.964] on Celeb-DF v2 (3-seed bootstrapped). Cross-dataset evaluation across the same three random seeds reveals a large, asymmetric generalization gap (AUC 0.79 FF++→\rightarrowCeleb-DF vs. 0.64 Celeb-DF→\rightarrowFF++), indicating that in-domain video-level stability does not transfer to unseen manipulation domains. These findings indicate that global self-attention improves robustness and video-level stability for deepfake detection within a given data domain, while highlighting the need for further work on cross-domain generalization.
Nov 5, 2026

UniGADD: Universal Generator-Agnostic Deepfake Detector

In this paper, we introduce Universal Generator-Agnostic Deepfake Detector (UniGADD), a novel method that employs supervised learning to achieve high accuracy on known deepfake generators, while maintaining robust performance on previously unseen ones. The proposed approach follows a two-stage optimisation process. In the first stage, a contrastive loss encourages the model to learn discriminative feature embeddings from real and known fake images, resulting in strong performance within the training domain. In the second stage, the embedding space is refined by promoting inter-cluster separation and intra-cluster compactness, applied exclusively to real samples. This refinement enhances generalisability, enabling the method to exhibit improved robustness against unseen deepfake generation techniques. UniGADD achieves accuracy on par with state-of-the-art methods for known generators, while significantly outperforming them on unseen cases, demonstrating its scalability and practical applicability for adversarial content detection.
Nov 4, 2026

DeepfakeGenome: Toward Next-Generation Deepfake Attribution

In recent years, AIGC technologies are capable of generating hyper-realistic forged facial images, posing severe threats to facial security safety. To tackle these challenges, early Deepfake research primarily centered on real-fake classification. Recently, growing efforts have been devoted to the Deepfake Attribution (DFA) of generated content. Nevertheless, existing research on Deepfake detection and attribution faces saturated performance in binary classification, limited diversity in datasets and algorithms, and imperfect evaluation protocols, which severely impede practical application. To address these limitations, we propose a comprehensive deepfake detection and attribution benchmark named DeepfakeGenome (DFG). It contains 100 facial forgery algorithms and 2M images in total, achieving 4x to 100x larger than prior DFA benchmarks. We further design 4 protocols for practical evaluation, including a novel retrieval-based attribution paradigm. Unlike previous open-set evaluation metrics, the proposed retrieval metrics are more aligned with the real-world active defense situation of blacklist registration mechanisms. Based on these elaborate designs, we investigate the performance ceiling of deepfake attribution task. Over 2k experimental evaluations are conducted, and 10 insightful findings are derived. We believe this work can provide new insights into the DFA research field. The Code and Benchmark of DFG are avaliable on https://huggingface.co/spaces/DeepfakeGenome/DFG_Page.
Nov 1, 2026

Detecting Generated-Depth Injection Attacks on RGB-D Place Authentication

Advances in monocular depth estimation (MDE) now let an attacker generate depth from publicly available RGB images and submit forged RGB-D queries. Such attacks break a core assumption of RGB-D place authentication: that depth comes from a sensor. We study a presentation attack detection (PAD) classifier that uses geometric consistency between the enrollment and query views, as a software-layer defense. A three-stage evaluation shows how far this classifier detects software-injected depth, depending on how accurately the attacker knows the camera intrinsics. In the first stage, the attacker has only an estimate of the intrinsics, and the PAD classifier separates forgeries generated by all three MDE models with a validation area under the receiver operating characteristic curve (AUC) of 0.997-0.999. In the second stage, the attacker obtains the exact intrinsics, and the original PAD classifier falls to near chance (AUC 0.54-0.61); a retrained PAD classifier, however, still has the registration residual between enrollment and query as a cue. In the third stage, an oracle evaluation, in which the evaluator fits warps using the ground-truth 3D geometry, shows that detection falls to near chance only in its strongest case, where every valid query keypoint is given its ground-truth 3D coordinate. Of the detection cues, the reprojection error captures the attacker's misestimate of the intrinsics, whereas the registration residual remains even when the attacker knows the exact intrinsics.
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.
Oct 27, 2026

Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage

Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical spoofing, and is carried not only by images but also by videos. Despite substantial progress, a unified anti-forgery foundation model covering such a broad threat spectrum remains absent. In this paper, we present Venus-DefakerOne2, which substantially extends the forensic capability boundary along both the forgery-form and media-type dimensions. Trained on tens of millions of open-source and in-house samples, it incorporates two key designs. Tide-Style-Tuning alternates LoRA and full-parameter fine-tuning to balance computational efficiency, generalization, and hard-sample fitting while mitigating catastrophic forgetting. Entropy-based Test Adaptation determines the optimal prediction modality by analyzing prediction entropy. Venus-DefakerOne2 achieves new state-of-the-art performance across a comprehensive suite of benchmarks, including DeepFake faces (96.7%), AI-generated images (93.3%), tampered documents (87.6%), manipulated natural images (89.6%), physical spoofs (93.1%), and AI-generated videos (96.0%). It significantly outperforms both specialized expert models and its predecessor, DefakerOne, establishing itself as a powerful and versatile foundation model for binary-decision forensic tasks.
Oct 27, 2026

FYC: FPR-Disparity Weight Perturbation and Youden Calibration for Fair Deepfake Detection

Deepfake detectors routinely achieve high aggregate accuracy while exhibiting substantial demographic disparities in their errors: false-positive rates differ by double digits across gender and skin tone. Most existing remedies require either full retraining with a fairness-aware objective or demographic-annotated training data, both impractical when only a pretrained checkpoint is available, while label-free post-hoc calibrators leave the detector's weights unchanged. We introduce FYC (FPR-disparity Weight Perturbation and Youden Calibration), a two-stage post-hoc method that perturbs a detector's weights under an FPR-disparity criterion, then calibrates a separate decision threshold for each demographic group - requiring no architectural changes and no full retraining. Evaluated against every detector benchmarked on AI-Face v2 across six intersectional gender x skin-tone groups, FYC outperforms the field on 18 of 21 reported fairness and utility metrics, including purpose-built fairness architectures, at a fraction of the training cost. We further identify why the choice of fairness criterion is critical: the original Demographic Parity objective used in prior weight-perturbation work is architecture-dependent and unpredictable, improving two of four evaluated architectures, leaving a third largely unchanged, and substantially degrading the fourth (PG-FDD), with no way to anticipate the outcome for a given checkpoint in advance. Conditioning the same objective on real images only - our FPR-disparity criterion - eliminates this unpredictability, improving fairness and accuracy jointly across all four architectures with no exceptions.
Oct 27, 2026

Intersectional Invariant Learning for Fair Deepfake Detection

Deepfake detection models achieve high overall accuracy but exhibit large performance disparities across demographic groups, causing some groups to experience substantially higher false-positive rates than others. Existing fairness-aware methods address this by constraining model outputs to equalize group predictions, but do not tackle the underlying feature-level bias. As a result, models may still rely on demographic characteristics, such as skin texture, as indirect cues for detecting manipulated content. To address this problem, we propose Intersectional Invariant Learning (IIL), a framework that improves feature learning rather than only adjusting model outputs. IIL alternates between identifying the most challenging demographic partitions and learning features that remain consistent across those partitions. The framework also includes a false-positive-rate fairness objective and group-balanced sampling across six gender x skin-tone intersectional groups. We evaluate IIL on a large-scale fairness benchmark containing over one million images, 10 baseline detectors, and 21 fairness and utility metrics. Results show that IIL achieves Pareto-optimal performance, simultaneously attaining an AUC above 99%, a false-positive rate under 2.5%, and the lowest intersectional fairness disparity (FMEO) among all compared methods. IIL outperforms prior fairness-aware methods on the large majority of the 21 evaluation metrics, while reducing both false-positive rates and intersectional fairness disparities by several-fold compared with the strongest competing method.
Oct 27, 2026

PairCLIP-SWA: Similarity-Guided Balancing and Stochastic Weight Averaging for Generalized Deepfake Image Detection with OpenCLIP

Deepfake detectors are almost always deployed as the single checkpoint that scored best on a validation split, yet the reliability of that choice is rarely measured. We measure it with PairCLIP-SWA, a single-backbone detector that adapts an OpenCLIP ViT-L/14 visual tower by progressive block unfreezing on a class-balanced corpus built by CLIP-similarity-guided one-to-one subsampling, and averages the fine-tuning trajectory in weight space. Trained in-domain on the IEEE SP Cup 2025 (DF-Wild-Cup) benchmark under the same protocol as the strongest published three-backbone ensemble, the weight-averaged detector reaches 97.04% accuracy, 98.64% AU-ROC and a 4.07% equal error rate, against 94.46%, 97.60% and 5.00%. Its training log shows why averaging matters: over the averaged epochs the non-averaged checkpoint swings across 5.34 points of validation accuracy while its validation loss more than doubles, whereas the average is never worse and is up to 5.99 points better. On an OpenForensics-derived benchmark the same instability becomes a misranking: the checkpoint that validation accuracy selects (98.43%) scores 88.85% on a disjoint 10,905-image test partition, rejecting 21.1% of genuine photographs, while the terminal average, ranked last on validation, scores 94.76%. A study of twenty-two in-house configurations on the identical DF-Wild-Cup split, including preprocessing ablations, shows that CLIP pre-training rather than ensembling drives accuracy, that secondary face cropping costs about 34 points, and that frequency-domain inputs transfer poorly. We recommend per-class selection criteria measured off the early-stopping split.
Oct 27, 2026

ARISE: Authentic Reference-Informed Stability Enhancement for Continual Multimodal Forgery Detection

Multimodal forgery detection is commonly studied under a static assumption: training attacks are expected to approximate those encountered after deployment. This assumption becomes increasingly fragile as generators, editing systems, and multimodal large language models continually introduce new forgery mechanisms and forensic evidence. We formulate this problem as attack-incremental continual multimodal forgery detection, where the binary real/fake interface remains fixed while emerging attacks must be learned without forgetting previous ones. We introduce Fable-Bench, which organizes attack evolution through complementary joint-modality, text-side, and image-side protocols. We further propose ARISE (Authentic Reference-Informed Stability Enhancement), motivated by the open-ended forged class and the comparatively reusable geometry of authentic content. ARISE fits a real-only Gaussian mixture model to projected authentic replay representations as a compact historical reference. Meanwhile, the proposed Gaussian-Responsibility-Aware Stability Preservation (GRASP) derives a sample-adaptive anisotropic metric that strongly constrains historically stable representation directions while retaining plasticity elsewhere. Our Vulnerability-Aware Replay (VAR) further estimates stage-wise vulnerability from authentic-density degradation, forged-to-authentic boundary confusion, and authentic-mode occupancy drift, then assigns bounded replay emphasis to fragile stages. All adaptive signals are obtained from training-time replay statistics, while inference uses only the original multimodal backbone and binary classification head. Experiments across three attack-evolution protocols and multiple detector architectures demonstrate improved historical retention and final average performance over representative continual-learning baselines.
Oct 26, 2026

Temporal Slice Learning for AI-Generated Video Detection with 400×\times Fewer FLOPs

Recent advances in generative video models have improved visual realism, making detection increasingly dependent on subtle temporal inconsistencies. However, these signals are weak and spatially localized, while most of the video content is redundant. This creates a fundamental mismatch: existing detectors rely on heavy backbones to model full videos, which leads to high computational cost and limited scalability. In this work, we rethink AI-generated video detection from a representation perspective. Instead of modeling entire videos, we restructure them into compact temporal slice representations that isolate informative temporal evolution. We introduce a lightweight framework using frequency-aware temporal slice consistency learning, where informative spatial rows and columns are aggregated over time to form slice-domain inputs. This reparameterization suppresses redundant appearance while preserving discriminative temporal dynamics, enabling efficient and targeted detection. By constructing slices from both high- and low-frequency regions, our method exposes complementary temporal artifacts, including unstable details and abnormal motion smoothness. We instantiate this idea in a Temporal Slice Consistency Network, which integrates task-driven slice localization, hierarchical positional encoding, and a lightweight Transformer to model cross-slice and cross-frequency dependencies. We further introduce AI-Artist, a new benchmark with artist-curated videos from recent high-fidelity generators, including Seedance and Kling. Experiments on GenVideo and AI-Artist show that our method achieves strong performance while requiring over 400×\times fewer model-forward FLOPs and 3.6×\times faster model inference than the strong video-based baseline ReStraV (2.9×\times faster end to end, including preprocessing), enabling scalable and practical deployment.
Oct 22, 2026

Spectra: Multi-Scale Implicit Decomposition for Deepfake Detection

Deepfakes increasingly undermine trust in digital media, yet existing detectors often struggle to generalize across unseen manipulation techniques, compression levels, and dataset shifts. Most approaches rely on RGB appearance, frequency-domain artifacts, or their combination, learning cues present in the final synthesized image. While effective in-distribution, such cues are frequently generator-specific and can diminish as synthesis models evolve. We argue that a complementary perspective can be obtained through implicit neural representations (INRs), which expose how an image is reconstructed rather than merely how it appears. By fitting an INR to an image and analyzing its internal activations, one can reveal reconstruction dynamics that are difficult to observe in the image domain alone and may capture more intrinsic differences between genuine and synthetic content. To this end, we propose Spectra, a deepfake detection framework that combines semantic visual representations with artifact-aware cues derived from INR reconstruction. Spectra extracts multi-level reconstruction heatmaps from image-specific INRs and jointly models them with semantic features through a bidirectional fusion mechanism. This enables direct interaction between image semantics and reconstruction artifacts, allowing the model to identify forgery cues that are less dependent on specific generation pipelines. Extensive experiments on multiple deepfake benchmarks demonstrate improved robustness and cross-dataset generalization, consistently outperforming detectors based solely on RGB appearance or semantic representations. Furthermore, we show that the proposed representation extends beyond deepfake detection to face presentation attack detection, highlighting its potential as a unified framework for facial attack detection.
Oct 22, 2026

MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition

Despite recent advances, deepfake detectors remain vulnerable to adversarial examples, particularly in diverse, real-world settings. We propose MIG-COW, a novel adversarial attack framework that generates highly generalizable and visually imperceptible adversarial examples. By combining momentum-integrated gradients with a consensus-orthogonal decomposition, MIG-COW captures both shared and model-specific vulnerabilities across heterogeneous CNN and ViT detectors. On the AADD-2025 Challenge benchmarks, MIG-COW achieves a 99.96% white-box attack success rate (ASR) with high perceptual similarity (SSIM), significantly outperforming existing baselines. However, its limited 7.16% ASR against official black-box targets - despite achieving the best overall score - highlights the ongoing challenge of transferability. We also demonstrate that incorporating low-performing but diverse models in the ensemble can degrade attack effectiveness, underscoring the need for careful surrogate model selection in real-world adversarial settings.
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.
Oct 21, 2026

Beyond Shortcut Learning: Hierarchical Spatial Prototype Regularization for Face Forgery Detection

Recent advances in generative models have enabled highly realistic face forgeries, yet generalizing deepfake detectors to unseen manipulation pipelines remains a major challenge. One critical yet underexplored issue is that the learned forensic representation itself may fail to remain stable across different manipulation sources. In this paper, we provide new evidence that naively fine-tuned vision models suffer from severe forensic representation collapse: their extracted cues are often entangled with unstable, dataset-specific artifacts, resulting in structurally fragile representations and poor cross-domain generalization. Leveraging this insight, we propose Hierarchical Spatial Prototype (HSP) regularization, which explicitly models the forgery manifold by learning a structured prototype subspace over spatial features. We further introduce prototype orthogonality and second-order assignment balance, which jointly preserve the geometric independence of latent forgery factors and promote high-effective-rank utilization of the forensic representation, thereby reducing reliance on dataset-specific shortcuts. Empirical results demonstrate that our method substantially improves generalizability, yielding average frame-level AUC gains of 5.6% and 5.3% in the cross-dataset and cross-manipulation settings, respectively. Moreover, when used as a plug-in module, HSP boosts the average video-level AUC of existing state-of-the-art detectors to 95.3% (+1.8%). These results demonstrate the practical value of HSP as an easy-to-adopt regularization module for enhancing deepfake detectors.
Oct 16, 2026

From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images

Generative models for deepfakes have rapidly evolved from GAN-based architectures to diffusion models and multimodal large language models (MLLMs). However, empirical research on human performance in detecting deepfake face images has not kept pace. It remains unclear if (and how) detection performance varies across generative models and whether model-specific training improves detection more effectively than general-purpose training. In this paper, we propose the Deepfake Face Artifact Taxonomy (DFAT), a cross-model taxonomy of human-recognizable visual artifacts in deepfake face images, based on which we build both general-purpose and model-specific training materials. Through an online experiment (n=524n = 524), we examined human performance in detecting deepfake face images and evaluated training efficacy across five representative generative models: three GAN-based, one diffusion-based, and one MLLM (GPT-5). Our results show that participants' detection accuracy was strongly model-dependent and that images generated by more recent and advanced models were not necessarily harder to detect. After training, participants achieved significant performance gains across most conditions, and their improvement varied by model. Notably, model-specific training generally yielded greater numerical gains than general-purpose training. In a five-month follow-up test (n=342n = 342), we observed no significant decline in detection accuracy and no significant increase in perceived stress. Overall, our findings provide actionable insights for designing effective, sustainable, and targeted training programs to counter the growing threat posed by deepfakes.
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.
Oct 15, 2026

An Agentic ENF Framework for Forensic Video Authentication Against Generative AI

Generative models now synthesise video that is hard to distinguish from genuine footage, and learned detectors that key on a generator's artefacts degrade sharply on unseen models. This paper develops a forensic framework that authenticates video by a signal that generation does not control: the electric network frequency (ENF), the mains-driven hum in audio and flicker in video. A unified two-channel detector extracts the ENF from audio and from rolling-shutter video through one second harmonic estimator and a shared network; a synthetic-injection training method, driven by an Ornstein-Uhlenbeck drift model and anchored to real recordings, overcomes the scarcity of labelled ENF data; a reference-matching channel verifies a claimed time of recording and recovers an unknown one; and a two-axis agentic orchestrator fuses recording authenticity with content-manipulation evidence under an asymmetric rule, escalating expensive detectors only when needed. A central finding reframes the task: an ENF-band flicker is present in generated video at a prominence indistinguishable from real footage, so its presence is not proof of authenticity, and authentication must rest on consistency with an independent reference rather than on presence. On held-out real recordings the detector accepts genuine audio and video at 93% and 100% against naive baselines of 53% and 15%; claimed-time authentication reaches an area under the curve of 1.0; and the agentic cascade matches a flat ensemble while cutting wall-clock time by 54% and frames decoded by 64%, without loss of accuracy.
Oct 15, 2026

Time to Fake It: Continual Machine Learning Intensifies Unfairness in Deepfake Detection

Deepfake detectors safeguard against misinformation, rendering their failures as much a societal as a technical concern. As generators constantly evolve, detectors trained on static datasets miss newly arising threats, while progressive training interferes catastrophically. Yet, mitigating forgetfulness in terms of accuracy, the prevalent focus of continual learning (CL), is insufficient to reflect real-world impact. We therefore scrutinize the effects of CL methods with respect to evolving fairness. To this end, we analyze four dimensions of fairness across diverse demographics for detectors trained progressively on a chronological sequence of 11 real-world deepfake generation methods. Tracking fairness metrics over time, we expose non-trivial interplays between performance and fairness that depend on both the choice of CL algorithm and demographic intersections. We find accuracy degradation to typically exacerbate unfairness and, conversely, fairness improvements to remain scarce over time. Dissecting the CL method families (rehearsal, prompts, regularization), we observe that inequitable forgetting is not explained by underrepresentation alone, but likely entangled with representation learning. We thus issue a call to action for CL methods to take social outcomes into account when balancing the stability-plasticity tradeoff.